Cold chain transportation management method and system based on fruit and vegetable maturity

Abstract

The invention provides a cold chain transportation management method and system based on fruit and vegetable maturity, and relates to the technical field of transportation management, and the method comprises the steps: obtaining a surface image of a to-be-transported fruit and vegetable, so as to analyze the maturity grade; after control parameters are matched according to the destination coordinates, the fruit and vegetable types and the maturity grades, the warehouse environment of the cold-chain transport vehicle is adjusted; and in the transportation process, the arrival time and the ripening rate of the fruits and vegetables are calculated, so that the warehouse environment of the cold-chain transportation vehicle is dynamically controlled after the adjustment parameters are analyzed. According to the method, maturity analysis is carried out on fruit and vegetable surface images, in the transportation process, environment data and the remaining transportation distance in a warehouse are collected in real time, the fruit and vegetable maturity rate and arrival time are analyzed, corresponding adjustment parameters are generated, self-adaptive adjustment control is carried out on the warehouse environment according to the adjustment parameters, and the problem that cold chain parameter control is not matched is solved.

Description

Technical Field

[0001] This application relates to the technical field of transportation management, and in particular to a method and system for cold chain transportation management based on the maturity of fruits and vegetables. Background Technology

[0002] With the development of fresh food e-commerce and cross-regional agricultural product supply chains, the demand for long-distance transportation of fruits and vegetables has increased significantly. To reduce spoilage rates and maintain the freshness of fruits and vegetables, cold chain transportation technology is widely used in the distribution process. Currently, cold chain transportation systems mainly rely on temperature and humidity control to maintain an ideal storage and transportation environment for fruits and vegetables throughout the entire transportation process, thereby extending shelf life and increasing the added value of the product.

[0003] In existing technologies, parameters such as transport temperature and humidity are usually preset before loading based on the type of fruits and vegetables, the distance to the destination, and seasonal climate conditions. During operation, the transport vehicle mainly relies on the on-board temperature control system to maintain the preset environment and collects sensor data at regular intervals to determine whether the equipment is operating normally.

[0004] Although temperature and humidity management during fruit and vegetable transportation can be achieved through fixed environmental control methods, existing solutions fail to dynamically adjust the cold chain environment according to the maturity of fruits and vegetables when there are significant differences in maturity or transportation distance. This results in some fruits and vegetables becoming overripe or deteriorating prematurely during transportation, leading to a mismatch between cold chain parameters and the condition of fruits and vegetables, and a decline in quality at the end of transportation. Summary of the Invention

[0005] To overcome the aforementioned problem of mismatch in cold chain parameter control, this application provides a cold chain transportation management method and system based on fruit and vegetable maturity, which can dynamically adjust the warehouse environment according to the maturity level of fruits and vegetables and transportation process data, thereby achieving adaptive preservation control of fruit and vegetable quality throughout the entire process.

[0006] On one hand, this invention provides a cold chain transportation management method based on fruit and vegetable maturity, applied to the transportation of fruits and vegetables after classification by type. The method includes: acquiring surface images of the fruits and vegetables to be transported; performing maturity analysis on the surface images to obtain maturity levels; matching parameters from a preset cold chain parameter database based on destination coordinates, fruit and vegetable type, and the maturity level to obtain corresponding control parameters; adjusting the cargo environment of the cold chain transport vehicle using the control parameters; calculating the remaining transportation distance and collecting environmental data within the cargo compartment of the cold chain transport vehicle in real time during transportation; calculating the arrival time based on the remaining transportation distance; analyzing the maturity rate of the fruits and vegetables based on the environmental data; and determining adjustment parameters based on the arrival time and maturity rate; and dynamically controlling the cargo environment of the cold chain transport vehicle according to the adjustment parameters.

[0007] As a preferred embodiment, the steps of acquiring surface images of the fruits and vegetables to be transported, performing maturity analysis on the surface images, and obtaining the maturity level of the fruits and vegetables include: acquiring visible light images of the fruit and vegetable surface using an RGB camera set in the loading area; preprocessing the visible light images to obtain standardized fruit and vegetable surface images; and extracting color feature parameters from the standardized fruit and vegetable surface images; acquiring spectral reflectance images of the fruit and vegetable surface within a specific wavelength range using a multispectral camera set in the loading area; performing band analysis on the spectral reflectance images; extracting reflectance data of a preset first and second band on the fruit and vegetable surface; calculating the ratio of the reflectance values ​​of the first and second bands to obtain spectral feature parameters; and inputting the color feature parameters and the spectral feature parameters into a pre-trained maturity classification model to output the maturity level of the fruits and vegetables.

[0008] As a preferred embodiment, the step of matching parameters from a preset cold chain parameter database based on destination coordinates, fruit and vegetable types, and maturity levels to obtain corresponding control parameters, and adjusting the cargo environment of the cold chain transport vehicle using the control parameters, includes: obtaining the current location coordinates and destination coordinates of the cold chain transport vehicle through an onboard GPS positioning system, calculating the actual transport distance between the two points, and calculating the estimated transport time based on the actual transport distance and the vehicle's average speed; inputting the fruit and vegetable types, maturity levels, and estimated transport time as query conditions into the preset cold chain parameter database, retrieving the record with the highest matching degree from the cold chain parameter database, and extracting the control parameters corresponding to the record with the highest matching degree; and sending the control parameters to the environmental control system of the cold chain transport vehicle to adjust the cargo environment of the cold chain transport vehicle.

[0009] As a preferred embodiment, the steps of calculating the remaining transportation distance and collecting environmental data within the cargo hold of the cold chain transport vehicle in real time during transportation include: collecting the real-time location coordinates of the cold chain transport vehicle at preset first time intervals using an onboard GPS positioning system, and calculating the remaining transportation distance based on the real-time location coordinates and destination coordinates; collecting temperature data at each monitoring point within the cargo hold at preset second time intervals using multiple temperature sensors located at different locations within the cargo hold, and calculating the average value of the temperature data as the average temperature of the cargo hold; collecting humidity data at each monitoring point within the cargo hold at preset second time intervals using multiple humidity sensors located at different locations within the cargo hold, and calculating the average value of the humidity data as the average humidity of the cargo hold; collecting oxygen concentration, carbon dioxide concentration, and ethylene concentration within the cargo hold at preset second time intervals using a gas sensor array located within the cargo hold; and using the average temperature, average humidity, oxygen concentration, carbon dioxide concentration, and ethylene concentration of the cargo hold as environmental data.

[0010] As a preferred embodiment, the steps of calculating the arrival time based on the remaining transportation distance, analyzing the ripening rate of fruits and vegetables based on the environmental data, and analyzing adjustment parameters based on the arrival time and the ripening rate include: calculating the arrival time based on the remaining transportation distance and the real-time driving speed of the vehicle; when the fluctuation range of the real-time driving speed exceeds a preset threshold, correcting the arrival time based on the average speed data of historical road segments to obtain a corrected arrival time; querying the corresponding rate correction coefficient from a preset ripening rate influencing factor database based on the environmental data, inputting the ripening level and the environmental data into a preset ripening rate analysis model to obtain the ripening rate; calculating the predicted ripening value of the fruits and vegetables upon arrival at the destination based on the ripening rate and the corrected arrival time, and analyzing adjustment parameters based on the predicted ripening value.

[0011] As a preferred embodiment, the step of analyzing the adjustment parameters based on the predicted maturity value includes: determining whether the predicted maturity value is within a preset target maturity range; when the predicted maturity value exceeds the upper limit of the target maturity range, querying the cold chain parameter database for adjustment parameters that can reduce the maturity rate of the current fruit and vegetable variety; when the predicted maturity value is below the lower limit of the target maturity range, querying the cold chain parameter database for adjustment parameters that can increase the maturity rate of the current fruit and vegetable variety; and when the predicted maturity value is within the target maturity range, keeping the current environmental control parameters in the cold chain transport vehicle's cargo compartment unchanged.

[0012] As a preferred embodiment, the step of dynamically controlling the cargo warehouse environment of the cold chain transport vehicle according to the adjustment parameters includes: comparing the difference between the adjustment parameters and the control parameters to obtain a deviation value, and determining the adjustment priority based on the deviation value; for temperature adjustment, when the absolute value of the temperature deviation is greater than a preset temperature adjustment threshold, calculating the required cooling power or heating power, and controlling the cooling module or heating module to operate according to the cooling power or heating power; for humidity adjustment, when the absolute value of the humidity deviation is greater than a preset humidity adjustment threshold, calculating the required humidification amount or dehumidification amount, and controlling the humidification module or dehumidification module to operate according to the humidification amount or dehumidification amount; for gas concentration adjustment, when the absolute values ​​of the oxygen concentration deviation, carbon dioxide concentration deviation, or ethylene concentration deviation are greater than the corresponding gas adjustment threshold, calculating the required gas injection amount or discharge amount, and controlling the gas adjustment module to open the corresponding gas valve for injection or exhaust operation, or to start the adsorption device or catalytic oxidation device for ethylene removal.

[0013] On the other hand, this application also provides a cold chain transportation management system based on fruit and vegetable maturity, applied to the transportation of fruits and vegetables after classification by type. The system includes: an image acquisition module for acquiring surface images of the fruits and vegetables to be transported, performing maturity analysis on the surface images to obtain the maturity level of the fruits and vegetables; a data matching module for matching parameters from a preset cold chain parameter database based on destination coordinates, fruit and vegetable type, and the maturity level to obtain corresponding control parameters, and adjusting the cargo environment of the cold chain transport vehicle using the control parameters; a data acquisition module for calculating the remaining transportation distance and collecting environmental data within the cargo compartment of the cold chain transport vehicle in real time during transportation; a data analysis module for calculating the arrival time based on the remaining transportation distance, analyzing the maturity rate of the fruits and vegetables based on the environmental data, and analyzing adjustment parameters based on the arrival time and maturity rate; and a parameter adjustment module for dynamically controlling the cargo environment of the cold chain transport vehicle according to the adjustment parameters.

[0014] The cold chain transportation management method and system based on fruit and vegetable maturity provided in this application have the following technical effects: adaptive adjustment. By analyzing the maturity of fruit and vegetable surface images and matching parameters with destination coordinates, fruit and vegetable types, and maturity levels, cold chain transport vehicles can obtain environmental control parameters that match the actual state of the fruits and vegetables before transportation begins. During transportation, by collecting environmental data and remaining transportation distance in real time within the warehouse, analyzing the fruit and vegetable maturity rate and arrival time, generating corresponding adjustment parameters, and adaptively adjusting and controlling the warehouse environment accordingly, the aforementioned problem of mismatched cold chain parameter control is overcome. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the cold chain transportation management method based on fruit and vegetable maturity provided in an embodiment of the present invention. Figure 2 This is a schematic block diagram of the structure of a cold chain transportation management system based on fruit and vegetable maturity provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or sub-modules is not necessarily limited to those steps or sub-modules explicitly listed, but may include other steps or sub-modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0019] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0020] Example 1: like Figure 1 As shown in the example, this application provides a cold chain transportation management method based on fruit and vegetable maturity. Applied to the transportation of fruits and vegetables after variety classification, it enables adaptive adjustment of environmental parameters during transportation to improve the quality consistency and preservation effect of fruits and vegetables upon arrival at their destination. This cold chain transportation management method specifically includes: Step S1: Obtain surface images of the fruits and vegetables to be transported, perform maturity analysis on the surface images, and obtain the maturity level of the fruits and vegetables.

[0021] The surface images of the fruits and vegetables to be transported are acquired using an image acquisition device. This device can be installed in the fruit and vegetable loading area or at the sorting line, preferably using an industrial camera with a resolution of at least 1920×1080 pixels to ensure image clarity. The surface images are uniformly illuminated using a lighting compensation module to avoid interference from shadows, reflections, and other factors that could affect the image analysis results. The maturity analysis module performs color and texture feature analysis on the acquired surface images, extracting key visual feature parameters of the fruit and vegetable surface. By statistically analyzing color components (such as the average values ​​of R, G, and B channels), brightness distribution, and texture roughness, the maturity stage of the fruits and vegetables is determined.

[0022] When testing mangoes, the acquired surface images are preprocessed, and the average value of the R channel in the surface color components is analyzed. When the average R channel value is between 150 and 180 and the standard deviation of surface brightness is less than 15, the mango is determined to be in the early ripening stage. When the average R channel value exceeds 200 and the texture feature contrast decreases to below 0.4, it is determined to be in the suitable ripening stage. The ripeness level of fruits and vegetables is obtained through the above analysis, and this level serves as the basis for subsequent environmental parameter matching.

[0023] Step S2: Match parameters from a preset cold chain parameter database based on destination coordinates, fruit and vegetable types, and maturity levels to obtain corresponding control parameters, and adjust the cargo warehouse environment of the cold chain transport vehicle through the control parameters.

[0024] The destination coordinates are obtained through the vehicle-mounted positioning module, and the types and maturity levels of fruits and vegetables are retrieved from the loading records. Then, the destination coordinates, fruit and vegetable types, and maturity levels are used as query conditions and input into a cold chain parameter database for matching. This database pre-stores optimal transportation environment parameters for different fruit and vegetable types at different maturity stages, including temperature, humidity, oxygen concentration, carbon dioxide concentration, and ethylene concentration. The matching algorithm employs a feature similarity-based parameter retrieval algorithm, calculating the Euclidean distance between the query conditions and sample records in the database, and selecting the record with the highest similarity as the optimal matching result. Based on the control parameters obtained from the matching, the control module controls the refrigeration system, humidification system, and gas conditioning system respectively to adjust the temperature, humidity, and gas composition of the cargo compartment.

[0025] For bananas with a ripeness level of "moderately ripe," the corresponding control parameters in the database are: temperature 13℃, humidity 90%, oxygen concentration 3%, carbon dioxide concentration 2%, and ethylene concentration 0.8ppm. Based on these parameters, the system automatically controls the refrigeration module to output the corresponding cooling capacity, lowering the warehouse temperature to 13℃; it controls the humidification module to maintain humidity at 90% using an ultrasonic humidifier; and it controls the gas regulation module to inject nitrogen to dilute the oxygen concentration and activate the ethylene adsorption device to maintain the ethylene concentration at 0.8ppm, thus providing a stable and suitable environment for banana transportation.

[0026] Step S3: During transportation, calculate the remaining transportation distance and collect environmental data inside the cargo compartment of the cold chain transport vehicle in real time.

[0027] The vehicle's current location coordinates are collected at fixed time intervals (e.g., 30 seconds) by the onboard GPS module, and the remaining transportation distance is calculated based on the destination coordinates. The remaining transportation distance calculation module uses a path planning algorithm to calculate the path length of a preset route to obtain the remaining distance along the preset transportation path. Simultaneously, the environmental monitoring module periodically collects environmental data inside the warehouse, including temperature, humidity, oxygen concentration, carbon dioxide concentration, and ethylene concentration. The data collection frequency is set according to the sensor type; a sampling period of 60 seconds is preferred for temperature and humidity sensors, and a sampling period of 120 seconds is preferred for gas concentration sensors.

[0028] For example, during an inter-provincial transport mission, the system acquires the vehicle's latitude and longitude coordinates every 30 seconds and calculates the remaining transport distance as 420 kilometers. Inside the cargo hold, four temperature sensors collect an average temperature of 12.8℃, a humidity sensor measures an average humidity of 91%, and gas sensors detect oxygen concentrations of 3.1%, carbon dioxide concentrations of 1.9%, and ethylene concentrations of 0.82 ppm. The system records this real-time data as environmental data for the current transport cycle for subsequent analysis.

[0029] Step S4: Calculate the arrival time based on the remaining transportation distance, analyze the ripening rate of fruits and vegetables based on environmental data, and analyze the adjustment parameters based on the arrival time and ripening rate.

[0030] The estimated arrival time is calculated based on the remaining transport distance and the vehicle's real-time speed. The speed is calculated from the displacement and time difference between two consecutive GPS sampling points. When a speed fluctuation exceeds a set threshold (e.g., ±15%), the system obtains the average speed of that road segment through a road traffic data interface and corrects the estimated arrival time. Subsequently, the system analyzes the ripening rate of fruits and vegetables based on current environmental data. The ripening rate analysis module uses an environmental factor correlation model based on empirical data, inputting temperature, humidity, oxygen concentration, carbon dioxide concentration, and ethylene concentration into the model, and outputting a ripening rate index of fruits and vegetables under the current environment. Based on the estimated arrival time and the current ripening rate, the predicted maturity value of the fruits and vegetables upon arrival at their destination is calculated, and the corresponding adjustment parameters are generated by the control logic module.

[0031] For bananas under the current environmental data, the system calculates a ripening rate index of 1.08 (relative to the ripening rate under standard conditions). With an estimated transport time of 10 hours, the predicted ripeness upon arrival is slightly higher than the upper limit of the target ripening range. Based on this, the system generates deceleration adjustment parameters, indicating a 1°C reduction in temperature, a 0.5% decrease in oxygen concentration, and a 0.2 ppm decrease in ethylene concentration to slow the ripening process.

[0032] Step S5: Dynamically control the cargo warehouse environment of the cold chain transport vehicle according to the adjustment parameters.

[0033] The system compares the adjusted parameters with the current control parameters, calculates the deviation values ​​of each environmental element, and performs dynamic adjustments according to preset priorities. Temperature adjustment has the highest priority; when the deviation exceeds 0.5℃, the system controls the refrigeration module to output additional cooling power or reduces the heating power. Humidity adjustment is the next highest priority; when the deviation exceeds 2%, the system controls the humidification or dehumidification module to operate. Gas concentration deviation has the lowest priority; when the oxygen concentration, carbon dioxide concentration, or ethylene concentration is detected to exceed the target value, the system controls the gas valve to perform inflation or deflation operations. The system monitors the adjustment effect in real time during the adjustment process to ensure that the environmental parameters gradually approach the target values.

[0034] When the system generates adjustment parameters of a 1°C decrease in temperature, a 2% increase in humidity, and a 0.2 ppm decrease in ethylene concentration, the control module instructs the refrigeration module to increase the compressor's operating power by 10%, controls the humidification module to start for 30 seconds, and controls the gas regulation module to start the ethylene adsorption device for 2 minutes. After the environmental parameters are adjusted, the system re-collects environmental data to verify the adjustment effect and ensure that the environment returns to the preset control range.

[0035] In this embodiment, surface images of the fruits and vegetables to be transported are acquired, and maturity analysis is performed on these images to determine their maturity level. Subsequently, based on the destination coordinates, fruit / vegetable type, and maturity level, parameters are matched from a pre-set cold chain parameter database to obtain control parameters corresponding to the fruit / vegetable. The cargo environment of the cold chain transport vehicle is then initially adjusted according to these control parameters. During transport, the remaining transport distance is calculated in real time, and environmental data within the cargo compartment of the cold chain transport vehicle is collected synchronously. Next, the arrival time is calculated based on the remaining transport distance, and the maturity rate of the fruits and vegetables is analyzed based on the environmental data. Finally, adjustment parameters are derived based on the arrival time and maturity rate, and the cargo environment of the cold chain transport vehicle is dynamically controlled according to these parameters, thereby achieving adaptive adjustment of the fruit and vegetable preservation environment throughout the entire transport process.

[0036] The above technical solution enables intelligent matching of environmental parameters for cold chain transportation based on the maturity level of fruits and vegetables. During transportation, dynamic adjustments are made based on the ripening rate and arrival time of the fruits and vegetables, achieving adaptive management throughout the entire cold chain transportation process and overcoming the problem of mismatched cold chain parameters. This not only improves the accuracy and real-time performance of environmental control during fruit and vegetable transportation, avoiding over-refrigeration or environmental incompatibility caused by fixed parameter settings, but also reduces energy costs while ensuring consistent fruit and vegetable quality, extends shelf life, and reduces transportation losses, thus improving the overall economy and reliability of cold chain transportation for fruits and vegetables.

[0037] Furthermore, step S1 can preferably be: Visible light images of the fruit and vegetable surface are acquired by an RGB camera set in the loading area. The visible light images are preprocessed, including noise reduction, illumination equalization, and region of interest extraction, to obtain standardized fruit and vegetable surface images. Color feature parameters are then extracted from the standardized fruit and vegetable surface images. The color feature parameters include the mean color components of the RGB color space, the hue and saturation components of the HSV color space, and the chromaticity components of the LAB color space.

[0038] Light equalization can reduce color distortion caused by differences in ambient light, making the color data of different batches of fruits and vegetables comparable; by extracting regions of interest, interference from the background of fruits and vegetables, the edges of the box, or reflective areas can be effectively removed, thus ensuring that the color feature parameters reflect the true color information of the surface of the fruits and vegetables.

[0039] In practical implementation, the brightness of the RGB components can be compensated by histogram equalization algorithm, the outline region of fruits and vegetables can be extracted by morphological operations, and the pixel values ​​of non-fruits and vegetables can be set to zero, so as to obtain a stable and consistent color feature input.

[0040] A multispectral camera set up in the loading area acquires spectral reflectance images of the fruit and vegetable surface within a specific wavelength range. Band analysis is performed on the spectral reflectance images to extract reflectance data of the fruit and vegetable surface in a preset first wavelength range (650nm to 750nm) and a second wavelength range (450nm to 550nm). The ratio of the reflectance data of the first wavelength range and the second wavelength range is calculated to obtain spectral characteristic parameters.

[0041] Multispectral reflectance analysis can reveal changes in pigment composition on the surface of fruits and vegetables. The 650nm to 750nm band primarily reflects the content of anthocyanins and carotenoids, while the 450nm to 550nm band corresponds to chlorophyll reflectance characteristics. By calculating the reflectance ratio of these two bands, the pigment transformation trend in fruits and vegetables from immature to fully ripe stages can be characterized.

[0042] The average reflection intensity of two bands can be recorded using a dual-channel integrating sphere spectrometer, and expressed as R=R 650-750 / R 450-550 Calculate the spectral characteristic parameters. If R increases, it indicates that the maturity of fruits and vegetables has improved.

[0043] Color feature parameters and spectral feature parameters are input into a pre-trained maturity classification model. The maturity classification model adopts a convolutional neural network structure and is trained by supervised learning on fruit and vegetable sample images at different maturity stages.

[0044] The maturity classification model outputs the maturity level of fruits and vegetables. The maturity level is divided into five levels according to the degree of maturity: immature, early ripe, moderately ripe, fully ripe and overripe. Each level corresponds to a maturity value range.

[0045] In this step, by inputting multi-source feature parameters into the maturity classification model, the surface color changes of fruits and vegetables and the internal pigment reflection characteristics can be considered simultaneously, thereby achieving high-precision judgment of the maturity of fruits and vegetables; the multi-layer feature extraction mechanism of the convolutional neural network can automatically learn the spectral difference characteristics of fruits and vegetables at different maturity stages, avoiding the misjudgment problem of traditional manual thresholding methods in complex lighting environments.

[0046] In practical applications, the maturity classification model adopts a structure of 3 convolutional layers and 2 fully connected layers, and is trained using the cross-entropy loss function. When the accuracy of predicting maturity level is higher than 95%, the model can be deployed to the loading area detection terminal to achieve online real-time judgment.

[0047] Specifically, the training process for the maturity classification model is as follows: Model structure: The Convolutional Neural Network (CNN) consists of 3 convolutional layers, 3 pooling layers, and 2 fully connected layers. The convolutional kernel sizes are 3×3, 5×5, and 3×3, respectively, and the activation function is ReLU.

[0048] Training data: ≥2000 surface images were collected for each type of fruit and vegetable, covering five levels: immature, early ripe, moderately ripe, fully ripe, and overripe.

[0049] Data augmentation: rotation, translation, brightness adjustment, and noise reduction make the model robust to changes in lighting and angle.

[0050] Training process: The cross-entropy loss function is used, the optimizer is Adam, the learning rate is 0.001, the number of training rounds is 50, and the validation set accounts for 20% of the training set.

[0051] Output: The maturity level is the classification result, and the probability value is also output to judge the reliability of the prediction.

[0052] Furthermore, step S2 can preferably be: The current location coordinates and destination coordinates of the cold chain transport vehicle are obtained through the vehicle-mounted GPS positioning system. The actual transport distance between the two points is calculated, and the estimated transport time is calculated based on the actual transport distance and the average driving speed of the vehicle.

[0053] By acquiring GPS positioning information in real time, the total transportation distance and remaining transportation time can be accurately calculated, providing a timely basis for subsequent dynamic environmental control; combined with historical route data, travel time errors caused by traffic conditions or road types can be corrected.

[0054] In actual transportation, the vehicle remote monitoring system can be used to update the current location in real time. When the average vehicle speed fluctuation is detected to exceed the set threshold, the estimated transportation time parameter can be automatically adjusted to improve the prediction accuracy.

[0055] The query conditions are: fruit and vegetable type, maturity level, and estimated transportation time. The query is input into a pre-set cold chain parameter database. The cold chain parameter database stores the optimal environmental control parameters for different fruit and vegetable types under different maturity levels and transportation time conditions. The optimal environmental control parameters are obtained by statistical analysis and machine learning modeling of historical transportation data. The database is then used to retrieve the record with the highest matching degree with the query conditions. The corresponding control parameters are extracted from the record with the highest matching degree. The control parameters include target temperature value, target humidity value, target oxygen concentration value, target carbon dioxide concentration value, and target ethylene concentration value.

[0056] Multi-condition matching can be used to achieve precise environmental control based on the characteristics of fruits and vegetables, avoiding over-cooling or over-ripening problems caused by using the same cold chain parameters for different types or ripeness of fruits and vegetables; machine learning models can continuously optimize the parameter database based on historical transportation results, improving matching accuracy and environmental adaptability.

[0057] The control parameters in the database can be generated based on the KNN algorithm or the random forest model. When the Euclidean distance between the input query conditions and historical samples is minimized, the system automatically extracts the corresponding parameters as control targets, ensuring that the environmental regulation strategy has data support and traceability.

[0058] The control parameters are sent to the environmental control system of the cold chain transport vehicle to adjust the cargo compartment environment. The environmental control system includes a refrigeration module, a heating module, a humidification module, a dehumidification module, and a gas regulation module. According to the control parameters, the environmental control system controls the refrigeration module or heating module to adjust the cargo compartment temperature to the target temperature value, controls the humidification module or dehumidification module to adjust the cargo compartment humidity to the target humidity value, and controls the gas regulation module to adjust the oxygen concentration and carbon dioxide concentration in the cargo compartment to the target oxygen concentration value and carbon dioxide concentration to the target carbon dioxide concentration value by filling nitrogen or venting gas. It also adjusts the ethylene concentration to the target ethylene concentration value through an adsorption device or a catalytic oxidation device.

[0059] Through multi-module linkage adjustment, dynamic and stable control of the fruit and vegetable transportation environment can be achieved, avoiding premature ripening of fruits and vegetables due to insufficient oxygen or excessive ethylene concentration; at the same time, fine corrections can be made based on real-time environmental feedback, improving the intelligence and safety of the transportation process.

[0060] When the control system detects a temperature deviation of more than ±0.5℃ or a humidity deviation of more than ±3%, it can automatically trigger a PID control algorithm to adjust the cooling power and humidification rate to ensure that the environmental parameters remain stable within the target range, thereby significantly extending the shelf life of fruits and vegetables and reducing losses.

[0061] Furthermore, step S3 can preferably be: The vehicle-mounted GPS positioning system collects the real-time location coordinates of the cold chain transport vehicle at preset first time intervals. The remaining transport distance is calculated based on the real-time location coordinates and the destination coordinates. The remaining transport distance is the path length from the current location to the destination along the preset path.

[0062] By periodically collecting GPS positioning information and combining it with preset transportation routes to calculate the remaining distance, the system can reflect the transportation progress of vehicles in real time and provide a dynamic time reference for environmental regulation. At the same time, it can trigger system warnings when route deviations or abnormal stops are detected, preventing the risk of overripe fruits and vegetables due to transportation delays.

[0063] The first time interval can be set to 1 minute. After each time the current location coordinates are collected, the system calls the weighted Dijkstra algorithm in the path planning module to recalculate the shortest path length from the current location to the destination, and uses this path length as the current remaining transportation distance. If the change in the remaining transportation distance collected three times in a row is less than a preset threshold (such as 100 meters), the system determines that the vehicle is in a low-speed or stagnant state and automatically extends the estimated arrival time so that the subsequent maturity rate analysis module can adjust the adjustment parameters.

[0064] Temperature data from each monitoring point in the warehouse is collected by multiple temperature sensors placed at different locations within the warehouse at preset second time intervals, and the average value of the temperature data is calculated as the average temperature of the warehouse.

[0065] By deploying temperature sensors at multiple points, environmental control deviations caused by single-point measurement errors can be avoided. Especially in situations where the warehouse space is large or the airflow distribution is uneven, temperature distribution uniformity can be assessed, thereby improving control accuracy.

[0066] Temperature sensors are installed at the top, middle and bottom of the warehouse, with two sensors each, for a total of six sampling points. Temperature values ​​are collected every 30 seconds. After receiving data from each monitoring point, the system performs outlier detection (such as removing measurement results that deviate from the average value by ±2σ), and then calculates the arithmetic mean to obtain the average temperature of the warehouse. When the temperature variance exceeds the set threshold, the system determines that there is local condensation or abnormal air circulation, and triggers the airflow circulation device to perform temperature equalization.

[0067] Humidity data from various monitoring points within the warehouse is collected at second intervals using multiple humidity sensors placed at different locations within the warehouse. The average humidity value of the collected humidity data is then calculated as the average humidity of the warehouse.

[0068] The humidity sensor array can monitor the spatial balance of air humidity inside the warehouse, preventing excessive humidity in some areas from causing moisture accumulation, mold, or rot on the surface of fruits and vegetables. At the same time, combined with temperature data, it can assess the dew point status of the air inside the warehouse in real time to prevent condensation.

[0069] A capacitive humidity sensor is installed at the front, rear and middle of the warehouse to sample the relative humidity every 30 seconds. The system uses a Kalman filter algorithm to smooth the continuous humidity data and then calculates the average value. If the humidity is lower than the set lower limit (e.g. 85%) and the temperature is 2°C higher than the target temperature, the system automatically activates the humidification module to replenish water vapor and ensure that fruits and vegetables maintain an ideal humid environment.

[0070] The oxygen, carbon dioxide, and ethylene concentrations in the cargo warehouse are collected every second time interval by an array of gas sensors installed inside the warehouse.

[0071] Gas sensor arrays are used to detect dynamic changes in the main gas components in the warehouse, which are indirect indicators of the respiration intensity and ripening rate of fruits and vegetables. A decrease in oxygen concentration and an increase in carbon dioxide and ethylene concentrations indicate accelerated metabolism of fruits and vegetables. Therefore, real-time monitoring can be used to assess whether fruits and vegetables are overripe.

[0072] The gas sensor array includes an electrochemical oxygen sensor, an infrared carbon dioxide sensor, and a metal oxide semiconductor ethylene sensor, arranged in the air circulation area in the center of the warehouse. Concentration data is collected every 30 seconds and uploaded to the central control unit. The system calculates the rate of change of each gas concentration based on the detection trend. If the rate of increase of ethylene concentration exceeds the threshold of 0.2 ppm / h, the catalytic oxidation device is automatically triggered to decompose ethylene and prevent accelerated maturation.

[0073] The average temperature, average humidity, oxygen concentration, carbon dioxide concentration, and ethylene concentration of the warehouse were used as environmental data.

[0074] By unifying multidimensional environmental parameters into a real-time environmental data vector, the system can simultaneously assess the ripening status of fruits and vegetables and the transportation environment. Through this environmental data, the system can couple and analyze time variables (remaining transportation distance) with spatial variables (temperature and humidity distribution, gas concentration), providing highly timely input for the calculation of subsequent adjustment parameters.

[0075] The environmental data vector E is updated every 30 seconds. t =[D t ,T t H t O2 t CO2 t C2H4 t ], where D t For the remaining transport distance, T t H represents the average temperature of the warehouse. t The average humidity of the warehouse, O2 t CO2 t C2H4 t These are the concentrations of oxygen, carbon dioxide, and ethylene, respectively; the central control system will...t Input the ripening rate analysis model to predict the current ripening trend of fruits and vegetables, thereby dynamically adjusting temperature or gas parameters to achieve intelligent environmental regulation.

[0076] Furthermore, step S4 can preferably be: The arrival time is calculated based on the remaining transport distance and the vehicle's real-time speed. The real-time speed is obtained by differential calculation of the position coordinates of multiple consecutive time points. When the fluctuation of the real-time speed exceeds a preset threshold, the arrival time is corrected based on the average speed data of historical road segments to obtain the corrected arrival time.

[0077] By continuously monitoring the actual operating speed of vehicles and dynamically calculating arrival time, it is possible to effectively cope with fluctuations in transportation time caused by factors such as road congestion, speed limits, or temporary detours, ensuring the accuracy of predicted arrival time and thus improving the timeliness of subsequent maturity prediction and environmental control.

[0078] The system records the vehicle's real-time location coordinates every 30 seconds, calculates the instantaneous speed by the coordinate difference between adjacent times, and uses a sliding window method to calculate the average speed data within the last 5 minutes. When the speed fluctuation exceeds the ±15% threshold, the system automatically calls the average driving speed of the corresponding road segment in the historical transportation database to make a weighted correction to the current estimated arrival time. If the system detects three consecutive speed drops exceeding 20%, the current arrival time is extended by the corresponding proportion to avoid premature arrival that could cause fruits and vegetables to overripe.

[0079] Based on environmental data, the corresponding rate correction coefficient is queried from the preset maturity rate influencing factor database. The rate correction coefficient characterizes the degree of influence of environmental parameters on the maturity rate when they deviate from the control parameters. The maturity level and environmental data are input into the preset maturity rate analysis model to obtain the maturity rate.

[0080] The maturation rate influencing factor database stores the maturation rate correction information of different fruit and vegetable varieties under multidimensional environmental parameters. It is used to reflect the degree of influence of the deviation between the warehouse environment and ideal control conditions on the metabolic rate of fruits and vegetables. By inputting real-time environmental data and maturity level into the maturation rate analysis model, the maturation rate of fruits and vegetables can be dynamically obtained, reflecting the current physiological change trend of fruits and vegetables.

[0081] The ripening rate analysis model can employ a multi-input single-output neural network structure, using fruit and vegetable maturity level, average warehouse temperature, average humidity, oxygen concentration, carbon dioxide concentration, and ethylene concentration as input variables, and outputting the fruit and vegetable ripening rate r0 (in terms of maturity level values ​​per hour). When the average warehouse temperature exceeds the control parameter by 2℃, the corresponding correction coefficient k is extracted from the ripening rate influencing factor database. t=1.08, when the ethylene concentration exceeds the target value of 0.3 ppm, the correction factor k is extracted. C2H4 =1.12, then the final rate correction factor is k=k t ×k C2H4 =1.21.

[0082] Based on the ripening rate and the corrected arrival time, the predicted maturity value of fruits and vegetables when they arrive at their destination is calculated, and the adjustment parameters are analyzed based on the predicted maturity value.

[0083] By combining the ripening rate with the corrected arrival time to predict maturity, the ripeness status of fruits and vegetables at the end of transportation can be predicted in advance, providing a basis for decision-making in subsequent environmental adjustments.

[0084] If we define the maturity rate as r1 and the corrected arrival time as t1, then the predicted maturity value R p =R0 + r1 × t1, where R0 is the current maturity value; when R p When the ripeness level exceeds the upper limit of the maturity range, the system assumes that the fruits and vegetables will be overripe upon arrival and triggers a cold chain parameter adjustment strategy.

[0085] Among them, the adjustment parameters, based on the numerical analysis of predicted maturity, can be preferably: Determine whether the predicted maturity value is within the preset target maturity range, which is preset based on the market demand and shelf life requirements of the destination.

[0086] When the predicted maturity value exceeds the upper limit of the target maturity range, it is determined that the maturity rate needs to be reduced. The adjustment parameters that can reduce the maturity rate of the current fruit and vegetable variety are queried from the cold chain parameter database.

[0087] When the forecast results show that fruits and vegetables will reach full ripeness or overripeness before the end of transportation, the system needs to take control measures to inhibit metabolic activity in order to delay the ripening process. At this time, the parameter set for inhibiting the ripening rate can be extracted from the cold chain parameter database and sent to the environmental control system for adjustment.

[0088] For bananas and similar fruits and vegetables, when the predicted maturity value is higher than the target upper limit of 0.8, the system retrieves adjustment parameters from the cold chain parameter database that can reduce the ripening rate: the target temperature value is reduced by 2°C, the target humidity value is increased by 5%, the ethylene concentration is reduced to 0.1 ppm, and the oxygen concentration is increased to 21%. Based on this, the system controls the refrigeration module to cool down and activates the gas regulation module to inject fresh air to increase the oxygen concentration, thereby effectively slowing down respiration and the rate of ethylene accumulation.

[0089] When the predicted maturity value is lower than the lower limit of the target maturity range, it is determined that the maturity rate needs to be increased. The adjustment parameters that can increase the maturity rate of the current fruit and vegetable variety are queried from the cold chain parameter database.

[0090] When forecasts indicate that fruits and vegetables will arrive in an immature or semi-ripe state, the system should appropriately accelerate the ripening process to ensure they reach their optimal sales period upon arrival. At this point, ripening control parameter sets can be selected from the cold chain parameter database to achieve coordinated control of warehouse gases and temperature / humidity.

[0091] For example, when the predicted maturity value is 0.5 below the target lower limit, the system retrieves adjustment parameters from the cold chain parameter database that can improve the ripening rate: the target temperature value is increased by 3°C, the target humidity value remains unchanged, the ethylene concentration is increased to 0.4 ppm, and the carbon dioxide concentration is maintained at 0.3%. The system controls the refrigeration module to increase the warehouse temperature and simultaneously starts the ethylene release device to carry out low-concentration ripening treatment, so that the fruits and vegetables reach the appropriate ripeness when they arrive at their destination.

[0092] When the predicted maturity value is within the target maturity range, keep the current environmental control parameters in the cargo compartment of the cold chain transport vehicle unchanged.

[0093] When the prediction results indicate that fruits and vegetables can maintain an ideal state of maturity at the end of transportation under the current environmental control conditions, the system does not need to make any additional adjustments. It only needs to maintain the existing control parameters to reduce system energy consumption and environmental disturbances.

[0094] When the predicted maturity value is within the target maturity range [0.6, 0.8], the system maintains stable operation of the current temperature, humidity and gas concentration parameters, and only performs routine monitoring and minor compensation to ensure the stability of the fruits and vegetables and prevent energy waste caused by frequent switching of the control system.

[0095] Furthermore, step S5 can preferably be: The difference between the adjustment parameter and the control parameter is compared to obtain the deviation value. The adjustment priority is determined based on the deviation value, with temperature deviation having the highest priority, humidity deviation having the second highest priority, and gas concentration deviation having the lowest priority.

[0096] The purpose of prioritizing adjustments is to control the parameters that have the most significant impact on the ripening rate of fruits and vegetables when multiple environmental parameters deviate simultaneously, thereby ensuring the rational allocation of control resources. For example, when there is a significant deviation between the average temperature of the warehouse and the target temperature, temperature adjustment is performed first to avoid abrupt changes in the ripening rate caused by abnormal temperature. Then, secondary corrections are made based on deviations in humidity and gas concentration, thus achieving a hierarchical and dynamic coordination of the control process.

[0097] During transportation, if the average temperature of the cargo warehouse increases by 2°C, the humidity decreases by 5%, and the ethylene concentration increases by 3ppm, the system will first activate the cooling module to cool down the cargo. After the temperature returns to the target range, the humidification module will be activated to increase the humidity. Finally, gas regulation will be performed to control the ethylene concentration, ensuring that all environmental parameters return to the set range stably under the priority control sequence.

[0098] For temperature regulation, when the absolute value of the temperature deviation is greater than the preset temperature regulation threshold, the required cooling power or heating power is calculated. The cooling power or heating power is calculated based on the temperature deviation value, the volume of the warehouse and the heat capacity of the fruits and vegetables through the heat balance equation, and the cooling module or heating module is controlled to operate according to the cooling power or heating power.

[0099] By establishing a thermal balance model for temperature regulation, the control commands not only depend on the magnitude of the temperature deviation, but also dynamically adjust the power output based on the total heat capacity of the fruits and vegetables in the warehouse and the warehouse's insulation performance, thus avoiding over-cooling or over-heating and achieving optimal energy consumption.

[0100] If the warehouse volume is 12m³, the total weight of fruits and vegetables is 800kg, and the temperature deviation is +3℃, the system calculates the heat to be removed based on the heat balance formula Q=c·m·ΔT, and automatically allocates the cooling power based on the efficiency coefficient of the refrigeration system. Once the target temperature is reached, the system will maintain the lowest power operation to prevent the temperature from rising too quickly.

[0101] For humidity control, when the absolute value of the humidity deviation is greater than the preset humidity control threshold, the required humidification or dehumidification amount is calculated, and the humidification module or dehumidification module is controlled to operate according to the humidification or dehumidification amount.

[0102] The humidity control process monitors the difference between the average humidity and the target humidity in the warehouse, and calculates the required change in water vapor by combining the warehouse volume, air temperature and saturated vapor pressure curve, thereby determining the operating time and power of humidification or dehumidification to ensure the dynamic balance of water content on the surface of fruits and vegetables.

[0103] When the average humidity of the warehouse is detected to be 70% and the target humidity is 85%, the system calculates the amount of water vapor that needs to be added and controls the ultrasonic humidification module to work continuously for 300 seconds to make the humidity of the warehouse rise steadily to the set value; if the humidity exceeds 90%, the dehumidification mode is automatically switched and the condensation dehumidification unit is turned on to recover water vapor.

[0104] For gas concentration regulation, when the absolute value of the oxygen concentration deviation, carbon dioxide concentration deviation, or ethylene concentration deviation is greater than the corresponding gas regulation threshold, the required gas intake or exhaust volume is calculated, and the gas regulation module is controlled to open the corresponding gas valve for gas intake or exhaust operation, or to start the adsorption device or catalytic oxidation device for ethylene removal.

[0105] Gas concentration regulation is achieved by establishing a gas balance model and calculating the adjustment amount based on the warehouse volume, current gas concentration, and target gas concentration. This allows for precise control of the respirable gas environment, preventing fruits and vegetables from aging or losing water prematurely in a closed environment. In particular, the control of ethylene concentration can be achieved by reducing the ethylene gas content released by fruits and vegetables through adsorption or catalytic decomposition technologies, thus slowing down the physiological ripening process.

[0106] When the ethylene concentration in the warehouse exceeds the set threshold of 5 ppm, the system automatically starts the catalytic oxidation unit to decompose ethylene into carbon dioxide and water molecules, and reduces the ethylene concentration to below 1 ppm within 30 minutes; if the oxygen concentration is below 18%, the system automatically introduces fresh air to restore gas balance and ensure that the fruits and vegetables are in a stable breathing environment.

[0107] Example 2: like Figure 2 As shown, this application also provides a cold chain transportation management system 10 based on fruit and vegetable maturity, applied to the transportation of fruits and vegetables after classification by type. The cold chain transportation management system specifically includes: Image acquisition module 11 is used to acquire surface images of fruits and vegetables to be transported, perform maturity analysis on the surface images, and obtain the maturity level of the fruits and vegetables.

[0108] The data matching module 12 is used to match parameters from a preset cold chain parameter database based on the destination coordinates, fruit and vegetable types and maturity levels to obtain corresponding control parameters, and adjust the cargo warehouse environment of the cold chain transport vehicle through the control parameters.

[0109] The data acquisition module 13 is used to calculate the remaining transportation distance and collect environmental data inside the cargo compartment of the cold chain transport vehicle in real time during the transportation process.

[0110] The data analysis module 14 is used to calculate the arrival time based on the remaining transportation distance, analyze the ripening rate of fruits and vegetables based on environmental data, and analyze the adjustment parameters based on the arrival time and ripening rate.

[0111] The parameter adjustment module 15 is used to dynamically control the cargo warehouse environment of cold chain transport vehicles according to the adjustment parameters.

[0112] In this embodiment, the surface image of the fruits and vegetables to be transported is acquired by the image acquisition module 11. Combined with the RGB camera and multispectral camera set in the loading area, visible light images and spectral reflectance images within specific wavelength ranges are acquired. The acquired images are preprocessed, including noise reduction, illumination equalization, region of interest extraction, and normalization. Color feature parameters and spectral feature parameters are extracted from the normalized images. The color feature parameters include the mean color components of the RGB color space, the hue and saturation components of the HSV color space, and the chromaticity components of the LAB color space. The spectral feature parameters are obtained by calculating the reflectance ratio of the 650nm to 750nm wavelength band to the 450nm to 550nm wavelength band.

[0113] Color and spectral feature parameters are input into a pre-trained maturity classification model. This model employs a convolutional neural network structure and is trained through supervised learning on fruit and vegetable sample images at different maturity stages, outputting the maturity level of the fruits and vegetables. Subsequently, the data matching module 12 retrieves the control parameters with the highest matching degree from a preset cold chain parameter database based on the destination coordinates, fruit and vegetable types, and maturity level. The control parameters include target temperature, target humidity, target oxygen concentration, target carbon dioxide concentration, and target ethylene concentration. The vehicle environmental control system adjusts the cargo environment of the cold chain transport vehicle, including the coordinated control of the refrigeration module, heating module, humidification module, dehumidification module, and gas regulation module.

[0114] During transportation, the data acquisition module 13 collects real-time data on the vehicle's current location, remaining transportation distance, and temperature, humidity, and gas concentration within the warehouse. The data analysis module 14 calculates the estimated arrival time and, combined with environmental data and a pre-set database of ripening rate influencing factors, analyzes the fruit and vegetable ripening rate to predict the maturity level upon arrival at the destination, thereby generating adjustment parameters. The parameter adjustment module 15 dynamically controls the warehouse environment based on the deviation between the adjustment parameters and the current control parameters, prioritizing temperature > humidity > gas concentration. This achieves precise adjustment of temperature, humidity, and gas concentration, ensuring that the fruits and vegetables remain within the target ripeness range upon arrival at their destination.

[0115] The solution in this embodiment enables dynamic control of the entire fruit and vegetable transportation process. This not only improves the controllability of cold chain transportation and the predictability of the shelf life of fruits and vegetables, but also effectively reduces fruit and vegetable losses and quality decline caused by fluctuations in the transportation environment. It ensures the freshness and marketability of fruits and vegetables during transportation and provides customized transportation environment management solutions for different types and maturity stages of fruits and vegetables.

[0116] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0117] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0118] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program instructing the relevant hardware to implement them. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0119] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A cold chain transportation management method based on fruit and vegetable maturity, applied to the transportation of fruits and vegetables after classification by type, characterized in that, include: Acquire surface images of the fruits and vegetables to be transported, perform maturity analysis on the surface images, and obtain the maturity level of the fruits and vegetables; Based on the destination coordinates, fruit and vegetable types, and maturity level, parameters are matched from a preset cold chain parameter database to obtain corresponding control parameters, and the cargo warehouse environment of the cold chain transport vehicle is adjusted through the control parameters. During transportation, the remaining transportation distance is calculated in real time and environmental data inside the cargo compartment of the cold chain transport vehicle is collected. The arrival time is calculated based on the remaining transportation distance, the ripening rate of fruits and vegetables is analyzed based on the environmental data, and adjustment parameters are analyzed based on the arrival time and the ripening rate. The warehouse environment of cold chain transport vehicles is dynamically controlled according to the aforementioned adjustment parameters.

2. The cold chain transportation management method based on fruit and vegetable maturity according to claim 1, characterized in that, The steps of acquiring surface images of the fruits and vegetables to be transported, performing maturity analysis on the surface images, and obtaining the maturity level of the fruits and vegetables include: Visible light images of the fruit and vegetable surface are acquired by an RGB camera set in the loading area. The visible light images are preprocessed to obtain standardized fruit and vegetable surface images, and color feature parameters are extracted from the standardized fruit and vegetable surface images. A multispectral camera set in the loading area acquires spectral reflectance images of the fruit and vegetable surface within a specific spectral range. Band analysis is performed on the spectral reflectance images to extract the reflectance data of the preset first and second spectral bands on the fruit and vegetable surface. The ratio of the reflectance values ​​of the first and second spectral bands is calculated to obtain spectral characteristic parameters. The color feature parameters and the spectral feature parameters are input into a pre-trained maturity classification model to output the maturity level of fruits and vegetables.

3. The cold chain transportation management method based on fruit and vegetable maturity according to claim 1, characterized in that, The step of matching parameters from a preset cold chain parameter database based on destination coordinates, fruit and vegetable types, and maturity levels to obtain corresponding control parameters, and adjusting the cargo warehouse environment of the cold chain transport vehicle using these control parameters, includes: The current location coordinates and destination coordinates of the cold chain transport vehicle are obtained through the vehicle-mounted GPS positioning system. The actual transport distance between the two points is calculated, and the estimated transport time is calculated based on the actual transport distance and the average driving speed of the vehicle. The fruit and vegetable types, maturity levels, and estimated transportation time are input into a preset cold chain parameter database as query conditions. The database is then used to retrieve the record that best matches the query conditions, and the control parameters corresponding to the record with the best match are extracted. The control parameters are sent to the environmental control system of the cold chain transport vehicle to adjust the cargo environment of the cold chain transport vehicle.

4. The cold chain transportation management method based on fruit and vegetable maturity according to claim 1, characterized in that, The steps of calculating the remaining transportation distance and collecting environmental data inside the cargo hold of the cold chain transport vehicle in real time during transportation include: The vehicle-mounted GPS positioning system collects the real-time location coordinates of the cold chain transport vehicle at preset first time intervals, and calculates the remaining transport distance based on the real-time location coordinates and the destination coordinates. Temperature data from each monitoring point in the warehouse is collected by multiple temperature sensors placed at different locations in the warehouse at preset second time intervals, and the average value of the temperature data is calculated as the average temperature of the warehouse. Humidity data from each monitoring point in the warehouse is collected at second time intervals by multiple humidity sensors installed at different locations in the warehouse, and the average value of the humidity data is calculated as the average humidity of the warehouse. The oxygen concentration, carbon dioxide concentration, and ethylene concentration in the cargo warehouse are collected every second time interval by a gas sensor array installed in the cargo warehouse. The average temperature of the warehouse, the average humidity of the warehouse, the oxygen concentration, the carbon dioxide concentration, and the ethylene concentration are used as environmental data.

5. The cold chain transportation management method based on fruit and vegetable maturity according to claim 1, characterized in that, The steps of calculating the arrival time based on the remaining transportation distance, analyzing the ripening rate of fruits and vegetables based on the environmental data, and analyzing the adjustment parameters based on the arrival time and the ripening rate include: The arrival time is calculated based on the remaining transportation distance and the real-time driving speed of the vehicle. When the fluctuation of the real-time driving speed exceeds a preset threshold, the arrival time is corrected based on the average speed data of historical road segments to obtain the corrected arrival time. Based on the environmental data, the corresponding rate correction coefficient is queried from the preset maturity rate impact factor database. The maturity level and the environmental data are then input into the preset maturity rate analysis model to obtain the maturity rate. Based on the ripening rate and the corrected arrival time, the predicted maturity value of the fruits and vegetables when they arrive at their destination is calculated, and the adjustment parameters are analyzed based on the predicted maturity value.

6. The cold chain transportation management method based on fruit and vegetable maturity according to claim 5, characterized in that, The step of analyzing the adjustment parameters based on the predicted maturity value includes: Determine whether the predicted maturity value is within the preset target maturity range. When the predicted maturity value exceeds the upper limit of the target maturity range, query the cold chain parameter database for adjustment parameters that can reduce the maturity rate of the current fruit and vegetable variety. When the predicted maturity value is lower than the lower limit of the target maturity range, the adjustment parameters that can improve the maturity rate of the current fruit and vegetable variety are queried from the cold chain parameter database. When the predicted maturity value is within the target maturity range, the current environmental control parameters in the cargo compartment of the cold chain transport vehicle remain unchanged.

7. The cold chain transportation management method based on fruit and vegetable maturity according to claim 1, characterized in that, The step of dynamically controlling the cargo warehouse environment of the cold chain transport vehicle according to the adjustment parameters includes: The difference between the adjustment parameter and the control parameter is compared to obtain the deviation value, and the adjustment priority is determined based on the deviation value. For temperature regulation, when the absolute value of the temperature deviation is greater than the preset temperature regulation threshold, the required cooling power or heating power is calculated, and the cooling module or heating module is controlled to operate according to the cooling power or heating power. For humidity control, when the absolute value of the humidity deviation is greater than the preset humidity control threshold, the required humidification or dehumidification amount is calculated, and the humidification module or dehumidification module is controlled to operate according to the humidification or dehumidification amount. For gas concentration regulation, when the absolute value of the oxygen concentration deviation, carbon dioxide concentration deviation, or ethylene concentration deviation is greater than the corresponding gas regulation threshold, the required gas intake or exhaust volume is calculated, and the gas regulation module is controlled to open the corresponding gas valve for gas intake or exhaust operation, or to start the adsorption device or catalytic oxidation device for ethylene removal.

8. A cold chain transportation management system based on fruit and vegetable maturity, applied to the transportation of fruits and vegetables after classification by type, characterized in that, include: The image acquisition module is used to acquire surface images of the fruits and vegetables to be transported, perform maturity analysis on the surface images, and obtain the maturity level of the fruits and vegetables. The data matching module is used to match parameters from a preset cold chain parameter database based on the destination coordinates, fruit and vegetable types, and maturity level to obtain corresponding control parameters, and adjust the cargo warehouse environment of the cold chain transport vehicle through the control parameters. The data acquisition module is used to calculate the remaining transportation distance and collect environmental data inside the cargo compartment of cold chain transport vehicles in real time during transportation. The data analysis module is used to calculate the arrival time based on the remaining transportation distance, analyze the ripening rate of fruits and vegetables based on the environmental data, and analyze adjustment parameters based on the arrival time and the ripening rate. The parameter adjustment module is used to dynamically control the cargo warehouse environment of the cold chain transport vehicle according to the adjustment parameters.

Images