Agricultural product cold chain temperature control adaptive adjustment method and system based on soil data

Abstract

The invention relates to the technical field of cold-chain logistics transportation control, in particular to an agricultural product cold-chain temperature control self-adaptive adjusting method and system based on soil data. The method comprises the following steps that historical soil monitoring records are matched by analyzing geographical location information of a producing area, soil physicochemical feature vectors are generated, physiological characteristic data of agricultural products are calculated through the vectors, a temperature-tolerant area set is determined, damage weighted optimization analysis is carried out in combination with the loading capacity, and a reference set temperature value is determined; and generating a compartment temperature field distribution diagram according to the reference temperature, calculating a temperature deviation degree vector, and matching each batch of agricultural products into the temperature field distribution diagram according to the deviation degree vector to generate a spatial layout topology. By establishing a soil data driven agricultural product physiological characteristic recognition system, a dynamic temperature optimization mechanism and a compartment space temperature resource intelligent allocation technology, the problem of temperature conflict in mixed loading and transportation of agricultural products in multiple producing areas is solved, and self-adaptive temperature control of cold chain transportation is realized.

Description

Technical Field

[0001] This invention relates to the field of cold chain logistics transportation control technology, and in particular to an adaptive temperature control method and system for agricultural products based on soil data. Background Technology

[0002] Current cold chain transportation systems generally adopt a standard temperature setting based on the type of agricultural product when handling mixed shipments of agricultural products from different origins, completely ignoring the decisive role of the soil environment in the intrinsic physiological characteristics of agricultural products. For example, tomatoes grown in saline-alkali soil have stronger frost resistance due to their higher cell sap concentration, while tomatoes grown in organic-rich soil have more vigorous respiration and require lower storage temperatures. However, current technology cannot identify these differences, resulting in some agricultural products suffering chilling injury or excessively rapid rotting under uniform temperatures.

[0003] Current refrigerated truck temperature control systems only focus on controlling the overall temperature uniformity, failing to recognize that the temperature gradient distribution naturally present inside the truck due to the refrigeration system layout is a usable resource. The temperature is lower at the front of the truck near the air outlet and higher at the rear near the air return outlet. This 2-3°C temperature difference can be used to meet the differentiated temperature requirements of different agricultural products, but current technology treats this as an unevenness that needs to be eliminated rather than a usable spatial resource.

[0004] Current cold chain transportation lacks a dynamic temperature adjustment mechanism during multi-site loading. Typically, a fixed temperature is set and maintained before loading begins. As vehicles load agricultural products from different origins sequentially, the combination of agricultural products inside the compartment changes continuously, and the optimal overall temperature should also be adjusted accordingly. However, current technology cannot optimize the temperature in real time based on the actual loading conditions, resulting in later-loaded agricultural products being placed in an unsuitable temperature environment.

[0005] In summary, existing technologies have several problems that urgently need to be addressed, including the inability to accurately control temperature based on differences in production location, the inability to fully utilize the temperature resources of the vehicle compartment, and the inability to adapt to dynamic loading processes. Summary of the Invention

[0006] Therefore, it is necessary to provide an adaptive temperature control method and system for agricultural product cold chain based on soil data to solve at least one of the above-mentioned technical problems.

[0007] To achieve the above objectives, an adaptive temperature control method for agricultural product cold chain based on soil data is proposed, comprising the following steps:

[0008] Step S1: Access the vehicle's loading plan and parse the geographical location information of each production area. Match the corresponding historical soil monitoring records based on the geographical location information, and filter and weight the historical soil monitoring records to generate soil physicochemical feature vectors.

[0009] Step S2: Calculate the physiological characteristic data of each batch of agricultural products using soil physicochemical feature vectors. The physiological characteristic data includes cell sap osmotic pressure data, basal respiration calorific value, and cell wall strength index. Determine the minimum safe temperature based on the cell sap osmotic pressure data. Determine the maximum safe temperature based on the basal respiration calorific value and cell wall strength index. Combine the minimum safe temperature and the maximum safe temperature to generate a set of tolerance temperature zones.

[0010] Step S3: Obtain the loading amount of each batch of agricultural products, combine it with the set of tolerable temperature zones to perform weighted optimization analysis of agricultural product damage, and determine the benchmark set temperature value;

[0011] Step S4: Generate a temperature field distribution map of the carriage based on the baseline set temperature value; calculate the temperature deviation vector based on the difference between the set of tolerable temperature zones and the baseline set temperature value; match each batch of agricultural products to the temperature field distribution map of the carriage based on the temperature deviation vector to generate the cargo space layout topology.

[0012] This invention transforms historical soil monitoring records from production areas into quantifiable physicochemical characteristic vectors of agricultural products' inherent constitution. By utilizing key indicators such as soil salinity and organic matter, it extrapolates the osmotic pressure and respiration heat characteristics of each batch of agricultural products, thus breaking free from the constraints of traditional general standards and achieving personalized definitions of the lower limit of cold resistance and the upper limit of heat resistance for agricultural products. By introducing a global damage minimization optimization mechanism based on loading volume, it scientifically resolves the temperature demand conflicts between different batches in multi-production area mixed loading scenarios, establishing a benchmark operating state with the lowest physiological loss for the entire vehicle. Furthermore, it creatively utilizes the inherent airflow temperature rise gradient of the cargo compartment to construct a three-dimensional thermal field distribution, transforming temperature differences, which were originally considered defects, into usable partitioned resources. Through cargo space layout topology generation driven by temperature deviation vector, it achieves adaptive temperature regulation, significantly reducing the hidden chilling injury and metabolic decay losses caused by soil environmental differences.

[0013] Preferably, the present invention also provides an adaptive temperature control system for agricultural product cold chain based on soil data, used to execute the adaptive temperature control method for agricultural product cold chain based on soil data as described above, the adaptive temperature control system for agricultural product cold chain based on soil data includes:

[0014] The origin habitat characteristic quantification module is used to access the vehicle loading plan and analyze the geographical location information of each origin. Based on the geographical location information, it matches the corresponding historical soil monitoring records, filters and weights the historical soil monitoring records, and generates soil physicochemical characteristic vectors.

[0015] The physiological tolerance boundary extrapolation module is used to calculate the physiological characteristic data of each batch of agricultural products using soil physicochemical feature vectors. The physiological characteristic data includes cell sap osmotic pressure data, basal respiration heat value and cell wall strength index. The minimum safe temperature is determined based on the cell sap osmotic pressure data. The maximum safe temperature is determined based on the basal respiration heat value and cell wall strength index. The minimum safe temperature and the maximum safe temperature are combined to generate a set of tolerance temperature zones.

[0016] The global thermal balance optimization module is used to obtain the loading amount of each batch of agricultural products, combine it with the set of tolerance temperature zones to perform weighted optimization analysis of agricultural product damage, and determine the benchmark set temperature value.

[0017] The three-dimensional spatial matching module is used to generate a temperature field distribution map of the carriage based on the benchmark temperature value; calculate the temperature deviation vector based on the difference between the set of temperature-tolerant zones and the benchmark temperature value; and match each batch of agricultural products to the temperature field distribution map of the carriage based on the temperature deviation vector to generate the cargo spatial layout topology.

[0018] The soil data-based adaptive temperature control system for agricultural products in the cold chain, provided by this invention, transforms static historical soil monitoring data into dynamic physiological tolerance indicators for agricultural products through the collaborative work of a habitat characteristic quantification module and a physiological tolerance boundary extrapolation module. This defines the frost and heat resistance boundaries for agricultural products from different origins, overcoming the limitations of empirical values. Combined with a global thermal balance optimization module, it can automatically calculate the baseline operating state with the minimum weighted physiological loss for the entire vehicle in complex scenarios involving multiple batches of mixed loading, effectively resolving temperature conflicts between different goods. Furthermore, by integrating a three-dimensional space matching module, it transforms the previously difficult-to-eliminate airflow temperature gradient within the vehicle compartment into usable partitioned storage resources. By generating three-dimensional spatial layout instructions, it achieves adaptive temperature control for agricultural products in the cold chain, constructing an intelligent cold chain temperature control system capable of responding to loading changes in real time and significantly reducing transportation losses. Attached Figure Description

[0019] Figure 1 A flowchart illustrating an adaptive temperature control method for agricultural product cold chain based on soil data, provided in an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of the damage minimization optimization curve provided in an embodiment of the present invention. Detailed Implementation

[0021] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0022] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0023] It should be understood that the term “and / or” as used herein includes any and all combinations of one or more of the associated items listed.

[0024] In this embodiment of the invention, reference Figure 1 The diagram shown is a flowchart illustrating the steps of the adaptive temperature control method for agricultural product cold chain based on soil data according to the present invention. In this example, the adaptive temperature control method for agricultural product cold chain based on soil data includes the following steps:

[0025] Step S1: Access the vehicle's loading plan and parse the geographical location information of each production area. Match the corresponding historical soil monitoring records based on the geographical location information, and filter and weight the historical soil monitoring records to generate soil physicochemical feature vectors.

[0026] In this embodiment of the invention, the system parses the agricultural product category code and geographical coordinates of the place of origin in the loading plan, selects the core soil index set such as nitrogen, calcium and salinity from historical soil monitoring records according to the preset physiological response association rules, then performs interval normalization on the index values ​​to generate a standardized soil parameter set, and combines the water sensitivity weight and structure sensitivity weight of the corresponding category for weighted synthesis, and finally outputs the soil physicochemical feature vector that quantifies the impact of the place of origin environment.

[0027] Step S2: Calculate the physiological characteristic data of each batch of agricultural products using soil physicochemical feature vectors. The physiological characteristic data includes cell sap osmotic pressure data, basal respiration calorific value, and cell wall strength index. Determine the minimum safe temperature based on the cell sap osmotic pressure data. Determine the maximum safe temperature based on the basal respiration calorific value and cell wall strength index. Combine the minimum safe temperature and the maximum safe temperature to generate a set of tolerance temperature zones.

[0028] In this embodiment of the invention, based on the soil physicochemical characteristic vector, the cell sap osmotic pressure data, basal respiration heat value, and cell wall strength index of agricultural products are calculated using linear regression and exponential growth models; the theoretical freezing point is calculated using osmotic pressure data and van der Hoff adjustment coefficient, and a safety margin is added to determine the minimum safe temperature; the maximum safe temperature is determined using the temperature compensation value converted from the basal respiration heat value and the cell wall strength index; finally, the two are combined and corrected to generate the set of temperature tolerance zones for this batch of agricultural products.

[0029] Step S3: Obtain the loading amount of each batch of agricultural products, combine it with the set of tolerable temperature zones to perform weighted optimization analysis of agricultural product damage, and determine the benchmark set temperature value;

[0030] In this embodiment of the invention, the tolerance temperature range set and loading amount of all batches of agricultural products in the carriage are summarized in real time, a batch temperature range data table is constructed and a loading weight coefficient group is calculated; when there is no common intersection of the temperature ranges of each batch, an optimization process based on damage minimization is triggered, by traversing the simulated temperature points and calculating the weighted total damage value of the whole vehicle including the asymmetric cold and heat damage weights, the temperature point with the minimum total damage is selected as the optimal equilibrium temperature, thereby determining the reference set temperature value of the refrigeration unit.

[0031] Step S4: Generate a temperature field distribution map of the carriage based on the baseline set temperature value; calculate the temperature deviation vector based on the difference between the set of tolerable temperature zones and the baseline set temperature value; match each batch of agricultural products to the temperature field distribution map of the carriage based on the temperature deviation vector to generate the cargo space layout topology;

[0032] In this embodiment of the invention, a temperature field distribution map of the carriage containing a three-dimensional temperature difference distribution is constructed based on the benchmark temperature value and the temperature rise gradient of the airflow in the carriage. At the same time, the difference between the ideal temperature of each batch and the benchmark value is calculated to generate a temperature deviation vector. According to the principle of minimizing error priority, each batch of agricultural products is matched to a specific temperature zone in the carriage. When the capacity of a single temperature zone is insufficient, the overflow allocation logic is activated to generate a capacity balancing scheme. Finally, the cargo space layout topology with the air outlet of the carriage as the origin and containing a clear length, width, height and coordinate interval is output.

[0033] Preferably, step S1 includes:

[0034] Identify agricultural product classification identifiers in the loading plan, invoke pre-set physiological response association rules, and extract the core soil indicator set corresponding to the agricultural product classification identifiers from historical soil monitoring records;

[0035] The values ​​of the core soil index set are normalized by interval to generate a standardized soil parameter set.

[0036] Based on the preset moisture sensitivity weight and preset structure sensitivity weight corresponding to the agricultural product classification labels, the standardized soil parameter set is weighted and calculated to synthesize the soil physicochemical feature vector.

[0037] In one specific implementation, the system first parses the received loading plan and identifies the coding information related to the agricultural product category. Based on a pre-set physiological response association rule base, it determines the feature fields to be extracted according to the identified category code. For example, when the loaded product is identified as leafy vegetables, "nitrogen content," "organic matter content," and "pH value" are locked as feature fields; when the loaded product is identified as solanaceous vegetables, "calcium content," "potassium content," and "salt content" are locked as feature fields. Then, based on the geographical coordinate index of each production area, the system retrieves the latest monitoring data of the corresponding plot from the historical soil monitoring records of the agricultural big data platform, and retains only the values ​​of the locked feature fields to form a core soil index set.

[0038] To eliminate differences in dimensions and orders of magnitude among different soil indicators, interval normalization was performed on the values ​​of each item in the core soil indicator set. Specifically, for each indicator, the historical maximum and minimum values ​​of that indicator in the corresponding production area were obtained as interval boundaries. A linear mapping algorithm was used to convert the current measured value into a dimensionless value between 0 and 1, thereby generating a standardized set of soil parameters. For example, if the soil salinity content of a certain plot is 8.2 g / kg, and the historical baseline range for that area is 0 to 10 g / kg, then the normalized parameter value is 0.82.

[0039] Subsequently, the system performs weighted synthesis based on the varying sensitivities of different agricultural product categories to environmental factors, using preset weighting parameters. The system pre-defines moisture sensitivity weights and structural sensitivity weights for each agricultural product category. The moisture sensitivity weight reflects the influence of soil indicators on the moisture content and osmotic pressure of the agricultural product, while the structural sensitivity weight reflects the influence of soil indicators on cell wall hardness and pericarp toughness. Each parameter in the standardized soil parameter set is multiplied by its corresponding weighting coefficient, summed, and arranged according to a predetermined vector dimension order to synthesize a multidimensional soil physicochemical characteristic vector. This vector typically contains values ​​for three dimensions: osmotic pressure, metabolism, and structure, serving as the quantitative basis for subsequent assessments of the physiological tolerance of agricultural products.

[0040] Preferably, determining the minimum safe temperature based on cell fluid osmotic pressure data in step S2 includes:

[0041] The osmotic pressure-related components in the soil physicochemical feature vector are extracted, and the cell sap osmotic pressure data are calculated using the transfer relationship between soil salinity and plant cell sap concentration.

[0042] Based on cell osmotic pressure data and a pre-set van der Hoff adjustment coefficient for the type of agricultural product, the freezing point depression is calculated, and the theoretical freezing point temperature is determined.

[0043] The minimum safe temperature is determined by adding a preset safety margin coefficient to the theoretical freezing point temperature.

[0044] In one specific implementation, the system first extracts the first dimension value from the soil physicochemical feature vector generated in the previous step as the osmotic pressure-related component. Based on soil science principles, there is a positive correlation between the soluble salt content in the soil and the concentration of cell sap absorbed by crop roots. Using a pre-set linear regression model, this osmotic pressure-related component is substituted into the calculation to obtain cell sap osmotic pressure data reflecting the concentration of liquid inside the agricultural product. This data is usually expressed in milliosmolar osmotic pressure (mOsm / L); a higher value indicates a higher solute concentration in the cell sap and stronger freeze resistance.

[0045] Next, the freezing point is calculated based on the colligative property principle of dilute solutions in physicochemistry. A preset van der Hoff adjustment factor matching the type of agricultural product being loaded is retrieved. This factor is a correction value for the standard van der Hoff factor, used to correct for colligative deviations in non-ideal solution environments. The cell sap osmotic pressure data is multiplied by this adjustment factor to calculate the freezing point depression, which is the decrease in the freezing point of the agricultural product's cell sap relative to pure water. Subsequently, this freezing point depression is subtracted from 0°C to obtain the theoretical freezing point temperature of the agricultural product. For example, if the calculated freezing point depression is 0.7°C, the theoretical freezing point temperature is -0.7°C.

[0046] Finally, to prevent irreversible freezing damage caused by localized overcooling during transportation, a protective threshold is set above the theoretical freezing point temperature. A preset safety margin factor is read, which is typically set based on the temperature control accuracy of the cold chain equipment (e.g., 2.5℃). The theoretical freezing point temperature is added to this safety margin factor; the sum is determined as the minimum safe temperature for this batch of agricultural products. This temperature value defines the lower limit of the allowable low temperature for this batch of goods during transportation; any ambient temperature below this value is considered to pose a risk of freezing damage.

[0047] Preferably, in step S2, determining the maximum safe temperature based on the basal respiratory calorific value and cell wall strength index, and combining the minimum and maximum safe temperatures to generate a set of tolerance temperature zones includes:

[0048] Extract the metabolic-related components from the soil physicochemical feature vector, and calculate the basic respiratory calorific value based on the metabolic-related components;

[0049] Extract the structure-related components from the soil physicochemical feature vectors, and calculate the cell wall strength index based on the structure-related components;

[0050] The baseline respiratory calorific value is converted into a respiratory temperature compensation value, and the maximum safe temperature is determined by combining it with the cell wall strength index.

[0051] The range consisting of the lowest and highest safe temperatures is offset and corrected using the breathing temperature compensation value to generate a set of tolerance temperature zones.

[0052] In one embodiment, the system extracts the second-dimensional metabolic component and the third-dimensional structural component from the soil physicochemical feature vector. For the metabolic component (primarily characterizing soil organic matter and nitrogen content), an exponential growth model is applied to calculate the postharvest metabolic rate potential of agricultural products, outputting a baseline respiration heat value reflecting the heat production capacity per unit mass. For the structural component (primarily characterizing soil calcium, silicon, and other mineral content), a linear weighted algorithm is used to assess the mechanical strength of fruit tissue, outputting a cell wall strength index that quantifies the degree of cell wall lignification.

[0053] Subsequently, based on the principle of thermodynamic equilibrium, the baseline respiration heat value is converted into a temperature-dimensional control index. Specifically, the additional temperature difference required to remove this respiration heat is calculated, resulting in a negative respiration temperature compensation value. Simultaneously, the cell wall strength index is used to define the upper limit of high-temperature tolerance. A higher cell wall strength index indicates stronger fruit softening resistance, thus a higher baseline temperature limit is set; conversely, a lower index results in a lower baseline temperature limit. This baseline upper limit temperature is then superimposed on the aforementioned respiration temperature compensation value to obtain the final maximum safe temperature. This value represents the highest ambient temperature that will not trigger respiration heat runaway or softening and decay.

[0054] Finally, a safe transportation temperature range for this batch of agricultural products is constructed. First, an initial temperature range is formed, with the determined minimum safe temperature as the lower limit and the maximum safe temperature as the upper limit. Considering the impact of high respiratory heat agricultural products on ambient temperature, the upper and lower boundaries of this initial range are synchronously offset and corrected (usually by downward shift) using respiratory temperature compensation values. The corrected closed range is then encapsulated as the set of tolerable temperature zones for this batch of goods. This set defines the dynamically suitable temperature range for this batch of agricultural products while simultaneously meeting the requirements for both freezing and spoilage prevention.

[0055] Preferably, step S3 includes:

[0056] In response to the loading completion signal of the vehicle at each loading station, identify the set of all batches of agricultural products that have been loaded in the current compartment;

[0057] Summarize the temperature tolerance ranges and loading volumes of all currently loaded batches of agricultural products, and generate a real-time batch temperature range data table;

[0058] Based on the proportion of each batch's loading volume to the current total loading volume, dynamically calculate the loading weight coefficient group;

[0059] Identify the intersection of temperature zones in each batch in the batch temperature zone data table. If no common temperature zone exists, trigger an optimization calculation process based on damage minimization to update the baseline set temperature value.

[0060] In one specific implementation, the system monitors the vehicle loading status in real time. Once a loading completion signal is received from a station, a new round of temperature decision-making is initiated. First, the electronic waybill is scanned to identify and lock the IDs of all batches of agricultural products currently located in the truck, constructing the current cargo set. For each batch in this set, its tolerance temperature zone set generated in the previous steps and the loading volume data obtained from real-time weighing are retrieved. This information is integrated and structured for storage, generating a real-time batch temperature zone data table.

[0061] To quantify the influence of each cargo batch on temperature decisions, a weighting calculation is performed. The total load capacity is calculated by summing the load capacities of all batches in the table. Then, the ratio of each batch's load capacity to the total load capacity is calculated; this ratio is the weighting coefficient for that batch. All batch weighting coefficients are compiled into a single loading weighting coefficient group to ensure that subsequent decisions tend to favor cargo with larger load capacities.

[0062] The core of the decision-making logic lies in finding the "greatest common divisor" of the temperature zone requirements for each batch. A mathematical intersection operation is performed on all temperature zone intervals in the batch temperature zone data table. If the result is not empty, meaning there exists a common temperature zone that is safe for all goods, the median of this common temperature zone is directly selected as the set temperature. If the result is an empty set, it indicates a temperature requirement conflict between the currently loaded goods (e.g., one batch requires [1℃, 3℃], and another batch requires [5℃, 8℃]), and a conflict resolution mode is immediately initiated, triggering an optimization calculation process based on damage minimization. This process aims to find a compromise temperature point through mathematical modeling, thereby updating the baseline set temperature value and achieving dynamic adaptive adjustment of the temperature control strategy as the loading process progresses.

[0063] Preferably, the optimization calculation process based on damage minimization includes:

[0064] A batch damage function set is constructed, and the batch damage function set defines the segmented calculation logic for each batch: when the temperature is below the lower tolerance limit, the damage value is calculated using the cold damage coefficient; when the temperature is above the upper tolerance limit, the damage value is calculated using the heat damage coefficient; and the value of the cold damage coefficient is greater than the value of the heat damage coefficient.

[0065] A step-size traversal is performed within a preset temperature range to generate several simulated temperature points;

[0066] For each simulated temperature point, the damage value of each batch of agricultural products currently loaded is calculated using the batch damage function group, and the weighted total damage value of the entire vehicle is calculated in combination with the loading weight coefficient group.

[0067] The simulated temperature point with the minimum weighted total damage value is selected as the optimal equilibrium temperature, and after stability verification, it is output as the benchmark set temperature value.

[0068] In one embodiment, the system first establishes a mathematical model to quantify the physiological damage to each batch of goods. For each batch, a piecewise batch damage function is defined: if the ambient temperature is within the batch's tolerance temperature range, the function output is zero; if the ambient temperature is below the lower limit of the temperature range, the function calculates the absolute value of the temperature difference multiplied by a preset chilling injury coefficient; if the ambient temperature is above the upper limit of the temperature range, the function calculates the absolute value of the temperature difference multiplied by a preset heat injury coefficient. Based on the physiological characteristics that freezing damage to agricultural products is irreversible while respiratory and metabolic damage can accumulate, the chilling injury coefficient is set to be significantly greater than the heat injury coefficient (e.g., 2.0 times), thereby constructing an asymmetric set of batch damage functions to ensure that the decision-making logic prioritizes avoiding low-temperature freezing damage.

[0069] Subsequently, within the controllable temperature range of the refrigeration unit (e.g., -2℃ to 15℃), a small scan step size (e.g., 0.1℃) is set, and a series of simulated temperature points are generated through discretization. These simulated temperature points are then substituted into the batch damage function set mentioned above to calculate the virtual damage value of each batch of goods at the current simulated temperature. Next, a loading weight coefficient set is introduced, and the virtual damage value of each batch is multiplied by its corresponding weight coefficient and summed to obtain the weighted total damage value of the entire vehicle at that simulated temperature point.

[0070] By iterating through all simulated temperature points and comparing them with the calculated weighted total damage value for the entire vehicle, the simulated temperature point corresponding to the minimum value is identified and marked as the optimal equilibrium temperature. Finally, this temperature undergoes engineering stability verification (e.g., avoiding areas with frequent compressor start-stop cycles). Once confirmed to be correct, it is locked and output as the baseline setpoint temperature. This value represents the compromise solution that minimizes overall loss while ensuring the safety of all goods in multi-batch temperature conflict scenarios.

[0071] Preferably, step S4, generating the temperature field distribution map of the carriage based on the reference set temperature value, includes:

[0072] Obtain the inherent physical structure parameters of the vehicle compartment and the air outlet, return air outlet and air volume parameters of the vehicle's refrigeration system to determine the airflow temperature gradient inside the vehicle compartment.

[0073] Using the baseline temperature value as the reference origin, and combining the airflow temperature rise gradient, the theoretical temperature of different longitudinal distance areas of the carriage is calculated;

[0074] Vertical temperature stratification correction and boundary effect compensation are performed on each longitudinal region to generate a temperature field distribution map of the carriage containing the actual temperature values ​​and spatial coordinate range of multiple temperature zones.

[0075] In one specific implementation, the system first reads pre-stored carriage configuration data, including the carriage's length, width, and height dimensions, the thermal resistance coefficient of the insulation layer, and the location of the refrigeration unit's air outlet (usually at the front top), return air outlet (usually at the rear bottom), and the rated air volume of the fan. Based on the principles of cold air jet attenuation and heat exchange, a one-dimensional steady-state heat transfer model is established to calculate the temperature rise rate of the cold air flowing along the length of the carriage, determining the airflow temperature rise gradient within the carriage (e.g., 0.3°C per meter).

[0076] Next, using the baseline set temperature value as the logical zero point (corresponding to the set value at the return air vent or temperature control probe location), the theoretical air temperature at different longitudinal sections inside the carriage is calculated using the airflow temperature gradient. Specifically, the carriage is divided into several virtual sections along its length (such as the front, middle, and rear sections), and the basic theoretical temperature of each section is calculated based on the distance between the center point of each section and the air outlet. Typically, the temperature in the front section, closer to the air outlet, is lower than the baseline value, while the temperature in the rear section, farther from the air outlet or closer to the door, is higher than the baseline value.

[0077] To improve the model's accuracy, a three-dimensional correction is further introduced. Considering the sinking of cold air and the heat leakage characteristics of the carriage walls, vertical temperature stratification correction (lower layers are cooler than upper layers) and boundary effect compensation are applied to each longitudinal section (reflecting the natural temperature rise near the side walls and doors, rather than actively adjusting it). After correction, the carriage space is discretized into several temperature difference units with clear three-dimensional coordinate ranges (X, Y, Z), and each unit is assigned a specific predicted temperature value, ultimately integrating them into a digital temperature field distribution map of the carriage. This map clearly maps the gradient distribution of the objectively existing "low-temperature zone" (usually located near the air vents), "stable temperature" (the middle of the carriage), and "temperature rise zone" (usually located near the doors or return air vents) within the carriage at the current set temperature.

[0078] Preferably, step S4, calculating the temperature deviation vector based on the difference between the set of tolerance temperature zones and the reference set temperature value, includes:

[0079] The ideal temperature set for each batch of agricultural products is calculated using the set of tolerance temperature zones.

[0080] Calculate the difference between the ideal temperature group of the batch and the reference set temperature value to generate a temperature deviation vector; a positive value in the temperature deviation vector indicates that the required temperature is higher than the reference set temperature value, and a negative value indicates that the required temperature is lower than the reference set temperature value.

[0081] In one specific implementation, the set of tolerable temperature zones for each batch of agricultural products is first analyzed. Based on preset preference rules (such as taking the midpoint of the interval or the golden section point close to the lower limit), the optimal storage temperature for each batch of goods is determined, forming a batch ideal temperature group. Subsequently, a difference calculation is performed, subtracting the baseline set temperature value from the ideal temperature of each batch. The calculation result constitutes a temperature deviation vector. Each element in this vector intuitively quantifies the personalized temperature difference requirement of the corresponding batch of goods relative to the overall baseline environment: a negative value means that the batch needs a colder environment than the baseline (a low-temperature zone needs to be found), and a positive value means that the batch needs a warmer environment than the baseline (a temperature rise zone needs to be found).

[0082] To achieve accurate placement, the system executes a spatial matching algorithm. It iterates through each temperature zone cell in the temperature field distribution map of the cargo compartment, calculates the absolute error between the predicted actual temperature and the ideal temperature for each batch, and constructs a two-dimensional temperature zone suitability matrix. In this matrix, rows represent cargo batches, columns represent cargo compartment temperature zones, and smaller element values ​​indicate a higher degree of matching.

[0083] Resource allocation logic is executed based on this matrix. The "cargo-temperature zone" pair with the smallest error in the matrix is ​​locked first, and the remaining physical space capacity of that temperature zone is checked. The batch loading quantity is compared with the temperature zone capacity; if the capacity is sufficient, it is locked directly; if the capacity is insufficient, overflow logic is activated, allocating the excess cargo to the next smallest temperature zone adjacent to the current temperature zone. Through this iterative filling method, a capacity balancing scheme covering all cargo is generated.

[0084] Finally, the scheme is translated into specific operational instructions. The X (length), Y (width), and Z (height) axis coordinate ranges of each target temperature zone in the carriage coordinate system are extracted. Combined with the cargo batch ID, a structured cargo spatial layout topology is output. This topology data is a set of explicit three-dimensional spatial instructions used to instruct loading and unloading equipment or personnel to place specific batches of agricultural products in designated locations such as the lower front section, upper middle section, or near the rear door of the carriage, thereby utilizing the physical temperature difference to compensate for the temperature difference required for physiological needs.

[0085] Preferably, in step S4, matching each batch of agricultural products to the temperature field distribution map of the carriage based on the temperature deviation vector to generate the cargo spatial layout topology includes:

[0086] Calculate the error between the ideal temperature corresponding to the temperature deviation vector and the actual temperature of each temperature zone in the temperature field distribution map of the carriage, and generate a temperature zone applicability matrix;

[0087] Match the batch loading volume with the temperature zone capacity to generate a capacity balancing scheme;

[0088] Based on the target temperature zones for each batch determined by the capacity balancing scheme, output the cargo spatial layout topology containing three-dimensional spatial coordinate instructions.

[0089] In one embodiment, the system first reads the ideal temperature value and the baseline set temperature value for each batch of agricultural products, determined by the set of tolerable temperature zones. The ideal temperature value is subtracted from the baseline set temperature value to obtain the temperature deviation value for each batch of agricultural products. Each discretized spatial temperature zone unit in the temperature field distribution map of the carriage is traversed to obtain the expected actual temperature of that unit. The absolute difference between the ideal temperature value of a specific batch of agricultural products and the expected actual temperature of a specific spatial temperature zone unit is calculated. This difference calculation is repeated for all combinations of batches of agricultural products and all spatial temperature zone units. The obtained absolute differences are arranged according to the correspondence between batches and temperature zones to construct a two-dimensional temperature zone suitability matrix. Rows in the matrix correspond to different batches of agricultural products, and columns correspond to different spatial temperature zones within the carriage. The smaller the value of a matrix element, the higher the degree of matching between the thermal environment of that spatial location and the physiological needs of that batch of agricultural products.

[0090] Iterative matching of loading volume and spatial capacity is performed based on the temperature zone suitability matrix. First, the element with the smallest value in the temperature zone suitability matrix is ​​identified, and the corresponding spatial temperature zone is designated as the preferred temperature zone for this batch of agricultural products. The physical volume capacity data of this preferred temperature zone and the total loading volume or weight data of the batch of agricultural products are read. When the loading volume of the batch of agricultural products is less than or equal to the remaining capacity of the preferred temperature zone, the entire batch of agricultural products is directly allocated to the preferred temperature zone, and the remaining capacity status of the temperature zone is updated. When the loading volume of the batch of agricultural products exceeds the remaining capacity of the preferred temperature zone, a splitting logic is executed, dividing the agricultural products into a primary portion and an overflow portion. The primary portion is allocated to fill the preferred temperature zone, and then the set of temperature zones that are physically adjacent to the preferred temperature zone (including front-to-back, left-to-right, or top-to-bottom adjacent) is searched in the temperature field distribution map of the carriage. The difference between the ideal temperature of the overflow portion and the actual temperature of each temperature zone in the adjacent temperature zone set is calculated, and the adjacent temperature zone with the smallest difference is selected as the secondary optimal temperature zone, and the overflow portion is allocated to this secondary optimal temperature zone. After allocation, the effectiveness of the scheme is verified by a weighted average algorithm. That is, the weighted average error between the actual ambient temperature and the ideal temperature after allocation is calculated by using the mass of the main component and the overflow component as weights. If the weighted average error is less than the preset temperature control accuracy threshold (such as 0.5℃), the allocation result is locked as a capacity balance scheme.

[0091] Based on the capacity balancing scheme, a cargo spatial layout topology is generated to guide physical operations. A three-dimensional Cartesian coordinate system is established inside the carriage, with the center point of the intersection between the inner wall where the refrigeration unit's air outlet is located and the carriage floor defined as the origin $(0,0,0)$. The direction extending along the length of the carriage towards the door is defined as the X-axis, the direction extending along the width of the carriage as the Y-axis, and the direction perpendicular to the carriage floor upwards as the Z-axis. The temperature zone numbers occupied by each batch of agricultural products in the capacity balancing scheme are parsed, and the corresponding geometric boundary data of each temperature zone in the carriage temperature field distribution map are found. The geometric boundary data is converted into numerical intervals under the above coordinate system, and a spatial coordinate instruction containing three dimensions is generated for each batch of agricultural products. The specific format of this instruction includes: length axis coordinate interval $[x_{start},x_{end}]$, width axis coordinate interval $[y_{start},y_{end}]$, and height axis coordinate interval $[z_{start},z_{end}]$. The above-mentioned instruction set containing a clear three-dimensional coordinate range is packaged and output to form a cargo space layout topology. This topology is used to drive automated loading and unloading equipment or instruct manual labor to accurately stack specific batches of agricultural products into physical space locations with corresponding temperature characteristics inside the carriage, thereby using the non-uniform temperature field inside the carriage to offset the differences in physiological tolerance of agricultural products from different soil sources.

[0092] Of particular importance is matching batch loading volume with temperature zone capacity to generate a capacity balancing scheme, including:

[0093] When the loading of a batch exceeds the capacity of its optimal matching temperature zone, the excess agricultural products will be allocated to the temperature zone adjacent to the optimal matching temperature zone and with the second smallest temperature error.

[0094] Verify whether the total weighted temperature error after allocation meets the preset threshold. If it does, lock the scheme as the capacity balancing scheme.

[0095] In one specific implementation, the system first identifies "overflow batches" where the load exceeds the capacity limit of a single temperature zone. For each batch, it is split into a primary portion and an overflow portion. The primary portion's quantity equals the maximum remaining capacity of its optimal matching temperature zone (i.e., the area with the smallest temperature error), and this primary portion is locked and allocated to that optimal temperature zone. For the remaining overflow portion, all candidate areas directly adjacent to the optimal temperature zone in the carriage space topology (e.g., adjacent front and rear or vertically) are searched, and the area with the smallest absolute value of error between its temperature and the ideal temperature of the batch is selected and defined as the suboptimal temperature zone. The overflow portion is then allocated to this suboptimal temperature zone.

[0096] After all allocations are completed, a quality check of the plan is performed. The actual temperature error of each portion of cargo (including the main portion and the overflow portion) is calculated, and the total weighted temperature error is calculated using the weight of each portion of cargo as the weight. This value is compared with a preset error threshold (e.g., 0.5℃). If the total weighted temperature error is less than or equal to the threshold, the current allocation plan is deemed to have achieved a balance between physical feasibility and temperature control accuracy, and is therefore locked and marked as the final capacity balance plan; if it exceeds the threshold, an alarm is triggered or manual intervention is prompted, indicating that the current temperature gradient resources in the cargo compartment can no longer meet the preservation requirements of this batch of cargo.

[0097] Most importantly, the three-dimensional spatial coordinate instructions in the cargo space layout topology define the length axis coordinate range, width axis coordinate range, and height axis coordinate range with the air outlet side of the carriage as the origin, which are used to indicate the specific stacking position of each batch of agricultural products in the carriage.

[0098] In one specific implementation, the generation of the cargo space layout topology employs digital three-dimensional coordinate mapping technology. First, a right-handed Cartesian coordinate system is established inside the carriage, with the intersection of the inner wall where the refrigeration unit's air outlet is located and the carriage floor defined as the reference origin (i.e., the zero point of the length axis). In this coordinate system, the length axis (X-axis) extends longitudinally along the carriage towards the door, the width axis (Y-axis) extends laterally along the carriage, and the height axis (Z-axis) extends vertically upwards from the floor. The target temperature zones for each batch of agricultural products determined in the preceding steps are mapped to specific geometric spaces within this coordinate system. For each batch of agricultural products, a set of three-dimensional spatial coordinate instructions containing closed intervals is generated. These instructions clearly define the permissible spatial range for that batch of goods, in the format: X-axis interval [x_start, x_end], Y-axis interval [y_start, y_end], and Z-axis interval [z_start, z_end]. For example, for agricultural products assigned to the "front-end air supply zone," the instruction will specify the X-axis interval as 0 to 2.5 meters and the Z-axis interval as 0 to 1.5 meters; for agricultural products assigned to the "rear-end return air temperature rise zone," the instruction will specify the X-axis interval as 6.0 to 8.0 meters. This instruction is directly output to automated loading and unloading equipment or a visualization terminal, forcibly limiting the physical placement of each batch of agricultural products during loading operations, ensuring that the actual stacking position strictly corresponds to the theoretical temperature zone in the thermal field distribution diagram.

[0099] Please see Figure 2 As shown, this is a schematic diagram of the damage minimization optimization curve. With temperature as the horizontal axis and damage value as the vertical axis, three curves are presented. The top solid line is the weighted total damage curve of the whole vehicle (its lowest point points to the horizontal axis), the middle curve is the damage curve of batch 1, and the bottom curve is the damage curve of batch 2. This intuitively reflects the damage change pattern of each batch of agricultural products and the whole vehicle at different temperatures.

[0100] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0101] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for adaptive temperature control of agricultural product cold chain based on soil data, characterized in that, The method includes the following steps: Step S1: Access the vehicle's loading plan and parse the geographical location information of each production area. Match the corresponding historical soil monitoring records based on the geographical location information, and filter and weight the historical soil monitoring records to generate soil physicochemical feature vectors. Step S2: Calculate the physiological characteristic data of each batch of agricultural products using soil physicochemical feature vectors. The physiological characteristic data includes cell sap osmotic pressure data, basal respiration calorific value, and cell wall strength index. Determine the minimum safe temperature based on the cell sap osmotic pressure data. Determine the maximum safe temperature based on the basal respiration calorific value and cell wall strength index. Combine the minimum safe temperature and the maximum safe temperature to generate a set of tolerance temperature zones. Step S3: Obtain the loading amount of each batch of agricultural products, combine it with the set of tolerable temperature zones to perform weighted optimization analysis of agricultural product damage, and determine the benchmark set temperature value; Step S4: Generate a temperature field distribution map of the carriage based on the baseline set temperature value; calculate the temperature deviation vector based on the difference between the set of tolerable temperature zones and the baseline set temperature value; match each batch of agricultural products to the temperature field distribution map of the carriage based on the temperature deviation vector to generate the cargo space layout topology.

2. The method according to claim 1, characterized in that, Step S1 includes: Identify agricultural product classification identifiers in the loading plan, invoke pre-set physiological response association rules, and extract the core soil indicator set corresponding to the agricultural product classification identifiers from historical soil monitoring records; The values ​​of the core soil index set are normalized by interval to generate a standardized soil parameter set. Based on the preset moisture sensitivity weight and preset structure sensitivity weight corresponding to the agricultural product classification labels, the standardized soil parameter set is weighted and calculated to synthesize the soil physicochemical feature vector.

3. The method according to claim 1, characterized in that, Step S2, which determines the minimum safe temperature based on cell fluid osmotic pressure data, includes: The osmotic pressure-related components in the soil physicochemical feature vector are extracted, and the cell sap osmotic pressure data are calculated using the transfer relationship between soil salinity and plant cell sap concentration. Based on cell osmotic pressure data and a pre-set van der Hoff adjustment coefficient for the type of agricultural product, the freezing point depression is calculated, and the theoretical freezing point temperature is determined. The minimum safe temperature is determined by adding a preset safety margin coefficient to the theoretical freezing point temperature.

4. The method according to claim 1, characterized in that, In step S2, the maximum safe temperature is determined based on the basal respiratory calorific value and cell wall strength index, and the minimum and maximum safe temperatures are combined to generate a set of tolerance temperature zones, including: Extract the metabolic-related components from the soil physicochemical feature vector, and calculate the basic respiratory calorific value based on the metabolic-related components; Extract the structure-related components from the soil physicochemical feature vectors, and calculate the cell wall strength index based on the structure-related components; The baseline respiratory calorific value is converted into a respiratory temperature compensation value, and the maximum safe temperature is determined by combining it with the cell wall strength index. The range consisting of the lowest and highest safe temperatures is offset and corrected using the breathing temperature compensation value to generate a set of tolerance temperature zones.

5. The method according to claim 1, characterized in that, Step S3 includes: In response to the loading completion signal of the vehicle at each loading station, identify the set of all batches of agricultural products that have been loaded in the current compartment; Summarize the temperature tolerance ranges and loading volumes of all currently loaded batches of agricultural products, and generate a real-time batch temperature range data table; Based on the proportion of each batch's loading volume to the current total loading volume, dynamically calculate the loading weight coefficient group; Identify the intersection of temperature zones in each batch in the batch temperature zone data table. If no common temperature zone exists, trigger an optimization calculation process based on damage minimization to update the baseline set temperature value.

6. The method according to claim 5, characterized in that, The optimization calculation process based on damage minimization includes: A batch damage function set is constructed, and the batch damage function set defines the segmented calculation logic for each batch: when the temperature is below the lower tolerance limit, the damage value is calculated using the cold damage coefficient; when the temperature is above the upper tolerance limit, the damage value is calculated using the heat damage coefficient; and the value of the cold damage coefficient is greater than the value of the heat damage coefficient. A step-size traversal is performed within a preset temperature range to generate several simulated temperature points; For each simulated temperature point, the damage value of each batch of agricultural products currently loaded is calculated using the batch damage function group, and the weighted total damage value of the entire vehicle is calculated in combination with the loading weight coefficient group. The simulated temperature point with the minimum weighted total damage value is selected as the optimal equilibrium temperature, and after stability verification, it is output as the benchmark set temperature value.

7. The method according to claim 1, characterized in that, Step S4, which generates the temperature field distribution map of the carriage based on the reference set temperature value, includes: Obtain the inherent physical structure parameters of the vehicle compartment and the air outlet, return air outlet and air volume parameters of the vehicle's refrigeration system to determine the airflow temperature gradient inside the vehicle compartment. Using the baseline temperature value as the reference origin, and combining the airflow temperature rise gradient, the theoretical temperature of different longitudinal distance areas of the carriage is calculated; Vertical temperature stratification correction and boundary effect compensation are performed on each longitudinal region to generate a temperature field distribution map of the carriage containing the actual temperature values ​​and spatial coordinate range of multiple temperature zones.

8. The method according to claim 1, characterized in that, Step S4, which calculates the temperature deviation vector based on the difference between the set of tolerable temperature zones and the benchmark set temperature value, includes: The ideal temperature set for each batch of agricultural products is calculated using the set of tolerance temperature zones. Calculate the difference between the ideal temperature group of the batch and the reference set temperature value to generate a temperature deviation vector; a positive value in the temperature deviation vector indicates that the required temperature is higher than the reference set temperature value, and a negative value indicates that the required temperature is lower than the reference set temperature value.

9. The method according to claim 1, characterized in that, In step S4, each batch of agricultural products is matched to the temperature field distribution map of the carriage based on the temperature deviation vector, generating the cargo spatial layout topology, including: Calculate the error between the ideal temperature corresponding to the temperature deviation vector and the actual temperature of each temperature zone in the temperature field distribution map of the carriage, and generate a temperature zone applicability matrix; Match the batch loading volume with the temperature zone capacity to generate a capacity balancing scheme; Based on the target temperature zones for each batch determined by the capacity balancing scheme, output the cargo spatial layout topology containing three-dimensional spatial coordinate instructions.

10. An adaptive temperature control system for agricultural product cold chain based on soil data, characterized in that, For executing the soil data-based adaptive temperature control system for agricultural product cold chain as described in claim 1, the soil data-based adaptive temperature control system for agricultural product cold chain includes: The origin habitat characteristic quantification module is used to access the vehicle loading plan and analyze the geographical location information of each origin. Based on the geographical location information, it matches the corresponding historical soil monitoring records, filters and weights the historical soil monitoring records, and generates soil physicochemical characteristic vectors. The physiological tolerance boundary extrapolation module is used to calculate the physiological characteristic data of each batch of agricultural products using soil physicochemical feature vectors. The physiological characteristic data includes cell sap osmotic pressure data, basal respiration heat value and cell wall strength index. The minimum safe temperature is determined based on the cell sap osmotic pressure data. The maximum safe temperature is determined based on the basal respiration heat value and cell wall strength index. The minimum safe temperature and the maximum safe temperature are combined to generate a set of tolerance temperature zones. The global thermal balance optimization module is used to obtain the loading amount of each batch of agricultural products, combine it with the set of tolerance temperature zones to perform weighted optimization analysis of agricultural product damage, and determine the benchmark set temperature value. The three-dimensional spatial matching module is used to generate a temperature field distribution map of the carriage based on the benchmark temperature value; calculate the temperature deviation vector based on the difference between the set of temperature-tolerant zones and the benchmark temperature value; and match each batch of agricultural products to the temperature field distribution map of the carriage based on the temperature deviation vector to generate the cargo spatial layout topology.

Images