A system and method for partition temperature control and remote supervision of an unmanned refrigerated vehicle

Abstract

The present application relates to a kind of unmanned refrigerated vehicle partition temperature control and remote monitoring system, the system includes: AI prediction temperature control module, by fusing weather, road conditions, goods heat parameters and vehicle state, the temperature and energy consumption trend of future 1 ~ 4 hours are predicted, power / set value suggestion is generated accordingly, to drive early adjustment;Multi-temperature zone independent control module is connected with AI prediction temperature control module, receives the power / set value suggestion given by AI prediction temperature control module, to actuator output baffle adjustment instruction, air door instruction and refrigeration / heating instruction, real-time acquisition each temperature zone state, send to collaborative control module;Collaborative control module is connected with multi-temperature zone independent control module, for constraining the path planning of vehicle according to the instruction issued by multi-temperature zone independent control module and the temperature collected, and when abnormal, linkage vehicle speed, parking point selection and remote takeover.

Description

Technical Field

[0001] This invention relates to the field of cold chain logistics and vehicle automatic control technology, and in particular to a system and method for zoned temperature control and remote monitoring of unmanned refrigerated trucks. Background Technology

[0002] With the increasing demand from pharmaceutical cold chain logistics and fresh food e-commerce, and the application of autonomous driving technology in delivery scenarios, it is necessary to ensure temperature compliance throughout the entire process while reducing energy consumption and operational risks under driverless conditions. Traditional refrigerated trucks generally use mechanical or electronic temperature control, achieving temperature control through compressor refrigeration and temperature sensors, mostly in a single temperature zone, maintaining the same temperature environment throughout the vehicle. However, this single temperature zone solution is difficult to meet the needs of mixed loading of multiple product categories; steady-state fluctuations are typically on the order of ±3 to 5℃. Currently, the research and development of autonomous refrigerated trucks focuses more on autonomous driving functions, and the temperature control subsystem still mostly adopts the traditional single temperature zone solution. There is a lack of joint optimization between autonomous driving planning and factors such as the heat load of the compartment, door opening operations, and environmental weather conditions. Existing technologies have accumulated experience in areas such as "vehicle-mounted IoT monitoring," "cloud platform / blockchain traceability," and "electronic temperature control," but a complete technology chain has not yet been formed for autonomous refrigerated trucks, including multi-temperature zone independent control, AI predictive adjustment, full-field temperature zone visualization monitoring, temperature control-path coordination, and graded anomaly handling. Summary of the Invention

[0003] In view of the above problems, the present invention provides a system and method for zoned temperature control and remote monitoring of unmanned refrigerated trucks, in order to solve the technical problems of existing technologies such as the mismatch between temperature control accuracy and multi-category requirements, blind spots in supervision and insufficient data reliability, the disconnect between temperature control and path planning in unmanned driving scenarios, and the imperfect anomaly handling mechanism.

[0004] This invention provides a system for zoned temperature control and remote monitoring of an unmanned refrigerated truck. The system includes: an AI predictive temperature control module, installed on the refrigerated truck, used to predict the temperature and energy consumption trend for the next 1-4 hours by integrating meteorological, road conditions, cargo thermal parameters, and vehicle status, and generate power / setpoint suggestions to drive advance adjustments; a multi-temperature zone independent control module, installed on the refrigerated truck and connected to the AI ​​predictive temperature control module, used to receive the power / setpoint suggestions from the AI ​​predictive temperature control module, output partition adjustment commands, damper commands, and cooling / heating commands to the actuators, collect the status of each temperature zone in real time, and send them to the collaborative control module; and a collaborative control module, installed on the refrigerated truck and connected to the multi-temperature zone independent control module, used to constrain the vehicle's path planning based on the commands issued by the multi-temperature zone independent control module and the collected temperatures, and to link vehicle speed, parking point selection, and remote takeover in case of anomalies.

[0005] Furthermore, the system also includes a full-process visual monitoring module, which is set on a cloud platform to collect the temperature and humidity of the carriage, location, door status, refrigeration unit and power supply status, generate heat maps and historical curves, and periodically upload summary data to the blockchain for evidence storage.

[0006] Furthermore, the multi-temperature zone independent control module includes a zoned refrigeration unit, which is an execution unit used to adjust the cooling capacity output of the corresponding temperature zone according to the control command. The execution unit includes a zoned evaporator, a fan, a damper, and a refrigerant flow regulating component.

[0007] This invention also provides a method for zoned temperature control and remote monitoring of an unmanned refrigerated truck. The method includes: Step 1, receiving a transportation task, a cargo list, and time requirements, and reading the constraint parameters for each type of cargo, including: target temperature range, allowable fluctuation threshold, and maximum acceptable over-temperature duration; Step 2, generating a temperature zone division scheme based on the cargo heat load and loading volume, and sending instructions to drive the partitions, dampers, and zoned refrigeration units into the initial state according to the scheme, completing the temperature zone division, and sensor self-testing and calibration; Step 3, after the sensor self-testing and calibration, collecting the temperature and humidity of each temperature zone in real time, forming a unified timestamp data frame with door magnets, positioning, vehicle speed, and external weather, and writing it into the vehicle cache; Step 4, based on future road sections... The system takes the following steps: 1) Environment, door opening operation plan, and current thermal status, along with data frames, and outputs future window temperature trends and energy consumption assessment results; 2) Determine whether temperature adjustment is needed in advance based on the future window temperature trend and energy consumption assessment results. If so, pre-cooling / preheating is performed in advance; 3) Combine constraint parameters to map temperature control constraints to path weights, prioritizing routes with lower heat loads and higher accessibility, and dynamically adjusting the arrival sequence; 4) During dynamic adjustment, if the real-time temperature deviation exceeds the control zone, the partitioned PID loop performs rapid correction. If over-temperature, equipment failure, or communication interruption events are triggered, automatic degradation control is executed according to the preset risk level handling strategy, and remote manual takeover is determined based on the risk level.

[0008] Furthermore, step 6 also includes: the full-process visualization monitoring module generates heat maps and historical curves, uploads the heat maps, trend curves and key events, and simultaneously hashes and signs the summary data on the blockchain according to a preset period.

[0009] Furthermore, the method also includes: Step 8, after the transportation task is completed, exporting a full-process temperature control traceability report, including temperature zone history, alarm records, handling actions and evidence index, for task traceability.

[0010] Furthermore, step 3 includes: step 31, the multi-temperature zone independent control module identifies the type of goods through electronic tags / order information and establishes a temperature zone topology in combination with the space constraints of the box; step 32, the multi-temperature zone independent control module issues control parameters such as set temperature, allowable deviation, maximum temperature rise rate, and recovery time window to each temperature zone. Step 33: The multi-temperature zone independent control module controls the partition position, damper opening, and zone evaporator / heater power to form the initial air supply organization for each temperature zone. Step 34: Each temperature zone independently performs PID calculations to obtain control quantities for compressor load, fan speed, and local compensation power. Step 35: When the temperature difference between adjacent temperature zones is too large, the multi-temperature zone independent control module dynamically restricts cross-zone airflow and adjusts the compensation coefficient to reduce boundary crosstalk. Step 36: When door opening, loading / unloading, or rapid acceleration occurs, short-term enhanced control is triggered to return to the target zone within a preset recovery time. Step 37: The current temperature zone health status, deviation statistics, and energy consumption ratio are output, forming a unified timestamp data frame with door magnets, positioning, vehicle speed, and external weather data, and written to the vehicle cache for use by the collaborative control module.

[0011] Further, step 5 includes: step 51, fusing in-vehicle temperature and humidity time series, historical door opening behavior, cargo thermal inertia, external temperature / sunlight, road congestion, and slope information; step 52, performing outlier removal, time alignment, missing data imputation, and sliding window construction to form an input vector that can be used for inference; step 53, obtaining the temperature curves and key inflection points of each temperature zone predicted by the model for the next 1 to 4 hours; step 54, estimating the energy consumption increment and overheating risk probability under different strategies based on the temperature curves and key inflection points; step 55, selecting the optimal strategy from three types of strategies—"temperature control accuracy priority / energy consumption priority / compromise mode"—based on the estimated energy consumption increment and overheating risk probability, and outputting the zone setpoint adjustment amount; step 56, comparing the actual temperature with the prediction results, calculating the prediction error and updating the model parameters or correction factors, and obtaining control suggestions by combining the zone setpoint adjustment amount; step 57, synchronizing the predicted trajectory and control suggestions to the multi-temperature zone control module, the visualization monitoring module, and the path coordination module to perform pre-cooling / preheating in advance.

[0012] Furthermore, the method for automatically degrading control according to the pre-planned procedure and deciding whether to remotely take over based on the risk level if overheating, equipment failure, or communication interruption events are triggered includes: Step 71, obtaining the estimated arrival time, road congestion, and environmental exposure indicators from multiple candidate paths generated by the autonomous driving system; Step 72, the collaborative control module maps the temperature zone risk prediction results to path penalty terms and calculates the comprehensive cost function; Step 73, selecting the path with the lowest comprehensive cost and simultaneously outputting a pre-adjustment instruction to the AI ​​predictive temperature control module; Step 74, if there are no abnormalities during the driving process, continuously monitoring overheating risk, equipment health, communication link status, and takeover capability; Step 75, if overheating, equipment failure, or communication interruption events are triggered, automatically degrading control is executed according to the preset risk level handling strategy, and remote takeover is initiated; Step 76, if remote takeover is successful, the operator issues a temporary strategy; if remote takeover fails, the local minimum risk strategy is executed; Step 77, key data fragments, control instructions, and manual operation records before and after the anomaly are uniformly archived and indexed on the blockchain for later traceability.

[0013] Furthermore, the preset risk level handling strategy includes: when the temperature deviation is controllable, the risk level is level one, and local automatic correction is performed; when a continuous deviation or single point of failure occurs, the risk level is level two, and the vehicle speed is reduced, the route is changed, and backup cooling is activated; when there is a risk of loss of control, the risk level is level three, and a safe stop is executed and remote takeover is initiated.

[0014] This invention provides a system and method for zoned temperature control and remote monitoring of unmanned refrigerated trucks. It mainly addresses the technical problems of existing technologies, such as single temperature zones with large fluctuations, making it difficult to simultaneously meet the mixed loading requirements of multiple categories such as pharmaceuticals, fresh produce, and frozen goods; limited measurement points, making it difficult to reflect the temperature field inside the truck compartment; centralized storage posing a risk of tampering and being unreliable evidence of the cold chain; failure to consider the thermal environment along the route, making it impossible to adjust the temperature control in advance based on the route; lack of coordinated optimization between energy consumption and temperature control; and the lack of graded and implementable automatic handling strategies for scenarios such as over-temperature, equipment failure, communication interruption, and emergency takeover. Attached Figure Description

[0015] Figure 1 A flowchart of a method for zoned temperature control and remote monitoring of an unmanned refrigerated truck provided by the present invention; Figure 2 A flowchart of a method for collecting temperature, humidity, and other parameters provided by this invention; Figure 3 This is a flowchart of a method for pre-cooling / preheating provided by the present invention; Figure 4 This is a flowchart of an exception handling method provided by the present invention. Detailed Implementation

[0016] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0017] Example 1: This invention provides a system and method for zoned temperature control and remote monitoring of an unmanned refrigerated truck. The system includes: an AI predictive temperature control module, a multi-temperature zone independent control module, a collaborative control module, and a full-process visual monitoring module. Figure 1 As shown, the method includes: Step 1: Receive the transportation task, cargo list and time requirements, and read the constraint parameters for each type of cargo, including: target temperature range, allowable fluctuation threshold, and maximum acceptable over-temperature duration; Step 2: Based on the heat load and loading volume of the goods, generate a temperature zone division scheme and send instructions to drive the partition, damper, and zoned refrigeration unit into the initial state according to the scheme, complete the temperature zone division, and perform sensor self-test and calibration. A multi-temperature zone independent control module, installed on the refrigerated truck and connected to an AI predictive temperature control module, receives power / setpoint suggestions from the AI ​​predictive temperature control module, outputs baffle adjustment commands, damper commands, and cooling / heating commands to the actuators, and collects the real-time status of each temperature zone, sending this data to the collaborative control module. The multi-temperature zone independent control module includes a zoned refrigeration unit, which is an actuator used to adjust the cooling output of the corresponding temperature zone according to the control commands. The actuator includes a zoned evaporator, fan, damper, and / or refrigerant flow regulating component. This module divides the truck compartment into 2 to 6 configurable temperature zones by controlling the baffles, dampers, and refrigeration / heating equipment, with each zone independently maintaining its target temperature.

[0018] Step 3: After the sensor self-test and calibration are completed, the temperature and humidity of each temperature zone are collected in real time, and a unified timestamp data frame is formed with the door magnet, positioning, vehicle speed, and external weather and written into the vehicle cache. Step 4: Based on the future road environment, door opening operation plan, current thermal status, and data frames, output the future window temperature trend and energy consumption assessment results; The AI-powered predictive temperature control module, installed on the refrigerated truck, predicts temperature and energy consumption trends for the next 1-4 hours by integrating weather, road conditions, cargo thermal parameters, and vehicle status. Based on this prediction, it generates power / setpoint suggestions to drive advance adjustments. The module receives external weather / map data via a sensor network, outputs setpoints to the multi-temperature zone control module, and provides predicted trajectories for display to the monitoring module.

[0019] Step 5: Determine whether the temperature needs to be adjusted in advance based on the future window temperature trend and energy consumption assessment results. If so, perform pre-cooling / preheating in advance. Step 6: Combine the constraint parameters to map the temperature control constraints into path weights, prioritize the selection of road segments with lower heat load and higher accessibility, and dynamically adjust the arrival order. Step 7: During the dynamic adjustment process, if the real-time temperature deviation exceeds the control range, the partitioned PID loop will perform rapid correction. If an over-temperature, equipment failure, or communication interruption event is triggered, automatic degradation control will be executed according to the preset risk level handling strategy, and remote manual takeover will be determined based on the risk level.

[0020] The collaborative control module, installed on the refrigerated truck, is connected to the multi-temperature zone independent control module. It is used to constrain the vehicle's route planning based on the instructions issued by the multi-temperature zone independent control module and the collected temperature, and to link the vehicle speed, parking point selection, and remote takeover in case of abnormalities.

[0021] Step 8: After the transportation task is completed, export the full temperature control traceability report, which includes temperature zone history, alarm records, handling actions and evidence index, for task traceability.

[0022] The fully visualized monitoring module, set up on the cloud platform, is used to collect the temperature and humidity of the carriage, its location, door status, and the status of the refrigeration unit and power supply. It generates heat maps and historical curves, and periodically uploads summary data to the blockchain for evidence storage.

[0023] This invention provides methods and systems covering: independent control of multiple temperature zones, AI-predictive temperature control based on multi-source data, temperature heat map visualization and blockchain evidence storage, and temperature control-path coordination and anomaly handling.

[0024] Example 2: This invention provides a system and method for zoned temperature control and remote monitoring of an unmanned refrigerated truck. The system includes: an AI predictive temperature control module, a multi-temperature zone independent control module, a collaborative control module, and a full-process visual monitoring module. Figure 1 As shown, the method includes: Step 1: Receive the transportation task, cargo list and time requirements, and read the constraint parameters for each type of cargo, including: target temperature range, allowable fluctuation threshold, and maximum acceptable over-temperature duration; Step 2: Based on the heat load and loading volume of the goods, generate a temperature zone division scheme and send instructions to drive the partition, damper, and zoned refrigeration unit into the initial state to complete the temperature zone division, as well as sensor self-test and calibration. The partition is an insulated partition composed of a polyurethane foam and aluminum foil composite insulation layer. This partition allows for dynamic adjustment of the temperature zone volume. Each temperature zone has independent air ducts and electric dampers, as well as zoned evaporators / heaters for cooling and preheating. Temperature zone division is determined based on the type and quantity of goods and heat load. Each temperature zone uses independent PID (PID is a classic control algorithm widely used in industrial control systems, robot control, autonomous driving, etc. A PID controller combines proportional (P), integral (I), and derivative (D) control actions to adjust the system's error signal in real time, ensuring the system output tracks or maintains near the desired reference value) and temperature equalization strategies to eliminate hot spots.

[0025] Step 3: After the sensor self-test and calibration are completed, the temperature and humidity of each temperature zone are collected in real time according to the generated temperature zone division scheme. The data frame is then combined with the door magnet, positioning, vehicle speed, and external weather data to form a unified timestamp data frame and written into the vehicle cache. like Figure 2 As shown, step 3 includes: Step 31: Identify the product type using electronic tags / order information, and establish a temperature zone topology based on the container space constraints; Step 32: Issue control parameters such as set temperature, allowable deviation, maximum temperature rise rate, and recovery time window to each temperature zone.

[0026] Step 33: Control the position of the baffle, the opening of the damper, and the power of the zoned evaporator / heater to form the initial air supply organization for each temperature zone; Step 34: Perform PID calculations independently for each temperature zone to obtain the control quantities for compressor load, fan speed, and local compensation power; Step 35: When the temperature difference between adjacent temperature zones is too large, dynamically restrict cross-zone airflow and adjust the compensation coefficient to reduce boundary crosstalk; Step 36: When door opening, loading / unloading, or rapid acceleration occurs, short-term enhanced control is triggered to return to the target zone within a preset recovery time. Step 37: Output the current temperature zone health status, deviation statistics and energy consumption ratio, form a unified timestamp data frame with door magnet, positioning, vehicle speed and external weather and write it into the vehicle cache for the collaborative control module to call.

[0027] Step 4: Based on the future road environment, door opening operation plan, current thermal status, and data frames, output the future window temperature trend and energy consumption assessment results; Generally, temperature prediction can use time series models such as LSTM; energy consumption prediction can use regression models; anomaly detection can use unsupervised detection such as isolated forests; and multi-objective optimization (accuracy, energy consumption, response speed) and online parameter updates are supported.

[0028] Step 5: Determine whether the temperature needs to be adjusted in advance based on the energy consumption assessment results. If so, perform pre-cooling / preheating in advance. like Figure 3 As shown, step 5 includes: Step 51: Integrate in-vehicle temperature and humidity time sequence, historical door opening behavior, cargo thermal inertia, external temperature / sunlight, road congestion and slope information; Step 52: Perform outlier removal, time alignment, missing value imputation, and sliding window construction to form an input vector that can be used for inference; Step 53: Obtain the temperature curves and key inflection points for each temperature zone predicted by the model for the next 1 to 4 hours; Step 54: Based on the temperature curve and key inflection points, estimate the energy consumption increment and overheat risk probability under different strategies; Step 55: Based on the estimated energy consumption increment and over-temperature risk probability, select the optimal strategy from the three strategies of "temperature control accuracy priority / energy consumption priority / compromise mode" and output the partition setpoint adjustment amount. Step 56: Compare the actual temperature with the predicted result, calculate the prediction error and update the model parameters or correction factor, and combine the adjustment amount of the zone setpoint to obtain control recommendations; Step 57: Synchronize the predicted trajectory and control recommendations to the multi-temperature zone control module, the visualization monitoring module, and the path coordination module to perform pre-cooling / preheating in advance.

[0029] Step 6: Combine the constraint parameters to map the temperature control constraints into path weights, prioritize the selection of road segments with lower heat load and higher accessibility, and dynamically adjust the arrival order. This step integrates temperature control constraints into path planning and, in case of anomalies, links vehicle speed, stop point selection, and remote takeover. It exchanges paths, environmental heat load assessments, and emergency commands bidirectionally with vehicle control mechanisms (such as the autonomous driving unit); and invokes multi-temperature zones and AI modules to execute pre-cooling / backup cooling strategies. This enables temperature-sensing path planning (avoiding high-temperature, sun-exposed sections); dynamic route rerouting; switching local strategy tables when communication is interrupted; and establishing low-latency remote takeover links. This step also utilizes a full-process visualization monitoring module to collect high-density data on the temperature and humidity of the vehicle compartment, its location, door status, and the status of the refrigeration unit and power supply, generating heat maps and historical curves. The heat maps, trend curves, and key events are uploaded, and summary data is hash-signed and uploaded to the blockchain at preset intervals. This provides data flow for cloud platform visualization and alarms; provides data packets to be uploaded to the blockchain for blockchain services; and provides detection input for anomaly handling. Specifically, the temperature sampling period can be on the order of 5 seconds; humidity on the order of 30 seconds; GPS / BeiDou positioning; real-time heat map rendering; hash verification and digital signature for tamper-proofing; and the on-chain period can be on the order of 5 minutes.

[0030] Step 7: During operation, when the real-time temperature deviation exceeds the control range, the partition PID loop performs rapid correction. If an over-temperature, equipment failure, or communication interruption event is triggered, automatic degradation control is executed according to the preset risk level handling strategy, and remote manual takeover is determined based on the risk level.

[0031] like Figure 4 As shown, the method for automatically degrading control according to the pre-planned procedure and deciding whether to remotely manually take over if over-temperature, equipment failure, or communication interruption events are triggered includes: Step 71: Obtain estimated arrival time, road congestion, and environmental exposure indices from multiple candidate paths generated by the autonomous driving system; Step 72: The collaborative control module maps the temperature zone risk prediction results into path penalty terms and calculates the comprehensive cost function; Step 73: Select the path with the lowest overall cost and output the pre-adjustment command to the AI ​​predictive temperature control module. Step 74: If there are no abnormalities during the operation, continue to monitor overheating risk, equipment health, communication link status, and takeover capability. Step 75: If an over-temperature, equipment failure, or communication interruption event is triggered, automatic degradation control is executed according to the preset risk level handling strategy, and remote takeover is initiated. The preset risk level handling strategies include: when the temperature deviation is controllable, the risk level is Level 1, and local automatic correction is performed; when a continuous deviation or single-point failure occurs, the risk level is Level 2, and the vehicle speed is reduced, the route is changed, and backup cooling is activated; when there is a risk of loss of control, the risk level is Level 3, and a safe stop is executed and remote takeover is initiated. Step 76: If remote takeover is successful, the operator issues a temporary policy; if remote takeover fails, the local minimum risk policy is executed. Step 77: Key data fragments, control instructions, and manual operation records before and after the anomaly are archived and indexed on the blockchain for later traceability.

[0032] Step 8: After the transportation task is completed, export the full temperature control traceability report, which includes temperature zone history, alarm records, handling actions and evidence index, for task traceability.

[0033] The key technical parameters of this technical solution are shown in Table 1.

[0034]

[0035] Table 1 Key Technical Parameters For example, Example 1: Pharmaceutical vaccine transportation. A batch of vaccines requires an environment of 2-8℃, with a total distance of approximately 200km and a travel time of about 4 hours. The system is configured with two temperature zones (primary + backup), with the primary temperature zone targeting 5℃ and a sensor density of approximately 4 points per cubic meter. After RFID identification upon loading, the temperature zone is assigned; AI predicts routes through areas exposed to direct sunlight and pre-cools the vehicle to 4.5℃; a summary is uploaded to the blockchain every 5 minutes throughout the journey; a temperature traceability report is generated upon arrival. The maximum measured temperature fluctuation is approximately 0.8℃, and energy consumption is reduced by approximately 25% compared to traditional solutions. Example 2: Fresh produce multi-category delivery. Frozen (approximately -18℃), refrigerated (approximately 4℃), and ambient (approximately 15℃) three-temperature zones are shared in a single container; partitions are dynamically adjusted according to the cargo volume. Each temperature zone has an independent PID (Process Control Point), and the target temperature is restored within approximately 30 seconds after the door is opened for pickup; the route avoids high-temperature sections, reducing energy consumption by approximately 15%. Example 3: Handling of refrigeration failures. After detecting an abnormal temperature rise rate, AI predicts that the threshold may be exceeded within about 10 minutes; the platform alarms, reduces speed, starts backup refrigeration (if configured), and plans a shaded parking spot; if the condition continues to deteriorate, an emergency shutdown is initiated and remote takeover is supported (establishment latency <500ms); abnormal process data is uploaded to the blockchain for responsibility determination.

[0036] In summary, this invention provides a system and method for zoned temperature control and remote monitoring of unmanned refrigerated trucks. This technical solution achieves independent temperature control in multiple temperature zones, with fluctuations controlled within ±1℃, meeting the differentiated needs of pharmaceuticals, fresh produce, and frozen goods. The entire temperature field is visualized, and blockchain-based evidence storage enhances data tamper resistance and traceability. Joint optimization of the path and temperature control reduces energy consumption by approximately 20%–30%. Over-temperature warnings, backup equipment, local autonomous operation, and remote takeover form a closed loop. This solves the problem of mixed loading in a single temperature zone due to the dynamic structure of multiple temperature zones, reduces the risk of over-temperature due to disturbances such as door opening and exposure to sunlight through predictive temperature control, and addresses the regulatory pain points of "invisibility and lack of trust" through visualization and blockchain evidence storage. Furthermore, in unmanned driving scenarios, temperature control, path management, and anomaly handling are integrated, reducing the risks of unattended operation.

[0037] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A system for zoned temperature control and remote monitoring of an unmanned refrigerated truck, characterized in that, The system includes: The AI ​​predictive temperature control module, installed on the refrigerated truck, is used to predict the temperature and energy consumption trend in the next 1 to 4 hours by integrating weather, road conditions, cargo thermal parameters and vehicle status, and generate power / set value suggestions to drive advance adjustment. The multi-temperature zone independent control module is installed on the refrigerated truck and connected to the AI ​​predictive temperature control module. It is used to receive power / set value suggestions from the AI ​​predictive temperature control module, output partition adjustment commands, damper commands and cooling / heating commands to the actuator, collect the status of each temperature zone in real time, and send them to the collaborative control module. The collaborative control module, installed on the refrigerated truck, is connected to the multi-temperature zone independent control module. It is used to constrain the vehicle's path planning based on the instructions issued by the multi-temperature zone independent control module and the collected temperature, and to link the vehicle speed, parking point selection, and remote takeover in case of abnormalities.

2. The system for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 1, characterized in that, The system also includes: The fully visualized monitoring module, set up on the cloud platform, is used to collect the temperature and humidity of the carriage, its location, door status, and the status of the refrigeration unit and power supply. It generates heat maps and historical curves, and periodically uploads summary data to the blockchain for evidence storage.

3. The system for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 1, characterized in that, The multi-temperature zone independent control module includes a zone cooling unit, which is an execution unit used to adjust the cooling capacity output of the corresponding temperature zone according to the control command. The execution unit includes a zone evaporator, a fan, a damper, and a refrigerant flow regulating component.

4. A method for using the system of zoned temperature control and remote monitoring of an unmanned refrigerated truck as described in any one of claims 1-3, characterized in that, The method includes: Step 1: Receive the transportation task, cargo list and time requirements, and read the constraint parameters for each type of cargo, including: target temperature range, allowable fluctuation threshold, and maximum acceptable over-temperature duration; Step 2: Based on the heat load and loading volume of the goods, generate a temperature zone division scheme and send instructions to drive the partition, damper, and zoned refrigeration unit into the initial state according to the scheme, complete the temperature zone division, and perform sensor self-test and calibration. Step 3: After the sensor self-test and calibration are completed, the temperature and humidity of each temperature zone are collected in real time, and a unified timestamp data frame is formed with the door magnet, positioning, vehicle speed, and external weather and written into the vehicle cache. Step 4: Based on the future road environment, door opening operation plan, current thermal status, and data frames, output the future window temperature trend and energy consumption assessment results; Step 5: Determine whether the temperature needs to be adjusted in advance based on the future window temperature trend and energy consumption assessment results. If so, perform pre-cooling / preheating in advance. Step 6: Combine the constraint parameters to map the temperature control constraints into path weights, prioritize the selection of road segments with lower heat load and higher accessibility, and dynamically adjust the arrival order. Step 7: During the dynamic adjustment process, if the real-time temperature deviation exceeds the control range, the partitioned PID loop will perform rapid correction. If an over-temperature, equipment failure, or communication interruption event is triggered, automatic degradation control will be executed according to the preset risk level handling strategy, and remote manual takeover will be determined based on the risk level.

5. The method for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 4, characterized in that, Step 6 further includes: the full-process visualization monitoring module generates heat maps and historical curves, uploads the heat maps, trend curves and key events, and hashes and signs the summary data on the blockchain according to a preset period.

6. The method for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 4, characterized in that, The method further includes: Step 8, after the transportation task is completed, exporting a full-process temperature control traceability report, including temperature zone history, alarm records, handling actions and evidence index, for task traceability.

7. The method for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 4, characterized in that, Step 3 includes: Step 31: Identify the product type using electronic tags / order information, and establish a temperature zone topology based on the container space constraints; Step 32: The multi-temperature zone independent control module sends control parameters to each temperature zone, including: set temperature, allowable deviation, maximum temperature rise rate, and recovery time window; Step 33: Control the position of the baffle, the opening of the damper, and the power of the zoned evaporator / heater to form the initial air supply organization for each temperature zone; Step 34: Perform PID calculations independently for each temperature zone to obtain the control quantities of compressor load, fan speed, and local compensation power; Step 35: When the temperature difference between adjacent temperature zones is too large, the multi-temperature zone independent control module dynamically restricts cross-zone airflow and adjusts the compensation coefficient to reduce boundary crosstalk. Step 36: When door opening, loading / unloading, or rapid acceleration occurs, short-term enhanced control is triggered to return to the target zone within a preset recovery time. Step 37: Output the current temperature zone health status, deviation statistics and energy consumption ratio. Combine the obtained parameters with door magnet, positioning, vehicle speed and external weather to form a unified timestamp data frame and write it into the vehicle cache for use by the collaborative control module.

8. The method for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 4, characterized in that, Step 5 includes: Step 51: Integrate in-vehicle temperature and humidity time sequence, historical door opening behavior, cargo thermal inertia, external temperature / sunlight, road congestion and slope information; Step 52: Perform outlier removal, time alignment, missing value imputation, and sliding window construction to form an input vector that can be used for inference; Step 53: Obtain the temperature curves and key inflection points for each temperature zone predicted by the model for the next 1 to 4 hours; Step 54: Based on the temperature curve and key inflection points, estimate the energy consumption increment and overheat risk probability under different strategies; Step 55: Based on the estimated energy consumption increment and over-temperature risk probability, select the optimal strategy from the three strategies of "temperature control accuracy priority / energy consumption priority / compromise mode" and output the partition setpoint adjustment amount. Step 56: Compare the actual temperature with the predicted result, calculate the prediction error and update the model parameters or correction factor, and combine the adjustment amount of the zone setpoint to obtain control recommendations; Step 57: Synchronize the predicted trajectory and control recommendations to the multi-temperature zone control module, the visualization monitoring module, and the path coordination module to perform pre-cooling / preheating in advance.

9. The method for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 4, characterized in that, The method for automatically degrading control according to the pre-planned procedure and deciding whether to remotely manually take over if over-temperature, equipment failure, or communication interruption events are triggered includes: Step 71: Obtain estimated arrival time, road congestion, and environmental exposure indices from multiple candidate paths generated by the autonomous driving system; Step 72: The collaborative control module maps the temperature zone risk prediction results into path penalty terms and calculates the comprehensive cost function; Step 73: Select the path with the lowest overall cost and output the pre-adjustment command to the AI ​​predictive temperature control module. Step 74: If there are no abnormalities during the operation, continue to monitor overheating risk, equipment health, communication link status, and takeover capability. Step 75: If an over-temperature, equipment failure, or communication interruption event is triggered, automatic degradation control is executed according to the preset risk level handling strategy, and remote takeover is initiated. Step 76: If remote takeover is successful, the operator issues a temporary policy; if remote takeover fails, the local minimum risk policy is executed. Step 77: Key data fragments, control instructions, and manual operation records before and after the anomaly are archived and indexed on the blockchain for later traceability.

10. A method for zoned temperature control and remote monitoring of an unmanned refrigerated truck according to claim 3 or 9, characterized in that, The preset risk level handling strategy includes: When the temperature deviation is controllable, the risk level is Level 1, and local automatic correction is enabled. When a persistent deviation or single point of failure occurs, the risk level is level two, and the vehicle speed is reduced, the route is changed, and the backup cooling is activated. When there is a risk of loss of control, the risk level is three, and a safe stop is executed and remote takeover is initiated.

Images