Cold-chain logistics temperature intelligent control method and system

Abstract

The invention provides a cold-chain logistics temperature intelligent control method and system, and relates to the technical field of temperature intelligent control. The method comprises the following steps: determining a corresponding target cold chain temperature and a breathing heat safety threshold value (the heat produced by the goods itself reaches a critical point of a danger degree) from a preset temperature control mapping table according to goods name information of a target goods; before goods enter the compartment, the refrigerating device is controlled in advance to adjust the compartment temperature to the target cold chain temperature and maintain the compartment temperature at low power. After goods are loaded, a point cloud acquisition device is used for acquiring a placement image, a goods stack center area with concentrated breathing heat is determined, and then an infrared thermal imager is controlled to directionally monitor the real-time temperature of the area. And if the temperature of any area exceeds the threshold value, the refrigeration device is controlled to supply air directionally, so that the temperature of the area is reduced to the target cold chain temperature. By implementing the method, frostbite or deterioration caused by abnormal local temperature of the goods can be effectively avoided, and the accuracy and the intelligent degree of temperature control in the cold chain transportation process are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent temperature control technology, and in particular to an intelligent temperature control method and system for cold chain logistics. Background Technology

[0002] In modern cold chain logistics and warehousing, precise temperature monitoring and control are crucial for ensuring the quality of goods. This is especially true for fresh produce such as fruits, vegetables, and flowers, which continuously generate respiration heat during storage and transportation. This heat release directly affects the ambient temperature around the goods. Therefore, efficient temperature monitoring technology has become a key support for the industry's development, ensuring cargo safety.

[0003] Currently, widely used temperature monitoring technologies are mainly based on fixed threshold judgment mechanisms. Sensors collect real-time temperature data of the storage environment for goods, and when the monitored temperature exceeds a preset threshold, the system automatically triggers refrigeration equipment to maintain the required temperature conditions for goods storage. This monitoring method based on a single temperature threshold is widely used in the cold chain logistics industry due to its simplicity and ease of implementation.

[0004] However, this existing technology has significant drawbacks. Especially in long-distance cold chain logistics transportation, some goods have a high rate of heat release through respiration, which can cause the local ambient temperature to rise, leading sensors to misjudge that the ambient temperature is too high. Once the refrigeration equipment is triggered to cool down, the temperature around the goods may drop below their suitable storage temperature, ultimately causing the goods to freeze. If left untreated, the temperature of the goods will exceed the standard, leading to spoilage. This not only causes economic losses but also seriously affects the quality of the goods and the stability of the supply chain. Summary of the Invention

[0005] This application provides a method and system for intelligent temperature control in cold chain logistics, which is used to solve the problem of local heat accumulation caused by dynamic changes in the stacking of goods in existing cold chain logistics, and to achieve differentiated and precise temperature control of goods.

[0006] In a first aspect, this application provides an intelligent temperature control method for cold chain logistics. The method includes: acquiring the name information of the target goods to be transported, and determining the target cold chain temperature and respiratory heat safety threshold corresponding to the target goods to be transported according to a preset temperature control mapping table. The respiratory heat safety threshold refers to the temperature critical point at which the goods themselves generate heat to a dangerous level. Within a set time before the target goods to be transported enter the compartment, controlling the refrigeration device to adjust the temperature inside the compartment to the target cold chain temperature and maintaining low-power operation. After the target goods to be transported are loaded into the compartment, acquiring a point cloud image of the goods placement through a point cloud acquisition device, and determining multiple cargo stacking core areas based on the cargo placement point cloud image. The cargo stacking core area is the central area where respiratory heat is concentrated due to the accumulation of goods. Controlling multiple infrared thermal imagers in the compartment to face each cargo stacking core area respectively, and monitoring the real-time temperature data of each cargo stacking core area. If the real-time temperature data of any cargo stacking core area exceeds the respiratory heat safety threshold, controlling the refrigeration device to directionally blow air into the cargo stacking core area to reduce the temperature of the cargo stacking core area to the target cold chain temperature.

[0007] By adopting the above technical solution, the target cold chain temperature and breathing heat safety threshold are first matched according to the cargo name to achieve targeted temperature control. Before loading, the cargo is pre-cooled to the target temperature and operated at low power to avoid temperature fluctuations during loading. After loading, the core area—where breathing heat tends to accumulate—is accurately identified, and these key areas are then monitored directionally using an infrared thermal imager. When the core temperature exceeds the threshold, the cooling unit delivers air directionally instead of cooling the entire reactor. This prevents non-core areas from freezing due to excessive cooling and quickly reduces the high temperature of the core, solving the problem of localized overheating or overcooling in traditional overall temperature control, achieving precise temperature control, and ensuring stable cargo quality.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of controlling the refrigeration device to adjust the temperature inside the compartment to the target cold chain temperature, the method further includes: acquiring multiple temperature data at set intervals using multiple candidate temperature sensors arranged inside the compartment; when each of the temperature data is within a preset safe range for the cold chain temperature of the target goods to be transported, increasing the set interval by a set delay period; repeating the above steps until the set interval reaches a preset maximum interval.

[0009] By adopting the above technical solution, the sampling frequency is reduced when the temperature is stable, thereby lowering sensor energy consumption and data processing pressure; while a high sampling density is maintained when the temperature fluctuates, ensuring that anomalies can be detected in a timely manner. By dynamically adjusting the sampling interval, a balance between energy consumption and monitoring efficiency is achieved while ensuring the accuracy of temperature monitoring.

[0010] In some embodiments of the first aspect, the acquisition of cargo placement point cloud images by a point cloud acquisition device and the determination of multiple cargo stacking core regions based on the cargo placement point cloud images include: acquiring multi-angle image data of cargo inside the carriage by a point cloud acquisition device; constructing a three-dimensional point cloud network of cargo stacking based on the multi-angle image data; performing meshing processing on the three-dimensional point cloud network and dividing the three-dimensional point cloud network into multiple virtual units according to a set mesh space size; determining multiple stacking packages in the three-dimensional point cloud network according to a stacking morphology determination model, which is constructed in advance by deep learning based on multiple stacking three-dimensional point cloud network sets with different stacked goods; calculating the number of virtual units contained in each stacking package to obtain the virtual breathing heat intensity value of each stacking package; and selecting multiple stacking packages, the same number as the number of infrared thermal imagers, according to the virtual breathing heat intensity values ​​from large to small to determine the cargo stacking core regions.

[0011] By employing the above technical solution, multi-angle image data is acquired to construct a 3D point cloud network, which can comprehensively reconstruct the cargo stacking morphology. Mesh processing divides it into virtual units for easier quantitative analysis. A model based on the stacking morphology constructed using deep learning is used to identify stacked packages. The respiratory heat intensity value is calculated by combining the number of virtual units, scientifically quantifying the heat generation risk in each area. The cargo stack core area is selected based on the intensity value, matching the number of infrared thermal imagers, achieving optimal allocation of monitoring resources and ensuring accurate monitoring of key areas. Selecting stacked packages with the same number of infrared thermal imagers facilitates efficient one-to-one operation for each imager.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of controlling multiple infrared thermal imagers in the control compartment to face each of the cargo stack core areas and monitor the real-time temperature data of each cargo stack core area, the method further includes: at set core correction times, acquiring temperature data of other stacked bags through infrared thermal imagers; if the temperature data of any other stacked bag exceeds the breathing heat safety threshold, controlling the refrigeration device to directionally blow air onto the corresponding other stacked bag to reduce the temperature of the other stacked bag to the target cold chain temperature, wherein the other stacked bags are stacked bags other than the cargo stack core areas.

[0013] By adopting the above technical solutions, the full-coverage monitoring strategy overcomes the limitations of focusing only on the fixed core area, forming a dynamic replenishment mechanism to ensure that the goods in the entire compartment are in a safe temperature environment, reducing the risk of goods deteriorating due to local temperature runaway.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of controlling the refrigeration device to directionally supply air to the corresponding other stacked packages if the real-time temperature data of any of the cargo core areas exceeds the breathing heat safety threshold, the method further includes: obtaining a first number of directional air supply to each other stacked package and a second number of directional air supply to each cargo core area within a set calibration time; if the first number exceeds the second number, redetermining the cargo core area according to the number of directional air supply in descending order; repeating the above steps to dynamically update the cargo core area.

[0015] By employing the above technical solution and comparing the directional air supply frequency of each stack, the frequency and severity of temperature anomalies in different areas can be reflected. When the air supply frequency of other stacks exceeds that of the reactor core area, it indicates that their heat generation risk is higher than that of the original reactor core area. At this point, the reactor core area is redefined, allowing monitoring resources to be shifted to the new high-risk area. By dynamically updating the reactor core area, the focus is continuously placed on the area with the most frequent temperature fluctuations and the highest risk, achieving adaptive optimization of monitoring resources and improving the overall temperature control effect and efficiency.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: after the directional air supply operation is completed, controlling the refrigeration device to return to a low-power operation state to wait for the next directional air supply.

[0017] By adopting the above technical solutions and the strategy of switching operating modes as needed, the system energy consumption is effectively reduced and the service life of refrigeration equipment is extended while ensuring the quality of goods, achieving a win-win situation in both temperature control and economic benefits.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of controlling the refrigeration device to directionally supply air to the cargo core area if the real-time temperature data of any cargo core area exceeds the breathing heat safety threshold, the method further includes: when it is determined by the vibration sensor that the cold chain logistics vehicle has encountered bumps, identifying the cargo status by the point cloud acquisition device; if it is detected that the target cargo has shifted and caused damage to the cargo core area corresponding to the target cargo, then after the vibration sensor determines that the cold chain logistics vehicle has finished bumping, recalculating the number of directional air supply times for the cargo core area within the calibration time, and redetermining the cargo core area according to the number of directional air supply times from large to small.

[0019] By adopting the above technical solution, invalid calculations are avoided when the cargo is in an unstable state, ensuring that the redefined core area matches the actual cargo distribution, improving the accuracy of core area identification, enabling the temperature control system to quickly adapt to dynamic changes during transportation, and ensuring the quality and safety of cargo in complex transportation environments.

[0020] In a second aspect, this application provides a temperature intelligent control system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the temperature intelligent control system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, this application provides a computer-readable storage medium including instructions that, when executed on a temperature intelligent control system, cause the temperature intelligent control system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer program product that, when run on a temperature intelligent control system, causes the temperature intelligent control system to perform the method described in the first aspect and any possible implementation thereof.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0024] 1. By employing technical means such as matching the target cold chain temperature and respiratory heat safety threshold based on cargo name information, pre-cooling the car compartment and maintaining it at low power, identifying the cargo core area for directional monitoring and directional air supply when the threshold is exceeded, the technology effectively solves the technical problems of local overheating misjudgment, excessive cooling causing cargo freezing damage, or insufficient cooling causing deterioration caused by the existing technology based on single threshold monitoring. Thus, it achieves the technical effects of accurately matching cargo characteristics, avoiding local temperature runaway, ensuring cargo quality, and being energy-efficient.

[0025] 2. By employing multi-angle image construction of a 3D point cloud network, combining deep learning models to identify stacked packages, and quantifying the respiratory heat intensity value through the number of virtual units to determine the core area of ​​the cargo stack, the technology effectively solves the technical problems of difficulty in accurately identifying concentrated respiratory heat areas of cargo and the failure to detect key areas due to unreasonable allocation of monitoring resources in existing technologies. This achieves the technical effects of accurately locating high-risk core areas, optimizing the allocation of monitoring resources, and improving the targeting and reliability of temperature control.

[0026] 3. By employing the technical means of statistically analyzing the number of directional air supply cycles for each stacked package and re-determining the core area when the number of air supply cycles for other stacked packages exceeds the original core area, the technical problems of fixed core areas and inability to adapt to dynamic changes in cargo stacking status and heat generation in existing technologies are effectively solved. This achieves the technical effects of dynamically adapting the core area to actual risks, ensuring that monitoring focuses on high-risk areas, and improving the adaptability and effectiveness of the overall temperature control system. Attached Figure Description

[0027] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0028] Figure 1 This is a schematic diagram of a system framework for a cold chain logistics temperature intelligent control method in the embodiments of this application.

[0029] Figure 2 This is a flowchart illustrating a method for intelligent temperature control in cold chain logistics as described in this application.

[0030] Figure 3 This is a schematic diagram of the physical device structure of a temperature intelligent control system in the embodiments of this application. Detailed Implementation

[0031] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to and includes any or all possible combinations of one or more of the listed items.

[0032] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0033] For ease of understanding, the structural framework used in the method provided in this embodiment is described below. Please refer to [link / reference]. Figure 1 This is a schematic diagram of a system framework for an intelligent temperature control method for cold chain logistics in this application embodiment.

[0034] exist Figure 1In the cargo compartment, the core space for storage and transportation is equipped with infrared thermal imagers, point cloud acquisition devices, and refrigeration units, and intelligent temperature control is achieved through a server. The cargo core area, a critical location prone to concentrated respiratory heat due to cargo stacking, is the system's primary monitoring target. The point cloud acquisition device collects point cloud images of the cargo arrangement, constructs a 3D point cloud network using multi-angle point cloud data, and performs meshing processing to accurately identify the cargo core area. This image information is then sent to the server of the intelligent temperature control system, providing a foundation for subsequent analysis. The infrared thermal imager collects real-time temperature data from the cargo core area and other stacked packages, transmitting this information to the server, allowing the server to monitor the dynamic temperature of the cargo. As the system's "brain," the server receives point cloud images of cargo placement and real-time temperature data. Based on preset logic, it determines whether the real-time temperature in the core area of ​​the cargo stack exceeds the respiratory heat safety threshold. If so, it sends a cooling command to the refrigeration unit, controlling it to direct airflow to that area to lower the temperature to the target cold chain temperature. Simultaneously, the server also undertakes the task of dynamically updating the core area of ​​the cargo stack. By statistically analyzing the number of times airflow is directed to each area within the calibration period and considering factors such as cargo movement and displacement, the server re-determines the core area. This ensures that temperature control accurately adapts to changes in cargo status, effectively manages temperature risks caused by respiratory heat and other factors during cold chain transportation, maintains stable cargo quality, and contributes to the efficient and intelligent operation of cold chain logistics.

[0035] In long-distance cold chain logistics transportation, some goods (such as ripe fruits and fresh meat) continuously release heat through respiration. If they are densely packed and poorly ventilated, this respiration heat can accumulate rapidly in localized areas, causing the temperature in the core area to spike. However, temperature sensors inside the truck are limited by their installation location and monitoring range, and can only obtain the temperature of a localized point. This can easily lead to misinterpretation of localized high temperatures as overall environmental conditions exceeding limits. When refrigeration equipment receives a signal, it cools the entire truck space indiscriminately, failing to target specific areas precisely. For example, when transporting strawberries, if the core of the stack reaches 30°C due to respiration heat, the sensors may misinterpret the temperature. After refrigeration is activated, the area around the strawberries, which was originally at a suitable temperature of 2°C, may suddenly drop to 0°C, causing frostbite. If left untreated, the core temperature will continue to rise, causing the strawberries to spoil and rot. Either scenario results in cargo damage, economic losses, disruption of the supply chain, and impacts upstream and downstream collaboration and the delivery of high-quality goods. This application provides a method that can accurately solve this problem. The process of the method provided in this implementation is described below. Please refer to... Figure 2 This is a flowchart illustrating a method for intelligent temperature control in cold chain logistics as described in this application.

[0036] S201. Obtain the name information of the target cargo to be transported, and determine the target cold chain temperature and respiratory heat safety threshold corresponding to the target cargo to be transported according to the preset temperature control mapping table. The respiratory heat safety threshold refers to the temperature critical point at which the cargo itself generates heat to a dangerous level. The target goods to be transported refer to commodities that require transportation via cold chain logistics, primarily plant-based goods that generate respiration heat in this application. Goods name information refers to the names or codes used to identify and distinguish different goods. The temperature control mapping table is a pre-built database table used to store the mapping relationship between different goods names and their corresponding target cold chain temperatures and respiration heat safety thresholds. The target cold chain temperature represents the optimal temperature range that needs to be maintained during transportation to ensure the quality of the goods; for example, the target cold chain temperature for cut flowers is typically 2-8℃. The respiration heat safety threshold refers to the critical temperature point at which the heat generated by the goods' own metabolism may lead to quality deterioration or safety risks; for example, the respiration heat safety threshold for some fruits is 15℃, exceeding which may accelerate spoilage.

[0037] In the cold chain logistics process, upon receiving a transportation order, the server in the intelligent temperature control system first extracts the name of the target goods to be transported from the order information. This process can be achieved through manual input, barcode scanning, RFID identification, etc. For example, when logistics personnel use a handheld terminal to scan the barcode on the goods packaging, the system automatically obtains the name information and transmits it to the intelligent temperature control system. Next, the system performs a matching query in a preset temperature control mapping table based on the obtained name information. The temperature control mapping table is usually stored in a relational database, and its structure may include fields such as name, target cold chain temperature range, respiratory heat safety threshold, and humidity requirements. The system traverses the records in the mapping table, finds the record that perfectly matches the current name, and extracts the corresponding target cold chain temperature and respiratory heat safety threshold. In some cases, the name may have aliases or synonyms; in this case, the system will perform intelligent matching, for example, treating "rose" and "cut rose" as the same type of goods.

[0038] In some embodiments, the acquisition of the name information of the target goods to be transported and the determination of corresponding parameters can be achieved in multiple ways: Optionally, the system can integrate a barcode scanning module. When the goods enter the warehouse, the operator uses a barcode scanner to scan the barcode on the goods packaging. The system automatically parses the name information in the barcode and compares it with the temperature control mapping table to obtain the target cold chain temperature and respiratory heat safety threshold. Optionally, the system can interface with the enterprise's ERP system. When a transportation order is generated, the ERP system will synchronize the name information to the temperature intelligent control system. The system can directly obtain the name information from the interface and perform parameter queries.

[0039] It should be added that the temperature control mapping table needs to be updated regularly to accommodate the arrival of new goods and adjustments to temperature parameters. Simultaneously, the system should have an exception handling mechanism; when a matching goods name cannot be found in the mapping table, the system should prompt the operator for manual confirmation and allow temporary addition or modification of mapping table records.

[0040] S202. Within a set time before the target goods to be transported enter the carriage, control the refrigeration device to adjust the temperature inside the carriage to the target cold chain temperature and maintain low power operation. The set time refers to the duration for which the refrigeration unit needs to be turned on before loading the goods to ensure that the temperature inside the compartment reaches and stabilizes within the target cold chain temperature range. This duration is usually determined based on factors such as the volume of the compartment, the ambient temperature, and the power of the refrigeration unit. The refrigeration unit refers to the equipment installed in a preset position inside the compartment of a cold chain transport vehicle to regulate the temperature inside the compartment.

[0041] Once the intelligent temperature control system determines the target cold chain temperature for the goods to be transported, it calculates the set time when the refrigeration unit needs to be turned on in advance, based on the current ambient temperature, the insulation performance of the cargo compartment, and the specifications of the refrigeration unit. For example, in high-temperature summer conditions, for a 20-cubic-meter insulated cargo compartment, the system might calculate that the refrigeration unit needs to be turned on 2 hours in advance. Before the set time arrives, the system sends a start command to the refrigeration unit, which then begins operating at maximum power to rapidly reduce the temperature inside the cargo compartment. During the cooling process, the system monitors temperature changes inside the cargo compartment in real time, acquiring temperature data through temperature sensors located at different positions within the compartment. When the temperature inside the cargo compartment approaches the target cold chain temperature range, the system gradually reduces the power of the refrigeration unit, putting it into a low-power operation state. In low-power operation, the refrigeration unit fine-tunes itself based on minor temperature fluctuations inside the cargo compartment, ensuring that the temperature remains within the target cold chain temperature range. For example, when the temperature inside the cargo compartment rises by 0.5°C, the refrigeration unit will initiate a short cooling cycle to bring the temperature back to the target range. During the loading process, frequent opening of the truck doors allows hot outside air to enter the compartment, causing the temperature to rise. At this time, the refrigeration unit automatically increases its power to quickly restore the temperature inside the compartment.

[0042] In some embodiments, the refrigeration unit can be controlled to adjust the temperature inside the vehicle compartment to the target cold chain temperature in various ways. Optionally, the system can employ a PID control algorithm to dynamically adjust the power of the refrigeration unit based on the difference between the current temperature inside the compartment and the target cold chain temperature. The specific steps are as follows: First, the system obtains the current temperature inside the compartment using a temperature sensor pre-installed inside the compartment; then, it calculates the difference between the current temperature and the target cold chain temperature; next, it calculates the control signal to be output based on the PID algorithm; finally, it sends the control signal to the refrigeration unit to adjust its power.

[0043] In some embodiments, after this step, the system enters the dynamic temperature monitoring phase. At this time, candidate temperature sensors distributed in different locations within the carriage begin synchronously collecting temperature data at set intervals (initially 10 seconds). These sensors employ a distributed network architecture to transmit data to the server in real time. The system first preprocesses the collected temperature data to obtain valid temperature data, and then compares each valid temperature data with a preset cold chain temperature safety range. If all temperature data are within the safety range, it indicates that the current temperature control is stable. At this point, the system gradually increases the set interval by a set delay (e.g., 5 seconds) to reduce unnecessary data collection frequency and lower system energy consumption. For example, after the first detection of stable temperature, the collection interval is extended from 10 seconds to 15 seconds. After each extension, the system continuously monitors for multiple cycles (e.g., 3 cycles) to ensure temperature stability. If no temperature anomaly is detected after extending the interval, the system continues to extend the interval until the preset maximum interval (e.g., 60 seconds) is reached. This adaptive adjustment mechanism allows the system to reduce resource consumption during temperature stabilization while maintaining necessary monitoring sensitivity.

[0044] It should be added that when the system detects any temperature data exceeding the safe range, it will immediately trigger an emergency response mechanism: shorten the data collection interval to the preset minimum value, and adjust the output power and airflow direction of the cooling device according to the degree and location of the temperature anomaly.

[0045] S203. After the target cargo to be transported is loaded into the carriage, a point cloud image of the cargo placement is obtained through a point cloud acquisition device, and multiple cargo stacking core areas are determined based on the cargo placement point cloud image. The cargo stacking core area is the central area where the respiratory heat is concentrated due to the accumulation of cargo. The point cloud acquisition device refers to multiple depth sensors installed in the cold chain compartment, including but not limited to millimeter-wave radar, lidar or structured light cameras, used to acquire three-dimensional spatial coordinate data of the cargo surface in a dark environment.

[0046] Once the cargo is loaded and the truck doors are closed, or once staff confirm the loading is complete according to relevant procedures, the intelligent temperature control system triggers a point cloud acquisition process. Multiple point cloud acquisition devices (such as millimeter-wave radar arrays) distributed at preset locations on the truck's roof and walls simultaneously activate, scanning the cargo from different angles. These sensors utilize high-frequency millimeter-wave technology, offering millimeter-level distance resolution and all-weather operation, capable of accurately acquiring three-dimensional information about the cargo surface even in dark environments. The system first preprocesses the raw point cloud data, including removing outliers, compensating for point cloud shifts caused by vehicle vibration, and fusing multi-sensor data through time synchronization and spatial registration. The preprocessed point cloud data is then transformed into a unified truck coordinate system, forming a complete three-dimensional point cloud network.

[0047] Next, the system performs meshing on the 3D point cloud network. Based on the dimensions of the cargo compartment and the characteristics of the goods, an appropriate mesh size is set, dividing the entire 3D space into regularly arranged virtual units. The number of points within each virtual unit is counted as the density value of that unit; units with higher density typically indicate areas with denser cargo stacking. To further analyze the cargo stacking pattern, the system calls a pre-trained stacking pattern determination model. This model, trained on a point cloud dataset containing tens of thousands of different cargo stacking scenarios, can identify natural clusters in the point cloud data. The model first extracts the local geometric features (such as curvature and normal vectors) and global context information of each virtual unit, and then uses a multilayer perceptron for classification, grouping virtual units with similar features into the same stacking package. Training the stacking pattern determination model requires collecting a large amount of 3D point cloud network data of different cargo stacks, labeling this data to mark the boundaries and features of each stacking package, and then using a deep learning algorithm to train the labeled data to obtain a model capable of automatically identifying stacking packages.

[0048] The number of virtual units contained in each stack is then calculated to obtain the virtual breathing heat intensity value of each stack. Here, a stack represents a set of point clouds with similar stacking characteristics in a 3D point cloud network, and is a candidate region for the cargo stack core area. A virtual unit refers to a small cubic space formed by dividing the 3D point cloud network according to a set grid space size during the meshing process. The virtual breathing heat intensity value represents the potential intensity of breathing heat generated by the cargo within the stack; it is a relative value. The virtual breathing heat intensity value of each stack is obtained by combining the number of virtual units with a preset breathing heat mapping table. Finally, stacks with the same number of infrared thermal imagers as the number of virtual breathing heat intensity values ​​are selected from largest to smallest to determine the cargo stack core area. This is because the number of infrared thermal imagers is limited, making it impossible to monitor all stacks in real time; therefore, areas with higher breathing heat intensity values ​​are selected as key monitoring targets.

[0049] S204. Control multiple infrared thermal imagers inside the control compartment to point towards the core area of ​​each cargo stack and monitor the real-time temperature data of each cargo core area; Infrared thermal imagers are devices that use infrared thermal imaging technology to measure the surface temperature of objects in a non-contact manner. Real-time temperature data refers to the temperature values ​​of the core area of ​​the cargo stack that are collected in real time by infrared thermal imagers. These data are presented in the form of numbers or images, reflecting the temperature changes in the core area of ​​the cargo stack.

[0050] Once the intelligent temperature control system determines the location of the cargo stack's core area, it calculates the required angle and direction for the infrared thermal imagers based on the coordinates of each core area. Then, the system sends control commands to multiple infrared thermal imagers installed within the cargo compartment, driving their pan-tilt units to rotate and ensure their lenses are accurately aimed at the corresponding cargo stack's core area. During the adjustment process, the system monitors the position and orientation of the infrared thermal imagers in real time to ensure accurate alignment with the target area. Once the infrared thermal imagers are in position, they begin continuous monitoring of the cargo stack's core area. The infrared thermal imagers acquire thermal images of the core area at regular intervals (e.g., every 10 seconds) and transmit the thermal image data to the intelligent temperature control system. The system then analyzes the thermal images to extract the temperature information of the cargo stack's core area.

[0051] In some embodiments, the infrared thermal imager can be controlled to face the cargo stack core area and monitor real-time temperature data in various ways: Optionally, the system can use a closed-loop control algorithm to achieve precise alignment. The specific steps are as follows: First, based on the coordinates of the cargo stack core area, the theoretical angle that the infrared thermal imager needs to be adjusted is calculated; then, the pan-tilt unit is driven to rotate to the theoretical angle position; next, a thermal image is acquired from the current viewing angle, and the image is analyzed to see if the target cargo stack core area is included; if it is not included or is not fully included, the angle that needs further adjustment is calculated based on the deviation, and the above steps are repeated until accurate alignment is achieved.

[0052] In some embodiments, after the intelligent temperature control system enters a stable operating phase, in addition to continuously monitoring the real-time temperature of the cargo core area, a periodic core correction mechanism is also activated. This mechanism is triggered by a preset core correction time, for example, the system is set to execute it every 30 minutes. Each time the correction time arrives, the system sends a control command to the infrared thermal imager, adjusting its monitoring angle from its original fixed orientation towards the core area to scanning other stacked bags within the cargo compartment. The infrared thermal imager then sequentially collects temperature data for each other stacked bag according to a preset scanning path (typically covering all stacked bags outside the core area within the cargo compartment) and generates a corresponding temperature thermal map.

[0053] The system analyzes the temperature data collected from other stacked bags, comparing each data point with the respiratory heat safety threshold. If the temperature data of one other stacked bag exceeds the threshold, it indicates that the area has experienced temperature anomalies due to respiratory heat accumulation or changes in heat dissipation conditions. At this point, the system immediately initiates a directional airflow procedure: first, it determines the spatial coordinates of the other stacked bag and calculates the angle and required airflow speed of the cooling unit's air outlet; then, it controls the louvers of the air outlet to rotate to the corresponding angle, while simultaneously adjusting the fan power to match the cooling demand, ensuring that the cold air can be accurately delivered to the area. During the directional airflow process, the system tracks the temperature changes in the area in real time using an infrared thermal imager until it drops to within the target cold chain temperature range, after which the air outlet returns to its normal state.

[0054] The core function of this periodic review mechanism is to avoid "blind spots"—even stacked packages that were not initially selected as the core area may experience temperature anomalies due to changes in cargo condition (such as increased respiration heat or changes in stacking shape) or external environmental influences (such as decreased local insulation performance of the wagon). Through regular scanning and timely intervention, the system can achieve comprehensive temperature control coverage of all cargo stacking areas within the wagon, further reducing the risk of cargo spoilage.

[0055] S205. If the real-time temperature data of any cargo core area exceeds the breathing heat safety threshold, the refrigeration unit is controlled to directionally blow air into the cargo core area so that the temperature of the cargo core area is reduced to the target cold chain temperature.

[0056] Directional air delivery refers to the refrigeration unit adjusting the direction and speed of the air outlet to directly deliver cold air to the designated core area of ​​the cargo stack in order to achieve rapid cooling.

[0057] When the intelligent temperature control system detects that the real-time temperature data of a certain cargo core area exceeds the breathing heat safety threshold, it immediately triggers the directional airflow control process. First, the system calculates the angle and direction that the refrigeration unit's air outlet needs to be adjusted based on the location coordinates of the cargo core area. Then, the system sends control commands to the refrigeration unit to adjust the louver angle of the air outlet and the fan speed, directing the cold air towards the cargo core area. During directional airflow, the system monitors the temperature changes in the cargo core area in real time. If the temperature drops slowly, the system appropriately increases the fan speed and cooling power to improve the cooling effect. Conversely, if the temperature drops too quickly, the system reduces the fan speed and cooling power to prevent damage to the cargo from excessively low temperatures. When the temperature in the cargo core area drops to the target cold chain temperature range, the system controls the refrigeration unit to gradually return to low-power operation while continuing to monitor the temperature in that area to ensure temperature stability.

[0058] In some embodiments, the refrigeration unit can be controlled to deliver directional airflow to the core area of ​​the cargo stack in various ways: Optionally, the system can employ distributed air outlet technology to achieve directional airflow. The specific steps are as follows: First, relevant personnel can pre-install multiple independently controllable air outlets at different locations within the cargo compartment; then, based on the location of the core area of ​​the cargo stack, determine which air outlet is closest to the core area and needs to be opened; next, by adjusting the louver angle and wind speed of each air outlet, the cold air is directed towards the target area; finally, based on temperature feedback data, the parameters of each air outlet are dynamically adjusted to achieve the optimal cooling effect.

[0059] In this embodiment, by combining precise temperature control parameters with cargo and achieving differentiated temperature management through positioning and directional control of the core area, it is possible to accurately identify localized high temperatures caused by the accumulation of respiratory heat in the core area of ​​the cargo, rather than overall ambient temperature anomalies. Thus, when cooling is triggered, air is directed only to the overheated area, avoiding excessive cooling of other areas. This effectively solves the problems of cargo freezing or deterioration caused by misjudgment of local respiratory heat in traditional fixed threshold monitoring, as well as the problems of excessive energy consumption and insufficient temperature control accuracy in overall cooling mode. In this way, intelligent and precise temperature control in cold chain transportation is achieved, which significantly reduces energy consumption and improves the operational efficiency of the cold chain logistics system while ensuring the stability of cargo quality.

[0060] In some embodiments, the respiration heat of goods is not only related to the quantity of goods piled up, but also influenced by factors such as maturity, variety characteristics, and storage time. For example, fruits gradually ripen during transportation, and the intensity of respiration may increase with maturity. Areas with initially low pile size but high maturity may actually generate more heat than the core area initially determined based on the quantity of goods piled up. Therefore, the core area of ​​goods piled up initially determined by point cloud data is only based on the pile shape and virtual respiration heat intensity value (mainly related to the quantity of goods piled up), and is a rough division. It needs to be recalibrated by the actual number of air supply cycles within the calibration period. Within the set calibration period (e.g., 2 hours), the system continuously records the number of directional air supply cycles for each core area of ​​goods piled up (second count) and other piled packages (first count). The trigger condition for directional air supply is that the area temperature exceeds the respiration heat safety threshold. Therefore, the number of air supply cycles directly reflects the frequency at which the actual heat generation in that area exceeds the safe range. If the first count for a certain other piled package exceeds the second count for any core area of ​​goods piled up, it indicates that the actual respiration heat intensity in that area has exceeded the initial assessment due to factors such as increased maturity, and the original core area division no longer reflects the actual situation. At this point, the reactor core region is redefined from high to low according to the number of directional air supply cycles (i.e., the frequency at which actual heat generation exceeds the threshold), which can more accurately capture the real heat concentration area.

[0061] Repeating this process allows for dynamic adaptation to changes in cargo breathing heat throughout the transportation process: as cargo maturity changes over time, some areas may frequently trigger ventilation due to increased breathing, while the initial core area may require less ventilation as the cargo gradually stabilizes (e.g., the breathing peak has passed). Through periodic calibration over time, the system can continuously correct the core area, avoiding temperature runaway caused by initial assessment biases. The calibration time represents the time period used to dynamically adjust the cargo core area; it is a statistical window set to correct the initial breathing heat intensity ranking determined based on the stack quantity, capturing actual changes in breathing heat caused by factors such as cargo maturity changes. The first count refers to the number of times directional ventilation is performed on other stacked packages besides the cargo core area within the set calibration time, reflecting the frequency with which the actual heat generation in these areas exceeds the safety threshold. The second count refers to the number of times directional ventilation is performed on the original cargo core area within the same calibration time, reflecting the actual heat generation in the initially determined high breathing heat areas. Dynamically updating the cargo core area refers to re-dividing the heat concentration areas that need to be monitored in order to adapt to the differences in respiration heat caused by factors such as changes in cargo maturity, by combining the comparison results of the first and second counts.

[0062] It should be noted that the calibration time should be set in conjunction with the cargo's breathing characteristics: for cargoes with vigorous respiration and rapid ripening changes (such as strawberries and lychees), the calibration time should be shortened (e.g., 1 hour) to quickly respond to changes in heat production; for cargoes with more stable respiration, the time can be extended to 4-6 hours. When comparing the first and second counts, a buffer threshold can be set (e.g., the first count must exceed the second count by two or more times) to avoid frequent updates caused by a single, accidental air supply. Furthermore, after redefining the reactor core area, the monitoring angle of the infrared thermal imager needs to be adjusted simultaneously, and the virtual intensity value of the corresponding area in the breathing thermal map table needs to be updated to make subsequent assessments more realistic.

[0063] In this embodiment, since the cargo breathing heat is affected by multiple factors such as maturity, the initial core area determined based on the stacking quantity has a coarse division problem. Therefore, the cargo core area is dynamically updated by second calibration through the actual number of air supply times within the calibration time. This effectively solves the problem of deviation in the initial core area division and high risk of temperature runaway caused by changes in cargo breathing heat, thereby achieving accurate adaptation to the dynamic changes in cargo breathing heat throughout the transportation process.

[0064] The temperature intelligent control system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3 This is a schematic diagram of the physical device structure of a temperature intelligent control system in the embodiments of this application.

[0065] It should be noted that, Figure 3The structure of the temperature intelligent control system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0066] like Figure 3 As shown, the intelligent temperature control system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 308 into random access memory (RAM) 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0067] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0068] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the various functions defined in the present invention.

[0069] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0070] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0071] Specifically, the temperature intelligent control system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the cold chain logistics temperature intelligent control method provided in the above embodiment.

[0072] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the temperature intelligent control system described in the above embodiments; or it may exist independently and not assembled into the temperature intelligent control system. The storage medium carries one or more computer programs, which, when executed by a processor of the temperature intelligent control system, cause the temperature intelligent control system to implement the cold chain logistics temperature intelligent control method provided in the above embodiments.

[0073] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0074] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0075] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for intelligent temperature control in cold chain logistics, characterized in that, The method includes: Obtain the name information of the target cargo to be transported, and determine the target cold chain temperature and respiratory heat safety threshold corresponding to the target cargo to be transported according to the preset temperature control mapping table. The respiratory heat safety threshold refers to the temperature critical point at which the cargo itself generates heat to a dangerous level. Within a set time before the target goods to be transported enter the carriage, the refrigeration device is controlled to adjust the temperature inside the carriage to the target cold chain temperature and maintain low power operation. After the target goods to be transported are loaded into the carriage, a point cloud image of the goods placement is acquired by a point cloud acquisition device, and multiple cargo stacking core areas are determined based on the cargo placement point cloud image. The cargo stacking core area is the central area where the respiratory heat is concentrated due to the accumulation of goods. Multiple infrared thermal imagers inside the control compartment are directed toward the core areas of each cargo stack, and real-time temperature data of each core area of ​​the cargo stack is monitored. If the real-time temperature data of any of the cargo core areas exceeds the breathing heat safety threshold, the refrigeration unit is controlled to directionally supply air to the cargo core area to reduce the temperature of the cargo core area to the target cold chain temperature.

2. The method according to claim 1, characterized in that, After the step of controlling the refrigeration device to adjust the temperature inside the vehicle compartment to the target cold chain temperature, the method further includes: Multiple temperature data are acquired at set intervals by using multiple backup temperature sensors arranged inside the carriage. When each of the temperature data is within the preset cold chain temperature safety range of the target goods to be transported, the preset interval time is increased according to the preset delay time. Repeat the above steps until the set interval duration reaches the preset maximum interval duration.

3. The method according to claim 1, characterized in that, The process of acquiring point cloud images of cargo placement using a point cloud acquisition device, and determining multiple cargo stack core areas based on the point cloud images, includes: Multi-angle image data of goods inside the carriage is acquired using a point cloud acquisition device; A three-dimensional point cloud network of cargo stacking is constructed based on the multi-angle image data; The three-dimensional point cloud network is meshed, and the three-dimensional point cloud network is divided into multiple virtual units according to a set mesh space size; The stacking pattern determination model determines multiple stacking packages in the three-dimensional point cloud network. The stacking pattern determination model is constructed in advance by deep learning based on multiple stacked three-dimensional point cloud network sets with different stacked goods. Calculate the number of virtual units contained in each stacking package, and obtain the virtual respiratory heat intensity value of each stacking package by combining the number of units with a preset respiratory heat mapping table; Based on the virtual breathing thermal intensity values ​​from largest to smallest, multiple stacked bags, the same number as the number of infrared thermal imagers, are selected to determine the cargo core area.

4. The method according to claim 1, characterized in that, After the step of controlling multiple infrared thermal imagers in the control compartment to be pointed towards each of the cargo stack core areas and monitoring the real-time temperature data of each cargo stack core area, the method further includes: At set core correction times, temperature data of other stacked bags are acquired by an infrared thermal imager. If the temperature data of any other stacked bag exceeds the breathing heat safety threshold, the refrigeration device is controlled to directionally blow air onto the corresponding other stacked bag to reduce the temperature of the other stacked bag to the target cold chain temperature. The other stacked bags are stacked bags other than those in the core area of ​​the cargo stack.

5. The method according to claim 1 or 4, characterized in that, After the step of controlling the refrigeration device to directionally supply air to the corresponding other stacked bags if the real-time temperature data of any of the cargo core areas exceeds the breathing heat safety threshold, the method further includes: Obtain the first number of times each of the other stacked packages is directionally ventilated and the second number of times each of the said cargo core areas is directionally ventilated within the set calibration time. If the first number of times exceeds the second number of times, the cargo core area is re-determined according to the number of times of directional air supply from largest to smallest; Repeat the above steps to dynamically update the cargo core area.

6. The method according to claim 1, characterized in that, Also includes: After the directional air supply operation is completed, the refrigeration unit is controlled to return to low-power operation to await the next directional air supply.

7. The method according to claim 1 or 5, characterized in that, After the step of controlling the refrigeration device to directionally supply air to the core area of ​​the cargo stack if the real-time temperature data of any of the cargo core areas exceeds the breathing heat safety threshold, the method further includes: When a vibration sensor determines that a cold chain logistics vehicle has encountered a bump, a point cloud data acquisition device is used to identify the status of the goods. If the target cargo is detected to have shifted, resulting in damage to the cargo core area corresponding to the target cargo, the system waits for the vibration sensor to confirm that the cold chain logistics vehicle has finished bumping, then recalculates the number of directional airflows to the cargo core area within the calibration time, and redetermines the cargo core area according to the number of directional airflows from largest to smallest.

8. A temperature intelligent control system, characterized in that, The intelligent temperature control system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the intelligent temperature control system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the intelligent temperature control system, the intelligent temperature control system performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the intelligent temperature control system, the intelligent temperature control system performs the method as described in any one of claims 1-7.

Images