Logistics and fresh-keeping collaborative control method for fresh agricultural products

Abstract

The present application relates to the technical field of cold chain logistics collaborative control, in particular to a logistics and preservation collaborative control method for fresh agricultural products, which first acquires cross-domain basic data such as fresh physiological properties, environmental time series, transportation plans and inventory states; secondly, homologous differentiation is carried out based on physiological characteristics, the environmental deviation is coupled with the physiological sensitivity coefficient to generate a preservation debt value representing the cumulative damage, and the damage benchmark is reduced by taking the remaining transportation time and the inventory counter-pressure as the space-time attenuation constraints to generate a dynamic debt capacity; then, the two are calculated in real time, the change rate is fused to construct a composite mismatch index to divide the mismatch level; finally, after the vehicle hardware boundary feasibility check, the micro-environment compensation or macro-logistics scheduling instruction corresponding to the level is output; the hysteresis of single environmental threshold control is avoided, and the predictive closed-loop stop-loss of micro-physiological damage and macro-logistics link is realized.

Description

Technical Field

[0001] This invention relates to the field of cold chain logistics collaborative control technology, specifically a collaborative control method for the preservation of fresh agricultural products. Background Technology

[0002] In the field of cold chain logistics for fresh agricultural products, controlling quality deterioration during transportation is a core technological aspect for ensuring product delivery quality and reducing loss rates. Fresh agricultural products undergo irreversible metabolic processes after leaving their place of origin, including respiration, transpiration, and microbial contamination. The rate of quality deterioration is closely related to the temperature and humidity conditions in the transportation environment. Currently, cold chain logistics control systems typically use preset static temperature and humidity ranges to regulate the transportation environment. This involves setting fixed temperature and humidity ranges based on the product category before transportation begins. During transportation, sensors monitor the temperature and humidity of the vehicle compartment in real time. When environmental parameters deviate from the preset range, refrigeration or humidification equipment is triggered to correct the deviation. This allows for timely responses to single, significant environmental exceedances, maintaining a certain degree of basic stability in the transportation environment.

[0003] However, the quality damage of fresh agricultural products is irreversible and cumulative. Once deterioration caused by deviations in temperature and humidity, such as cell damage, moisture loss, and microbial contamination, occurs, it cannot be repaired and continues to accumulate over time. Existing control methods based on instantaneous threshold judgments only assess whether the environmental conditions at the current moment are within the compliance range. They lack the ability to quantitatively track the total irreversible accumulation of quality damage over time. This results in the system being unable to perceive the cumulative quality burden formed by multiple short-term deviations. Consequently, it is impossible to compare this cumulative burden with constraints that dynamically change with the transportation process, such as remaining transportation time and destination receiving conditions. It is difficult to accurately determine the true quality risk level faced by the current batch at a specific transportation stage, ultimately leading to a control lag where the quality has substantially deteriorated but the system has not yet triggered effective intervention. Summary of the Invention

[0004] In view of the problems in related technologies, the present invention provides a collaborative control method for logistics preservation of fresh agricultural products, so as to overcome the above-mentioned technical problems existing in the existing related technologies.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a collaborative control method for logistics preservation of fresh agricultural products, comprising the following steps:

[0006] Acquire physiological attribute data, transportation environment time series data, transportation plan data, and destination inventory status data for agricultural products to be transported;

[0007] Based on the physiological attribute data, the initial tolerance value of the agricultural products to be transported is determined, and the corresponding environmental physiological sensitivity coefficient is extracted.

[0008] The real-time environmental deviation corresponding to the time series data of the transportation environment is coupled with the environmental physiological sensitivity coefficient, and integral and cumulative calculation is performed along the transportation time axis to generate a preservation debt value that represents irreversible damage.

[0009] Extract the remaining transportation time from the transportation plan data, and calculate the inventory back pressure coefficient based on the destination inventory status data. Use the remaining transportation time and the inventory back pressure coefficient as spatiotemporal attenuation constraints to dynamically reduce the initial tolerance value, thereby generating a dynamic tolerance value that characterizes the system's future digestion threshold.

[0010] The preservation debt value and the dynamic debt capacity value are subjected to real-time adversarial calculation. The instantaneous difference between the two is extracted as the basic mismatch amount. The time change rate of the basic mismatch amount is calculated. The basic mismatch amount and the time change rate are fused to generate a composite mismatch index.

[0011] The composite mismatch index is compared with a preset range to determine the mismatch level of the agricultural product to be transported.

[0012] The vehicle environmental adjustment capability parameters in the transportation plan data are obtained. The candidate environmental compensation control quantity corresponding to the mismatch level is compared with the vehicle environmental adjustment capability parameters. Hardware boundary feasibility verification is performed. Based on the result of the hardware boundary feasibility verification and the mismatch level, the corresponding cooperative control result is output to the physical execution end. The updated basic data is obtained in a loop to perform closed-loop control.

[0013] This invention also includes a collaborative control system for logistics preservation of fresh agricultural products, comprising:

[0014] The data acquisition module is used to acquire physiological attribute data, transportation environment time series data, transportation plan data, and destination inventory status data of the agricultural products to be transported.

[0015] The benchmark determination module is used to determine the initial tolerance value of the agricultural product to be transported based on the physiological attribute data, and to extract the corresponding environmental physiological sensitivity coefficient.

[0016] The preservation debt calculation module is used to couple the real-time environmental deviation corresponding to the transportation environment time series data with the environmental physiological sensitivity coefficient, perform integration and accumulation calculation along the transportation time axis, and generate a preservation debt value that represents irreversible damage.

[0017] The dynamic debt capacity constraint module is used to extract the remaining transportation time from the transportation plan data, calculate the inventory counter-pressure coefficient based on the destination inventory status data, and use the remaining transportation time and the inventory counter-pressure coefficient as spatiotemporal attenuation constraints to dynamically reduce the initial debt capacity value and generate a dynamic debt capacity value that characterizes the future digestion threshold of the system.

[0018] The mismatch grading module is used to perform real-time adversarial calculations on the preservation debt value and the dynamic tolerance debt value, extract the instantaneous difference between the two as the basic mismatch amount, calculate the time change rate of the basic mismatch amount, merge the basic mismatch amount and the time change rate to generate a composite mismatch index; compare the composite mismatch index with a preset interval to determine the mismatch level of the agricultural product to be transported.

[0019] The verification execution module is used to obtain the vehicle environmental adjustment capability parameters in the transportation plan data, compare the candidate environmental compensation control quantity corresponding to the mismatch level with the vehicle environmental adjustment capability parameters, perform hardware boundary feasibility verification, and output the corresponding cooperative control result to the physical execution end based on the result of the hardware boundary feasibility verification and the mismatch level, and cyclically obtain the updated basic data to perform closed-loop control.

[0020] By employing the above technical solution, the present invention provides a collaborative control method for logistics preservation of fresh agricultural products, which has at least the following beneficial effects:

[0021] 1. This invention acquires heterogeneous data from multiple sources, including physiological attributes, transportation environment, transportation plans, and destination inventory, to construct a real-time adversarial model between freshness debt value and dynamic tolerance debt value. It unifies the irreversible accumulation of quality damage and the dynamic decay of the system's tolerance limit into the same quantitative framework. After graded judgment by composite mismatch index, it drives graded collaborative control outputs of environmental fine-tuning, local logistics adjustment, and forced logistics reconstruction. The physical executability of control commands is ensured through hardware boundary feasibility verification, realizing continuous quantitative tracking and graded closed-loop response of quality risks in the entire process of fresh agricultural product transportation.

[0022] 2. Based on the positive and negative combinations of temperature deviation and humidity deviation, this invention dynamically calls the cross-coupling sensitivity coefficients of the corresponding quadrants, enabling differentiated quantitative modeling of superlinear water loss under high temperature and low humidity, superlinear spoilage under high temperature and high humidity, chilling injury-spoilage composite damage under low temperature and high humidity, and chilling injury-water loss composite damage under low temperature and low humidity. Discrete disturbance events are equivalent to pulse increments superimposed on the continuous integral term, so that the preservation debt value can simultaneously capture the irreversible cumulative damage to quality caused by continuous environmental deviations and sudden disturbance events.

[0023] 3. In constructing the dynamic capacity tolerance value, this invention introduces a power function nonlinear time decay mechanism. By setting a time margin decay index greater than one, the capacity tolerance gradually decays in the early and middle stages of transportation and accelerates its contraction at the end of transportation. At the same time, it incorporates a multi-dimensional inventory counter-pressure coefficient based on the warehouse congestion factor, outbound speed, and the average aging index of existing inventory, so that the upper limit of damage that the system can tolerate can be dynamically adjusted according to the transportation process and the receiving conditions at the destination.

[0024] 4. This invention compares the environmental compensation control quantity with the current vehicle's cooling, ventilation, and humidification capacity limits one by one. When the candidate control quantity exceeds the hardware capacity limit, it forcibly skips the micro-environment control compensation stage and upgrades the mismatch level to a higher level of logistics intervention logic. This enables the control decision to automatically upgrade to the logistics planning level when the hardware capacity is saturated, avoiding the output of invalid control commands. Attached Figure Description

[0025] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0026] Figure 1 A flowchart of the collaborative control method for logistics preservation of fresh agricultural products provided by the present invention;

[0027] Figure 2 This is a schematic diagram of the modules of the collaborative control system for logistics preservation of fresh agricultural products provided by the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Exemplary method:

[0030] In the cold chain logistics of fresh agricultural products, the impact of the transportation environment on product quality has an irreversible cumulative characteristic—quality deterioration caused by deviations in temperature and humidity, such as cell membrane damage, transpiration water loss, and microbial contamination, cannot be repaired once it occurs and continues to accumulate over time. Existing cold chain control systems make instantaneous limit exceedance judgments based on preset static temperature and humidity thresholds. When sensors detect that the environment in the vehicle compartment deviates from the preset range, they trigger refrigeration or humidification equipment to correct the deviation. This instantaneous judgment method only assesses whether the environmental state at the current moment is compliant, lacking the ability to quantitatively track the total irreversible accumulation of quality damage over time. As a result, the system cannot compare historical accumulated damage with dynamic constraints such as remaining transportation time and destination receiving conditions in real time, thus failing to accurately determine the true quality risk level of the current batch.

[0031] If the above problems are not addressed, even if each brief environmental deviation during transportation is quickly corrected and the system never generates an over-limit alarm, the cumulative effect of multiple deviations may still cause product quality to fall below acceptable levels. Especially when there is very little remaining buffer time at the end of transportation and serious inventory backlog at the destination, the system, lacking a quantitative assessment of the mismatch between cumulative damage and the dynamic tolerance limit, cannot promptly trigger a tiered upgrade response from environmental fine-tuning to logistics plan restructuring, ultimately resulting in irreversible loss of high-value fresh produce.

[0032] To address the aforementioned challenges, this application first considers how to continuously accumulate and quantify irreversible quality damage occurring throughout the transportation process. Existing methods only independently assess instantaneous environmental deviations, failing to track the total damage burden resulting from the integration of deviations over time. To resolve this, this application, based on fresh produce metabolic dynamics, integrates temperature deviations, humidity deviations, and their cross-coupling effects along the time axis, and equates discrete disturbances such as door openings and node delays to pulse increments, constructing a monotonically increasing preservation debt value to continuously quantify the total accumulated irreversible damage. Simultaneously, this application discovers that the system's tolerance for accumulated damage is not a fixed constant but dynamically decays with decreasing remaining transportation time and increasing destination inventory pressure. Therefore, this application constructs a dynamic tolerance debt value that integrates nonlinear time decay and multidimensional inventory back pressure, serving as a time-varying upper limit for the system's tolerable damage. By performing real-time adversarial calculations on the preservation debt value and dynamic tolerance debt value and incorporating deterioration trend prediction, a composite mismatch index is generated for graded judgment. This drives the collaborative control output from environmental fine-tuning to logistics restructuring, and hardware boundary verification ensures the physical executability of control commands, thereby achieving accurate identification and graded response to quality risks.

[0033] To address this, this embodiment proposes a collaborative control method for logistics preservation of fresh agricultural products. For example... Figure 1 As shown, the method includes the following steps:

[0034] In this embodiment, a batch of Red Beauty strawberries transported via cold chain from a production base in Yantai, Shandong to a fresh food distribution center in Shanghai is used as an example to demonstrate the complete calculation process of the entire solution. This batch of strawberries is a berry variety, and the total estimated transportation time is 10 hours. The system calculates the time every 5 minutes (i.e., the sampling period). A complete calculation of preservation debt and capacity is performed once per calculation cycle. The following calculation is based on the 6th hour after the start of transportation (i.e., Let's take a calculation cycle at point ) as an example for a detailed demonstration.

[0035] S1. Obtain physiological attribute data, transportation environment time series data, transportation plan data, and destination inventory status data of the agricultural products to be transported;

[0036] Specifically, the four types of data are obtained from different physical ports or data interfaces: physiological attribute data comes from product files pre-entered at the point of origin (which can be stored in product QR codes or RFID tags); transportation environment time-series data comes from real-time sampling data streams from temperature and humidity sensor arrays deployed inside the vehicle; transportation plan data comes from real-time push notifications from the logistics scheduling system; and destination inventory status data comes from interface queries to the destination warehouse management system (WMS). These four types of data form the input basis for all subsequent calculation steps; the absence of any one type of data will prevent the system from accurately quantifying quality risks.

[0037] In this embodiment, the physiological attribute data includes: agricultural product category information as berries (strawberries), variety information as Hongyan, maturity level as 70% (commercial maturity), post-harvest duration as 4 hours, pre-cooling completion rate as 85%, and water loss sensitivity coefficient. Sensitivity coefficient to cold damage / corrosion The packaging type is a breathable PET small box (transparency parameter is medium). The temperature and humidity cross-coupling sensitivity coefficient table includes coefficient values ​​in four quadrants (see subsequent S3 step for details). Transportation environment time-series data includes: real-time temperature of the vehicle compartment within the current calculation period. Real-time humidity The data also includes discrete disturbance events recorded in the past 6 hours (including a 3-minute door opening event in the second hour and a 15-minute node delay event in the fourth hour). Transportation plan data includes: current node location near Nanjing, Jiangsu (G40 Shanghai-Shaanxi Expressway), and remaining transportation time. Total estimated time for the entire journey The current maximum cooling capacity of the vehicle is that the temperature can be lowered to [temperature value missing]. (Full-load cooling power approximately 8kW), humidification capacity up to [value missing] can raise humidity to [value missing]. Destination-side inventory status data includes: current warehouse capacity congestion factor. (Indicates that the warehouse is at 70% capacity) Actual outbound speed Maximum outbound capacity Average aging index of existing inventory .

[0038] S2. Determine the initial tolerance value of the agricultural products to be transported based on the physiological attribute data, and extract the corresponding environmental physiological sensitivity coefficient;

[0039] It should be noted that the purpose of this step is to determine the upper limit of quality damage that the current batch of agricultural products can withstand under ideal conditions (i.e., the initial tolerance value) based on the specific physiological characteristics of the batch. At the same time, it extracts a set of coefficients describing the sensitivity of the variety to deviations in temperature and humidity (i.e., the environmental physiological sensitivity coefficient). The initial tolerance value is the starting benchmark for subsequent dynamic tolerance debt calculation, and the environmental physiological sensitivity coefficient is the core parameter for subsequent preservation debt calculation.

[0040] The determination of the initial tolerance value of the agricultural products to be transported based on the physiological attribute data includes:

[0041] S21. Obtain agricultural product category information, maturity level, post-harvest duration, and pre-cooling completion rate from the physiological attribute data;

[0042] Among them, agricultural product category information (such as berries, leafy vegetables, root vegetables, etc.) determines the basic pattern and rate of quality deterioration; maturity level reflects the metabolic activity of the product, the higher the maturity, the more vigorous the metabolism and the lower the tolerance; post-harvest duration reflects the natural aging time that the product has undergone after leaving the parent plant, the longer the duration, the lower the remaining tolerance; pre-cooling completion reflects whether the product has been sufficiently cooled to the target temperature before shipment, insufficient pre-cooling means that the product is still in a high temperature range in the early stage of transportation, which will accelerate the initial quality loss.

[0043] S22. From the preset agricultural product physiological parameter database, query the preset loss tolerance benchmark that matches the agricultural product category information;

[0044] Among them, the preset agricultural product physiological parameter library is a pre-built database that stores post-harvest physiological characteristic parameters such as quality tolerance benchmarks, environmental physiological sensitivity coefficients, and optimal preservation environment ranges for various categories of agricultural products. Preset damage tolerance benchmarks. It refers to the theoretical maximum tolerable damage amount of agricultural products under standard maturity, standard post-harvest duration, and complete pre-cooling conditions. It is usually calibrated based on post-harvest physiological experimental data of agricultural products and industry experience.

[0045] In this embodiment, the preset damage tolerance standard for strawberries (berries) (Dimensionless unit).

[0046] S23. Using the maturity level, post-harvest duration, and pre-cooling completion rate as correction factors, the preset tolerance benchmark is dynamically corrected to generate an initial tolerance value characterizing the initial tolerance limit of the agricultural product to be transported. Initial tolerance value The calculation formula is:

[0047] ,

[0048] in, Preset tolerance benchmark; Maturity correction factor; This is a post-harvest duration correction factor; This is a correction factor for precooling completion.

[0049] Specifically, the three correction factors mentioned above are obtained from the corresponding physiological attribute data through table lookup mapping or function mapping, respectively; for The system uses a preset maturity level-correction factor lookup table for discrete lookup. This table divides maturity levels into several standard tiers and pre-assigns a correction factor value to each tier; for example, five-tenths maturity corresponds to... 70% ripe corresponds to Nine-tenths ripe corresponds to In this embodiment, 70% ripe corresponds to... (Compared to half-cooked) (There is a 10% reduction). For The result is obtained by using the post-collection duration as the independent variable and a preset linear decay function: ,in, The pre-calibrated decay rate per unit time for this product category was obtained by linear regression fitting of the quality retention rate of this product category under standard storage conditions for different post-harvest durations. This rate is used to linearly convert the post-harvest time into a proportional reduction in tolerance (in this example, strawberry). In this embodiment, 4 hours after sampling... .for As a percentage of pre-cooling completion The independent variable is obtained through a predefined power function mapping: ,in, The pre-cooling sensitivity index is obtained by fitting a power function curve to the transportation quality loss data of this type of agricultural product under different pre-cooling completion levels. It is used to control the nonlinear response sensitivity of pre-cooling completion level to the reduction of tolerance (in this embodiment). This power function mapping results in a smaller correction magnitude when the precooling completion rate is in a higher range (e.g., above 80%), and a sharper correction magnitude when the completion rate is in a lower range (e.g., below 50%), to reflect the non-linear reduction effect of insufficient precooling on quality tolerance. In this embodiment, the precooling completion rate is 85%, then... .

[0050] For example, in this embodiment: This means that the initial tolerance value of this batch of strawberries is approximately 99.5.

[0051] Simultaneously, the system extracts the set of environmental physiological sensitivity coefficients corresponding to this category from the agricultural product physiological parameter database, including: water loss sensitivity coefficient. Sensitivity coefficient to cold damage / corrosion The table of temperature and humidity cross-coupling sensitivity coefficients (the coefficient values ​​for the four quadrants will be explained in detail in subsequent step S3) also includes these coefficients. These coefficients reflect the physiological sensitivity of the variety to different types of environmental deviations; the higher the value, the more sensitive the variety is to the corresponding type of deviation and the faster its quality deteriorates.

[0052] S3. Couple the real-time environmental deviation corresponding to the transportation environment time series data with the environmental physiological sensitivity coefficient, and perform integration and accumulation calculation along the transportation time axis to generate a preservation debt value that represents irreversible damage.

[0053] It should be noted that this step accumulates and integrates the quality damage caused by environmental deviations at every moment during transportation, generating a monotonically increasing preservation debt value. This value reflects the irreversibility of damage to fresh produce quality: once damage occurs, it cannot be repaired; the only way to mitigate further damage accumulation is to control the rate of subsequent deviations. This characteristic differs from existing technologies that rely on instantaneous temperature fluctuations, enabling precise tracking of the cumulative effects of multiple brief deviations.

[0054] Among them, the preservation debt value representing irreversible damage includes:

[0055] S31. Determine the temperature reference value and humidity reference value corresponding to the target preservation zone based on the physiological attribute data;

[0056] Specifically, based on the category and variety information of the current batch of agricultural products, the optimal preservation temperature range and optimal preservation humidity range for that variety are retrieved from the agricultural product physiological parameter database, and the midpoint of the range is taken as the corresponding reference value.

[0057] In this embodiment, the optimal preservation temperature range for strawberries is: to Corresponding temperature reference value The optimal humidity range for food preservation is: to Corresponding humidity reference value .

[0058] S32. Extract the real-time temperature and real-time humidity from the time-series data of the transportation environment; calculate the difference between the real-time temperature and the temperature reference value to obtain the temperature deviation; calculate the difference between the real-time humidity and the corresponding humidity reference value to obtain the humidity deviation; temperature deviation... and humidity deviation The calculation formula is:

[0059] ,

[0060] ,

[0061] In this embodiment, the current calculation cycle ( Real-time temperature Real-time humidity ,but , A positive temperature deviation indicates that the temperature inside the vehicle is higher than the optimal preservation temperature, while a negative humidity deviation indicates that the humidity inside the vehicle is lower than the optimal preservation humidity.

[0062] S33. Identify the positive and negative direction combinations of the temperature deviation and the humidity deviation, and retrieve the corresponding cross-coupling sensitivity coefficient from the environmental physiological sensitivity coefficient according to the positive and negative direction combinations;

[0063] It should be noted that different combinations of temperature and humidity deviations can trigger drastically different physiological damage patterns, and their combined effect exhibits superlinear characteristics (i.e., the combined effect is greater than the sum of the individual effects). This step constructs a cross-coupling sensitivity function that dynamically switches with the direction of deviation. ,in accordance with and The positive and negative direction combinations call the coupling sensitivity coefficient of the corresponding quadrant: when and When (high temperature and low humidity), call The positive feedback superlinear acceleration characterizing transpiration water loss is achieved by high temperatures accelerating the conversion of intercellular liquid water to gaseous state, while low humidity prevents water vapor from forming a saturated layer on the surface, thus further accelerating transpiration; when and When (high temperature and high humidity), call The superlinear acceleration characterizing microbial reproduction—high temperature and high humidity provide optimal growth conditions for pathogens; when and At times (low temperature and high humidity), call This characterizes the combined damage caused by chilling injury and putrefaction—low temperature increases cell membrane permeability and cell fluid leakage, while high humidity exacerbates the formation of surface water films, thus promoting microbial infection; when and At that time (low temperature and low humidity), call This characterizes the combined damage from chilling injury and water loss; when any deviation is 0, .

[0064] In this embodiment, the cross-coupling sensitivity coefficient is set to: , , , Current state and It belongs to the high temperature and low humidity quadrant, and should be called upon. .

[0065] S34. Weighted integral of the independent sensitivity coefficients among the temperature deviation, humidity deviation, cross-coupling sensitivity coefficient and environmental physiological sensitivity coefficient to obtain the continuous damage integral term;

[0066] Furthermore, the continuous damage integral term is obtained as follows:

[0067] First, multiply the absolute value of the temperature deviation by the absolute value of the humidity deviation, and then multiply by the cross-coupling sensitivity coefficient to obtain the coupling integral sub-term;

[0068] Secondly, multiply the absolute value of the temperature deviation by the cold damage sensitivity coefficient in the independent sensitivity coefficient to obtain the independent temperature integral term;

[0069] Next, the absolute value of the humidity deviation is multiplied by the water loss sensitivity coefficient in the independent sensitivity coefficient to obtain the humidity independent integral term;

[0070] Finally, the coupled integral term, the temperature-independent integral term, and the humidity-independent integral term are summed and integrated over the time dimension to obtain the continuous damage integral term.

[0071] Specifically, at each sampling time Instantaneous damage rate It consists of three items:

[0072]

[0073] Among them, the first item The first term is a temperature-independent integral term, representing the rate of independent damage caused by temperature deviations (such as cold damage or heat damage); the second term... The third term is an independent integral term for humidity, representing the independent damage rate caused by humidity deviations (such as transpiration loss); The coupled integral term characterizes the superlinear composite damage rate caused by the combined deviation of temperature and humidity. Integrating along the time axis from the starting point of transportation to the current moment yields a continuous damage integral term.

[0074] For example, in this embodiment, the current sampling time instantaneous damage rate (Unit: per hour). As can be seen, the coupled integral term (18.0) accounts for the vast majority of the instantaneous damage rate (approximately 78.3%), which is much larger than the sum of the two independent terms (5.0). This is precisely the superlinear characteristic of the cross-coupling effect.

[0075] S35. Extract discrete disturbance event data from the time series data of the transportation environment, and convert the discrete disturbance event data into pulse disturbance increase amount according to the preset event penalty mapping relationship;

[0076] Discrete disturbance events refer to intermittent, sudden events during transportation that cause a sharp deviation from the cabin environment, such as door opening events (external hot air intrusion during loading and unloading operations), node stagnation events (prolonged vehicle stays at transfer stations or toll booths leading to decreased cooling efficiency), and loading / unloading switching events. These events are typically short in duration but have a significant impact, making them difficult to accurately capture with continuous integration; therefore, they are equivalent to the increase in impulse disturbance. This is added to the preservation debt value. The preset event penalty mapping relationship is usually calculated by looking up a table based on the event type and duration. For example, each door opening event is calculated with a penalty of 2.0 units per minute.

[0077] In this embodiment, the door opens at 3 minutes past the second hour. A node delay event occurred at 15 minutes past the 4th hour. (The unit penalty for a node stagnation event is lower than that for a door open event because the refrigeration equipment is still running but its efficiency is reduced.) The total increase in pulse disturbance for both events is... .

[0078] S36. The continuous damage integral term is superimposed with the increase in pulse perturbation to generate a preservation debt value that monotonically increases with time. Preservation debt value The complete calculation formula is:

[0079] ,

[0080] The integral term runs along the time axis from the point of origin of transportation ( Accumulated up to the current time , It is the sum of the pulse increments of all discrete disturbance events up to the current moment.

[0081] For example, in this embodiment, it is assumed that during the first 6 hours of transportation, the environment is basically stable for the first 4 hours (the temperature is maintained at...). to Humidity maintained at to The average instantaneous damage rate is approximately 3.5 units / hour; from the 4th to the 6th hour, due to the increase in external ambient temperature, the temperature inside the carriage gradually rises to 4.5°C, and the humidity decreases to 86%, causing the average instantaneous damage rate to rise to approximately 15.0 units / hour. Therefore, the continuous damage integral term is approximately... In addition to the increase of 21.0 in pulse perturbation, in The value of freshness debt at that time .

[0082] S4. Extract the remaining transportation time from the transportation plan data, and calculate the inventory back pressure coefficient based on the destination inventory status data. Use the remaining transportation time and the inventory back pressure coefficient as spatiotemporal attenuation constraints to dynamically reduce the initial tolerance value and generate a dynamic tolerance value that characterizes the future digestion threshold of the system.

[0083] It should be noted that the dynamic debt capacity value It is not a fixed constant, but rather decreases dynamically with respect to constraints in two dimensions: In the time dimension, the shorter the remaining transportation time, the less buffer period the system has, and the less room for maneuver available for environmental compensation later; in the spatial dimension, the greater the back pressure from inventory at the destination (such as inventory backlog or poor quality existing inventory), the weaker the destination's ability to absorb new arrivals. The combined effect of these two constraints causes the dynamic capacity debt value to exhibit a monotonically decreasing trend, and this contraction accelerates at the end of the transportation process.

[0084] The dynamic debt capacity value that generates the future digestion threshold of the generation system includes:

[0085] S41. Extract the current warehouse capacity congestion factor, actual outbound speed and maximum outbound capacity from the destination inventory status data;

[0086] Among them, the current storage capacity congestion factor This represents the current storage capacity utilization rate of the warehouse. The larger the value, the more crowded the warehouse and the fewer available storage spaces; actual outbound speed Characterized by the current actual cargo throughput rate at the destination; maximum outbound capacity. Characterizes the theoretical maximum throughput rate of the destination under full load operation.

[0087] S42. Calculate the ratio of the actual outbound speed to the maximum outbound capacity, and multiply the difference between the preset constant and the ratio by the current warehouse capacity congestion factor to generate a dimensionless inventory back pressure coefficient; the calculation formula is as follows:

[0088] ,

[0089] in, This represents the current warehouse congestion factor. This refers to the actual outbound speed; To maximize outbound capacity; Congestion back pressure, representing the physical logistics dimension, tends to be when warehouses are congested and outbound speeds are far below maximum capacity. This indicates that the back pressure is relatively large; The average aging index of existing inventory at the destination is obtained by summing the remaining shelf life percentage of each batch in the warehouse management system (WMS) in real time and taking a weighted average (for example, if a batch has consumed 70% of its shelf life, then the aging index of that batch is 0.7). It is used to quantify the overall quality deterioration of existing inventory. The corresponding weight coefficients and This is used to balance the relative importance of physical logistics backpressure and quality backpressure. It is usually calibrated based on statistical analysis of the contribution rate of logistics bottlenecks and quality degradation to actual losses in historical operational data at the destination. When historical losses at the destination are mainly caused by poor warehouse turnover, Take the larger value; when the main cause is cross-deterioration of aging inventory, Take the larger value.

[0090] Specifically, the average aging index is introduced because when there is already a large amount of inventory nearing the end of its shelf life in the destination warehouse, even if the newly arrived goods are of good quality, they face the risk of being queued and delayed in being put on the shelves or being cross-degraded with aging inventory. This kind of quality-related pressure is usually ignored in existing technologies, but it has a significant impact on fresh produce.

[0091] For example, in this embodiment, the following is set , Substitute the values: .

[0092] S43. Obtain the total estimated time for the entire journey from the transportation plan data, and calculate the ratio of the remaining transportation time to the total estimated time for the entire journey as a time scaling parameter;

[0093] Among them, the time scaling parameter This reflects the proportion of the current remaining transportation time to the total travel time. In this embodiment, .

[0094] S44. Using the time scaling parameter and the inventory counter-pressure coefficient, the initial tolerance value is reduced according to a preset scaling logic to generate a monotonically decreasing dynamic tolerance value. Dynamic tolerance value The calculation formula is:

[0095] ,

[0096] in, This is the initial tolerance value; The basic debt retention factor represents the minimum debt retention ratio that the system retains even when the remaining transport time approaches zero (set in this embodiment). That is, to retain at least 15% of the initial tolerance value), the reason for retaining this basic amount instead of making The damage was reduced to zero because even at the transportation terminal, the final inspection and rapid turnover at the destination could still absorb a small amount of residual damage. The inventory back pressure adjustment weight is set in this embodiment. This is used to control the extent to which inventory back pressure reduces the debt-holding capacity; The time margin decay index is preset. (In this embodiment, it is set) ).

[0097] Furthermore, regarding The setting is based on the following: When When, power function exist The decay slows down when it approaches 1 (i.e., in the initial stage of transportation), while... The decay accelerates sharply as it approaches zero (i.e., at the end of the transport process). Specifically, when The decay curve is linear; when During the first half of the transportation process (when the remaining time accounts for more than 50%), the capacity to handle liabilities only decreases by about 30%, but in the last 10% of the transportation period, the capacity to handle liabilities will drop sharply. This means that even if deviations occur in the early and middle stages of transportation, there is still sufficient time to recover through environmental compensation. However, any deviation at the end of the transportation process will directly translate into irreversible quality losses due to the lack of buffer time.

[0098] For example, in this embodiment: First, calculate the time scaling term: ,but Next, calculate the inventory back pressure item: ;final .

[0099] S5. Perform real-time adversarial calculations on the preservation debt value and the dynamic debt capacity value, extract the instantaneous difference between the two as the basic mismatch amount, calculate the time change rate of the basic mismatch amount, and merge the basic mismatch amount and the time change rate to generate a composite mismatch index.

[0100] It should be noted that when Exceed When this occurs, it indicates that the accumulated quality damage has exceeded the system's tolerance limit, and a mismatch risk begins to emerge. To not only capture the current mismatch amount but also predict the worsening trend of the mismatch state, the time change rate of the basic mismatch amount (i.e., the deterioration rate) is further introduced, and this is achieved through... The function ensures that the trend component is superimposed only when the mismatch worsens.

[0101] First, calculate the basic mismatch. .when This indicates that a mismatch risk has begun to emerge. In this embodiment, The mismatch is positive, indicating that the freshness preservation debt has significantly exceeded the dynamic debt capacity value.

[0102] Under normal transportation conditions, Monotonically increasing, The mismatch continues to worsen. However, when the control system intervenes to implement macro-level logistics interventions, the mismatch may improve: if the warehouse is changed to a low-pressure turnover warehouse (reducing...) ), will A step rebound occurs; if the path is reconstructed (shortened) Although this would lead to the current theoretical debt capacity limit The accelerated reduction, however, essentially cuts off future debt preservation by significantly shortening future environmental exposure time. The integral interval significantly reduced the rate of debt accumulation. To extract the deteriorating trend and ignore the fluctuations during the improvement period, this step constructs a composite mismatch index that incorporates the rate of change.

[0103] The process of fusing the basic mismatch amount with the rate of change over time to generate a composite mismatch index includes:

[0104] Determine whether the rate of change of time is greater than zero;

[0105] If so, the time change rate is multiplied by a preset trend weight coefficient and a reference time constant to obtain a trend component, and the basic mismatch is added to the trend component to generate a composite mismatch index.

[0106] If not, then set the trend component to zero and directly use the basic mismatch amount as the composite mismatch index;

[0107] The reference time constant is used to unify the data dimensions of each item in the composite mismatch index.

[0108] Specifically, the composite mismatch index The calculation formula is:

[0109] ,

[0110] in, Trend weighting coefficient (set in this embodiment) This is used to control the proportion of trend prediction components in the composite index. The larger the value, the more sensitive the system is to deteriorating trends and the more inclined it is to issue early warnings, but an excessively large value will lead to an increase in the false alarm rate; As a reference time constant (set in this embodiment) ), used to ensure dimensional consistency—basic mismatch quantity For a dimensionless scalar, the rate of change over time The dimension is "units / hour", multiplied by This is then converted to a dimensionless quantity, ensuring that the two terms can be directly added. The max function in the above formula is the mathematical equivalent of the aforementioned branching logic.

[0111] For example, in this embodiment, it is assumed that the basic mismatch in the previous sampling period is The current cycle is Then the rate of change over time is (Unit: per hour). Since this value is greater than zero, the trend component is... The composite mismatch index is This value not only reflects the current mismatch (39.6), but also includes the predicted trend of the mismatch state accelerating (12.96), enabling the system to respond in advance.

[0112] S6. Compare the composite mismatch index with a preset range to determine the mismatch level of the agricultural product to be transported;

[0113] It should be noted that the purpose of this step is to convert continuous quantities... It is mapped to discrete control levels to drive subsequent collaborative control strategies with different intensities.

[0114] The determination of the mismatch level of agricultural products to be transported includes:

[0115] Obtain a first threshold and a second threshold preset by the system to construct multiple preset intervals, wherein the second threshold is greater than the first threshold;

[0116] Among them, the first threshold Second threshold Together The value space is divided into four intervals: the safe zone ( ), Level 1 mismatch interval ( ), second-order mismatch interval ( ) and third-level mismatch intervals ( ).

[0117] In this embodiment, the first threshold Second threshold Thresholds are typically set empirically based on the sensitivity of the agricultural product category to quality deterioration and the intervention and response capabilities of the logistics system. This corresponds to a slight deviation from the boundary that can be controlled by "minor environmental adjustments". This corresponds to a serious deviation from the boundary of "necessary intervention at the logistics planning level".

[0118] If the composite mismatch index is greater than zero and less than or equal to the first threshold, then output a data label indicating a level 1 mismatch.

[0119] Among them, Level 1 mismatch (mild risk) corresponds to The range indicates that the quality damage has slightly exceeded the tolerance limit, but the rate of deterioration can be reduced to a controllable range by adjusting the temperature and humidity settings of the carriage.

[0120] If the composite mismatch index is greater than the first threshold and less than or equal to the second threshold, then output a data label indicating a mismatch level of two.

[0121] Among them, Level 2 mismatch (moderate risk) corresponds to The range indicates that the quality damage has moderately exceeded the tolerance limit. Environmental adjustments alone are insufficient to reverse the deterioration trend. It is necessary to combine this with adjustments to the local logistics plan (such as adjusting the unloading order and skipping low-priority transit nodes) to reduce the subsequent exposure time.

[0122] If the composite mismatch index is greater than the second threshold, a data label indicating a mismatch level of three is output.

[0123] Among them, Level 3 mismatch (severe risk) corresponds to The range indicates that the quality damage has seriously exceeded the tolerance limit, and it is necessary to implement mandatory loss prevention and path reconstruction (such as re-allocating the original order, forcing the unloading of goods in the nearest warehouse, or transferring to a fast turnover or downgrade processing channel).

[0124] In this embodiment, Therefore, the output data label indicates a level three mismatch. Based on the calculation results from the preceding steps, the cause of the level three mismatch is: on the one hand, the preservation of debt value... The price rose rapidly due to the high temperature and low humidity environment during the 4th to 6th hours and two discrete disturbance events; on the other hand, the dynamic debt capacity value... The contraction was significant due to only 40% of the remaining transportation time and a downward pressure of 0.308 on inventory at the destination. The combined effect of these two factors led to a sharp increase in the mismatch.

[0125] S7. Obtain the vehicle environmental adjustment capability parameter in the transportation plan data, compare the candidate environmental compensation control quantity corresponding to the mismatch level with the vehicle environmental adjustment capability parameter, perform hardware boundary feasibility verification, and output the corresponding cooperative control result to the physical execution end based on the result of the hardware boundary feasibility verification and the mismatch level, and cyclically obtain the updated basic data to perform closed-loop control.

[0126] It should be noted that this step is responsible for mapping the mismatch level to specific control instructions and performing hardware boundary feasibility checks before output to ensure the physical executability of the instructions. The introduction of hardware boundary checks addresses the problem in existing technologies where control algorithms may output idealized instructions that exceed the device's capabilities—for example, in extreme heat, the algorithm might suggest lowering the temperature to [a certain level]. However, the maximum capacity of vehicle refrigeration equipment can only be reduced to... If the command is output directly, it will be invalid control. By verifying before execution, the system can automatically upgrade the control strategy to a higher level of logistics intervention when hardware capabilities are insufficient.

[0127] The output of the corresponding collaborative control results to the physical execution end includes:

[0128] Match the mismatch level in the preset control strategy mapping table to obtain the corresponding candidate environmental compensation control quantity, and determine whether the candidate environmental compensation control quantity is greater than the upper limit of the capability corresponding to the vehicle environmental adjustment capability parameter.

[0129] Specifically, the preset control strategy mapping table is a pre-built multi-level strategy library, where each mismatch level corresponds to a set of candidate control actions and environmental compensation target values. For example, for a level one mismatch, the candidate environmental compensation control quantity might be to lower the temperature setpoint by 1.5°C and raise the humidity setpoint by 5%; for a level two mismatch, the candidate environmental compensation control quantity might be to lower the temperature setpoint to the lower limit of the range (0°C) and raise the humidity setpoint to the upper limit (95%), while simultaneously overlaying a logistics plan adjustment instruction. The system compares the candidate environmental compensation control quantities with the current vehicle's upper limits for cooling / ventilation / humidification capacity item by item.

[0130] If so, a verification failure signal is generated, the mismatch level is forcibly upgraded to the processing logic corresponding to a higher mismatch interval, the microenvironment control compensation stage is skipped, and the logistics plan intervention instruction is output to the physical execution end;

[0131] Specifically, this step ensures that the system does not output invalid environmental control commands, but instead escalates directly to logistical intervention. For example, if a candidate control variable for a first-level mismatch requires the temperature to be reduced to... However, the equipment's limit is... If so, the system will skip the first-level environmental fine-tuning and directly execute the second-level logistics adjustment strategy.

[0132] If not, a verification pass signal is generated, and at least one of the microenvironment control command and logistics plan intervention command that matches the current mismatch level is output.

[0133] In this embodiment, the current mismatch level is level three. The cooperative control results corresponding to level three mismatch include: first, hardware verification is performed—the system checks the candidate environmental compensation control quantity corresponding to level three mismatch (reducing the temperature to...). Humidity rises to The current upper limit of vehicle cooling capacity can be reduced to Humidification capacity can be increased to The verification passed. Based on this, the control output for level three mismatch is a strong intervention reconfiguration command: at the environmental control level, immediately adjust the temperature setpoint to... Humidity setting set to To maximize the suppression of subsequent debt growth rate At the logistics planning level, the original order re-allocation process was initiated, transferring the batch of strawberries from the original Shanghai distribution center to a nearby transit warehouse in Nanjing, which is closer to the current location (allowing for the remaining transportation time to be used for other purposes). (The time was reduced from 4 hours to approximately 1 hour), and at the same time, the Nanjing distribution warehouse was contacted to mark the batch of goods as priority for warehousing to reduce inventory back pressure. By significantly shortening Future preservation debt The integration interval was compressed from 4 hours to 1 hour, while environmental compensation reduced the instantaneous damage rate. It dropped significantly from 23.0 to about 3.6, making The total increment during the remaining transportation period will be approximately [originally] Compressed to approximately On the debt-bearing side, due to The shortening will lead to a shorter time ratio Further reduce thus The price continued to decline, but the market shifted to a low-resistance turnover warehouse. (From 0.308 to approximately 0.15) caused the inventory reduction item to... Improved to Partially offset Shortening decline.

[0134] After executing the control output, the system continues at the sampling period. Collect real-time status data and recalculate the preservation debt value in a loop. Dynamic Debt Cap and composite mismatch index This enables dynamic tracking and servo control throughout the entire process, until the goods are successfully handed over to the warehouse.

[0135] In this embodiment, it is assumed that after executing the above-mentioned strong intervention command, the environment is adjusted to approximately [value missing]. Humidity approximately ( , It belongs to the low temperature and high humidity quadrant. The instantaneous damage rate decreased to Unit: per hour. To (i.e., when it arrives at the Nanjing transit warehouse) In contrast, if this strong intervention had not been implemented and transportation had continued along the original route... Upon arrival in Shanghai, the debt for fresh produce will climb to... Otherwise, the quality will suffer severe and irreversible deterioration. Strong intervention reduced the preservation debt at the final warehousing point from 157.0 to 68.6, reducing the debt increment by approximately 96% (from 92.0 to 3.6). The goods were then stored in the nearest warehouse in an acceptable quality condition, and the entire transportation control loop was completed.

[0136] Exemplary system:

[0137] Please see Figure 2 A collaborative control system for logistics preservation of fresh agricultural products, comprising:

[0138] The data acquisition module is used to acquire physiological attribute data, transportation environment time series data, transportation plan data, and destination inventory status data of the agricultural products to be transported.

[0139] The benchmark determination module is used to determine the initial tolerance value of the agricultural product to be transported based on the physiological attribute data, and to extract the corresponding environmental physiological sensitivity coefficient.

[0140] The preservation debt calculation module is used to couple the real-time environmental deviation corresponding to the transportation environment time series data with the environmental physiological sensitivity coefficient, perform integration and accumulation calculation along the transportation time axis, and generate a preservation debt value that represents irreversible damage.

[0141] The dynamic debt capacity constraint module is used to extract the remaining transportation time from the transportation plan data, calculate the inventory counter-pressure coefficient based on the destination inventory status data, and use the remaining transportation time and the inventory counter-pressure coefficient as spatiotemporal attenuation constraints to dynamically reduce the initial debt capacity value and generate a dynamic debt capacity value that characterizes the future digestion threshold of the system.

[0142] The mismatch grading module is used to perform real-time adversarial calculations on the preservation debt value and the dynamic tolerance debt value, extract the instantaneous difference between the two as the basic mismatch amount, calculate the time change rate of the basic mismatch amount, merge the basic mismatch amount and the time change rate to generate a composite mismatch index; compare the composite mismatch index with a preset interval to determine the mismatch level of the agricultural product to be transported.

[0143] The verification execution module is used to obtain the vehicle environmental adjustment capability parameters in the transportation plan data, compare the candidate environmental compensation control quantity corresponding to the mismatch level with the vehicle environmental adjustment capability parameters, perform hardware boundary feasibility verification, and output the corresponding cooperative control result to the physical execution end based on the result of the hardware boundary feasibility verification and the mismatch level, and cyclically obtain the updated basic data to perform closed-loop control.

[0144] Exemplary computer-readable media:

[0145] Embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps described in the "Exemplary Methods" section above according to the various embodiments of this application.

[0146] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0147] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0148] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0149] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0150] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0151] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A collaborative control method for logistics preservation of fresh agricultural products, characterized in that, Includes the following steps: Acquire physiological attribute data, transportation environment time series data, transportation plan data, and destination inventory status data for agricultural products to be transported; Based on the physiological attribute data, the initial tolerance value of the agricultural products to be transported is determined, and the corresponding environmental physiological sensitivity coefficient is extracted. The real-time environmental deviation corresponding to the time series data of the transportation environment is coupled with the environmental physiological sensitivity coefficient, and integral and cumulative calculation is performed along the transportation time axis to generate a preservation debt value that represents irreversible damage. Extract the remaining transportation time from the transportation plan data, and calculate the inventory back pressure coefficient based on the destination inventory status data. Use the remaining transportation time and the inventory back pressure coefficient as spatiotemporal attenuation constraints to dynamically reduce the initial tolerance value, thereby generating a dynamic tolerance value that characterizes the system's future digestion threshold. The preservation debt value and the dynamic debt capacity value are subjected to real-time adversarial calculation. The instantaneous difference between the two is extracted as the basic mismatch amount. The time change rate of the basic mismatch amount is calculated. The basic mismatch amount and the time change rate are fused to generate a composite mismatch index. The composite mismatch index is compared with a preset range to determine the mismatch level of the agricultural product to be transported. The vehicle environmental adjustment capability parameters in the transportation plan data are obtained. The candidate environmental compensation control quantity corresponding to the mismatch level is compared with the vehicle environmental adjustment capability parameters. Hardware boundary feasibility verification is performed. Based on the result of the hardware boundary feasibility verification and the mismatch level, the corresponding cooperative control result is output to the physical execution end. The updated basic data is obtained in a loop to perform closed-loop control.

2. The collaborative control method for logistics preservation of fresh agricultural products according to claim 1, characterized in that, The determination of the initial tolerance value of the agricultural product to be transported based on the physiological attribute data includes: Obtain information on agricultural product category, maturity level, post-harvest duration, and pre-cooling completion rate from the physiological attribute data; From the preset database of physiological parameters of agricultural products, query the preset loss tolerance benchmark that matches the category information of the agricultural product; Using the maturity level, the post-harvest duration, and the pre-cooling completion rate as correction factors, the preset tolerance benchmark is dynamically corrected to generate an initial tolerance value that characterizes the initial tolerance limit of the agricultural product to be transported.

3. The collaborative control method for logistics preservation of fresh agricultural products according to claim 1, characterized in that, The generated preservation debt value, which represents irreversible damage, includes: Based on the physiological attribute data, determine the temperature and humidity reference values ​​corresponding to the target preservation zone; Extract the real-time temperature and real-time humidity from the time-series data of the transportation environment; calculate the difference between the real-time temperature and the temperature reference value to obtain the temperature deviation; calculate the difference between the real-time humidity and the corresponding humidity reference value to obtain the humidity deviation. Identify the positive and negative directional combinations of the temperature deviation and the humidity deviation, and retrieve the corresponding cross-coupling sensitivity coefficient from the environmental physiological sensitivity coefficients based on the positive and negative directional combinations; The independent sensitivity coefficients among the temperature deviation, humidity deviation, cross-coupling sensitivity coefficient, and environmental physiological sensitivity coefficient are weighted and integrated to obtain the continuous damage integral term. Extract discrete disturbance event data from the time series data of the transportation environment, and convert the discrete disturbance event data into pulse disturbance increase amount according to the preset event penalty mapping relationship; The continuous damage integral term is superimposed with the increase in the pulse disturbance to generate a preservation debt value that monotonically increases over time.

4. The collaborative control method for logistics preservation of fresh agricultural products according to claim 1, characterized in that, The obtained continuous damage integral term includes: Multiply the absolute value of the temperature deviation by the absolute value of the humidity deviation, and then multiply by the cross-coupling sensitivity coefficient to obtain the coupling integral sub-term; Multiply the absolute value of the temperature deviation by the cold damage sensitivity coefficient in the independent sensitivity coefficient to obtain the independent temperature integral term; Multiply the absolute value of the humidity deviation by the water loss sensitivity coefficient in the independent sensitivity coefficient to obtain the humidity independent integral sub-term; The coupled integral term, the temperature-independent integral term, and the humidity-independent integral term are summed and integrated over the time dimension to obtain the continuous damage integral term.

5. The collaborative control method for logistics preservation of fresh agricultural products according to claim 1, characterized in that, The dynamic debt capacity value for generating the future digestion threshold of the characterization system includes: Extract the current warehouse congestion factor, actual outbound speed, and maximum outbound capacity from the destination inventory status data; Calculate the ratio of the actual outbound speed to the maximum outbound capacity, and multiply the difference between the preset constant and the ratio by the current warehouse capacity congestion factor to generate a dimensionless inventory back pressure coefficient. Obtain the total estimated time for the entire journey from the transportation plan data, and calculate the ratio of the remaining transportation time to the total estimated time for the entire journey as a time scaling parameter; Using the time scaling parameter and the inventory counter-pressure coefficient, the initial tolerance value is reduced according to the preset scaling logic to generate a monotonically decreasing dynamic tolerance value.

6. The collaborative control method for logistics preservation of fresh agricultural products according to claim 1, characterized in that, The step of fusing the basic mismatch amount with the rate of change over time to generate a composite mismatch index includes: Determine whether the rate of change of time is greater than zero; If so, the time change rate is multiplied by a preset trend weight coefficient and a reference time constant to obtain a trend component, and the basic mismatch is added to the trend component to generate a composite mismatch index. If not, then set the trend component to zero and directly use the basic mismatch amount as the composite mismatch index; The reference time constant is used to unify the data dimensions of each item in the composite mismatch index.

7. The collaborative control method for logistics preservation of fresh agricultural products according to claim 1, characterized in that, The determination of the mismatch level of the agricultural products to be transported includes: Obtain a first threshold and a second threshold preset by the system to construct multiple preset intervals, wherein the second threshold is greater than the first threshold; If the composite mismatch index is greater than zero and less than or equal to the first threshold, then output a data label indicating a level 1 mismatch. If the composite mismatch index is greater than the first threshold and less than or equal to the second threshold, then output a data label indicating a mismatch level of two. If the composite mismatch index is greater than the second threshold, a data label indicating a mismatch level of three is output.

8. The collaborative control method for logistics preservation of fresh agricultural products according to claim 7, characterized in that, The output corresponding to the collaborative control result sent to the physical execution end includes: Match the mismatch level in the preset control strategy mapping table to obtain the corresponding candidate environmental compensation control quantity, and determine whether the candidate environmental compensation control quantity is greater than the upper limit of the capability corresponding to the vehicle environmental adjustment capability parameter. If so, a verification failure signal is generated, the mismatch level is forcibly upgraded to the processing logic corresponding to a higher mismatch interval, the microenvironment control compensation stage is skipped, and the logistics plan intervention instruction is output to the physical execution end; If not, a verification pass signal is generated, and at least one of the microenvironment control command and logistics plan intervention command that matches the current mismatch level is output.

9. A system for implementing the collaborative control method for logistics preservation of fresh agricultural products according to any one of claims 1-8, characterized in that, include: The data acquisition module is used to acquire physiological attribute data, transportation environment time series data, transportation plan data, and destination inventory status data of the agricultural products to be transported. The benchmark determination module is used to determine the initial tolerance value of the agricultural products to be transported based on the physiological attribute data, and to extract the corresponding environmental physiological sensitivity coefficient. The preservation debt calculation module is used to couple the real-time environmental deviation corresponding to the transportation environment time series data with the environmental physiological sensitivity coefficient, perform integration and accumulation calculation along the transportation time axis, and generate a preservation debt value that represents irreversible damage. The dynamic debt capacity constraint module is used to extract the remaining transportation time from the transportation plan data, calculate the inventory counter-pressure coefficient based on the destination inventory status data, and use the remaining transportation time and the inventory counter-pressure coefficient as spatiotemporal attenuation constraints to dynamically reduce the initial debt capacity value and generate a dynamic debt capacity value that characterizes the future digestion threshold of the system. The mismatch grading module is used to perform real-time adversarial calculations on the preservation debt value and the dynamic tolerance debt value, extract the instantaneous difference between the two as the basic mismatch amount, calculate the time change rate of the basic mismatch amount, merge the basic mismatch amount and the time change rate to generate a composite mismatch index; compare the composite mismatch index with a preset interval to determine the mismatch level of the agricultural product to be transported. The verification execution module is used to obtain the vehicle environmental adjustment capability parameters in the transportation plan data, compare the candidate environmental compensation control quantity corresponding to the mismatch level with the vehicle environmental adjustment capability parameters, perform hardware boundary feasibility verification, and output the corresponding cooperative control result to the physical execution end based on the result of the hardware boundary feasibility verification and the mismatch level, and cyclically obtain the updated basic data to perform closed-loop control.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer-executable instructions are executed by a processor, they implement the steps of the method as described in any one of claims 1-8.

Images