Cold-chain logistics temperature control supervision method and system based on GPS linkage

Abstract

The invention discloses a cold-chain logistics temperature control supervision method and system based on GPS linkage, and relates to the related technical field of cold-chain logistics, and the method comprises the steps: installing a vehicle-mounted terminal on a cold-chain logistics transport vehicle, and collecting the vehicle position information and carriage temperature data in real time; encrypting and uploading to a monitoring processing center, and calling cold-chain logistics temperature control analysis dual channels of the target cold-chain goods; obtaining a temperature comparison result with a preset safe temperature threshold value, and matching and determining a target temperature control analysis channel; and performing temperature control analysis, determining a temperature control adjustment strategy parameter, and performing cold-chain logistics temperature control supervision. The technical problems that in the prior art, temperature control supervision lags behind, deep fusion analysis with the vehicle position and the transportation state is not carried out, specific reasons of temperature abnormity cannot be distinguished, and the regulation and control strategy is lack of accuracy and predictability are solved, and real-time, accurate and intelligent cold chain transportation temperature control abnormity recognition and supervision are achieved. And the reliability, the safety and the efficiency of cold-chain logistics are improved.

Description

Technical Field

[0001] This application relates to the technical field of cold chain logistics, specifically to a GPS-linked method and system for temperature control monitoring in cold chain logistics. Background Technology

[0002] Temperature fluctuations are a key factor affecting cargo quality during cold chain transportation, especially in long-distance or cross-regional logistics. Environmental changes, equipment malfunctions, or operational errors can all lead to abnormal temperatures, resulting in spoilage, shortened shelf life, and even food safety incidents. Real-time, accurate monitoring and intelligent control of the cold chain transportation environment has become a pressing technical challenge. Traditional cold chain logistics temperature control relies heavily on manual recording and periodic inspections, such as using temperature recorders to download data after transportation. This approach suffers from significant lag, failing to provide immediate warnings and interventions for abnormal temperatures. Furthermore, the lack of dynamic correlation with vehicle location and transportation status makes it difficult to distinguish the specific causes of temperature anomalies, such as equipment malfunction, door opening, or changes in the external environment. This results in a lack of targeted control strategies and low efficiency. In addition, IoT-based cold chain transportation monitoring lacks deep integration and intelligent analysis of multi-source data, making it difficult to adapt to complex and ever-changing logistics scenarios, leading to high false alarm rates or insufficient control response.

[0003] Therefore, current technologies suffer from several technical problems, including lagging temperature control monitoring, lack of in-depth integration and analysis with vehicle location and transportation status, inability to distinguish the specific causes of temperature anomalies, and a lack of precision and predictability in control strategies. Summary of the Invention

[0004] This application provides a GPS-linked cold chain logistics temperature control monitoring method and system, which solves the technical problems existing in the prior art, such as lagging temperature control monitoring, lack of in-depth integration and analysis with vehicle location and transportation status, inability to distinguish the specific causes of temperature anomalies, and lack of precision and predictability in control strategies. It achieves the technical effect of realizing real-time, accurate, and intelligent identification and monitoring of temperature control anomalies in cold chain transportation, thereby improving the reliability, safety, and efficiency of cold chain logistics.

[0005] This application provides a GPS-linked method for temperature control monitoring in cold chain logistics. The method includes: installing an on-board terminal on a cold chain logistics transport vehicle, the on-board terminal integrating a GPS positioning module, a temperature sensor, and a wireless communication module; collecting vehicle location information and compartment temperature data in real time through the GPS positioning module and the temperature sensor; encrypting and uploading the vehicle location information and compartment temperature data to a monitoring and processing center via the wireless communication module; calling a dual-channel cold chain logistics temperature control analysis for the target cold chain goods through the monitoring and processing center, the dual-channel including a short-term temperature control analysis channel and a long-term temperature control analysis channel; obtaining the temperature comparison result between the compartment temperature data and a preset safe temperature threshold; matching the temperature comparison result with the dual-channel cold chain logistics temperature control analysis to determine the target temperature control analysis channel; performing temperature control analysis on the vehicle location information and compartment temperature data based on the target temperature control analysis channel to determine temperature control adjustment strategy parameters; and performing cold chain logistics temperature control monitoring through the temperature control adjustment strategy parameters.

[0006] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: obtaining a cold chain logistics cargo database through the monitoring and processing center; obtaining cold chain cargo attribute elements, including cargo type, biochemical change characteristics, microbial inhibition requirements, and storage requirements; classifying and analyzing the temperature control of each cold chain cargo in the cold chain logistics cargo database according to the cold chain cargo attribute elements to obtain a multi-cargo temperature control analysis dual-channel database; and matching and calling the target cold chain cargo's attribute elements with the multi-cargo temperature control analysis dual-channel database to obtain a cold chain logistics temperature control analysis dual-channel database.

[0007] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: classifying and identifying each cold chain cargo in the cold chain logistics cargo database according to the cold chain cargo attribute elements to obtain a cold chain logistics cargo attribute element parameter set; clustering and integrating the cold chain logistics cargo database based on the cold chain logistics cargo attribute element parameter set to obtain a cold chain logistics cargo cluster set; performing data mining and temperature control analysis on the cold chain logistics cargo cluster set to obtain a multi-cargo short-term temperature control analysis channel set and a multi-cargo long-term temperature control analysis channel set; and combining the multi-cargo short-term temperature control analysis channel set and the multi-cargo long-term temperature control analysis channel set in parallel to obtain the multi-cargo temperature control analysis dual-channel database.

[0008] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: performing temperature control data mining on the cold chain logistics cargo cluster set to obtain a historical temperature control dataset for the cold chain logistics cargo cluster; constructing a cold chain logistics temperature control effect index set; performing safe temperature analysis on the historical temperature control dataset of the cold chain logistics cargo cluster according to the cold chain logistics temperature control effect index set to determine a safe temperature threshold set for the cold chain logistics cargo cluster; classifying the historical temperature control dataset of the cold chain logistics cargo cluster according to the safe temperature threshold set to obtain a short-term cold chain logistics cargo cluster temperature control dataset and a long-term cold chain logistics cargo cluster temperature control dataset; performing temperature control analysis based on the short-term and long-term cold chain logistics cargo cluster temperature control datasets to obtain a set of short-term and long-term temperature control analysis channels for multiple cargoes.

[0009] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: Based on the short-term cold chain logistics cargo cluster temperature control dataset, determine the cargo cluster compartment temperature dataset and the cargo cluster temperature control adjustment dataset; obtain the cargo cluster temperature deviation dataset between the cargo cluster compartment temperature dataset and the cold chain logistics cargo cluster safe temperature threshold set; perform temperature control training and fitting based on the cargo cluster temperature deviation dataset and the cargo cluster temperature control adjustment dataset to obtain a set of PID temperature controllers, and use the PID temperature controller set as a set of short-term temperature control analysis channels for multiple cargoes; perform temperature control analysis based on the long-term cold chain logistics cargo cluster temperature control dataset to construct a set of long-term temperature control analysis channels for multiple cargoes.

[0010] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: Arranging the long-term cold chain logistics cargo cluster temperature control dataset in chronological order to obtain a long-term cold chain cargo cluster temperature control time-series dataset; determining the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, cargo cluster remaining distance dataset, and cargo cluster temperature control adjustment dataset based on the long-term cold chain cargo cluster temperature control time-series dataset; performing temperature trend prediction training based on the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, and cargo cluster remaining distance dataset to generate a cargo cluster temperature trend predictor set; and performing temperature control analysis based on the cargo cluster temperature trend predictor set and the cargo cluster temperature control adjustment dataset to construct a multi-cargo long-term temperature control analysis channel set.

[0011] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: obtaining a cargo cluster temperature trend prediction dataset based on the output data of the cargo cluster temperature trend predictor set; using a deep neural network structure to perform correlation temperature control training and iterative feedback optimization on the cargo cluster temperature trend prediction dataset and the cargo cluster temperature control adjustment dataset to obtain a cargo cluster temperature control analyzer set; and connecting and merging the cargo cluster temperature trend predictor set and the cargo cluster temperature control analyzer set to construct the multi-cargo long-term temperature control analysis channel set.

[0012] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: when the temperature comparison result shows that the temperature data of the compartment exceeds a preset safe temperature threshold, the short-term temperature control analysis channel is activated as the target temperature control analysis channel; if the temperature comparison result shows that the temperature data of the compartment is within the preset safe temperature threshold, the long-term temperature control analysis channel is activated as the target temperature control analysis channel.

[0013] In a possible implementation, the GPS-linked cold chain logistics temperature control monitoring method further performs the following processing: based on the arrangement and stacking of the target cold chain goods, a cold air circulation impact analysis is performed to obtain the cold air diffusion impact coefficient of the goods; based on the cold air diffusion impact coefficient of the goods, the temperature rise impact factor of the goods is determined, and the temperature control adjustment strategy parameters are corrected based on the temperature rise impact factor of the goods.

[0014] This application also provides a GPS-linked cold chain logistics temperature control monitoring system, comprising: a data acquisition module for installing a vehicle-mounted terminal on a cold chain logistics transport vehicle, the vehicle-mounted terminal integrating a GPS positioning module, a temperature sensor, and a wireless communication module, which collects vehicle location information and compartment temperature data in real time through the GPS positioning module and the temperature sensor; a temperature control analysis channel calling module for encrypting and uploading the vehicle location information and compartment temperature data to a monitoring and processing center through the wireless communication module, and calling the dual channels for cold chain logistics temperature control analysis of the target cold chain goods through the monitoring and processing center, the dual channels for cold chain logistics temperature control analysis including a short-term temperature control analysis channel and a long-term temperature control analysis channel; a temperature control analysis channel matching module for obtaining the temperature comparison result of the compartment temperature data with a preset safe temperature threshold, matching the temperature comparison result with the dual channels for cold chain logistics temperature control analysis to determine the target temperature control analysis channel; and a temperature control strategy parameter determination module for performing temperature control analysis on the vehicle location information and compartment temperature data based on the target temperature control analysis channel, determining temperature control adjustment strategy parameters, and performing cold chain logistics temperature control monitoring through the temperature control adjustment strategy parameters.

[0015] This application proposes a GPS-linked cold chain logistics temperature control monitoring method and system. An onboard terminal is installed on the cold chain transport vehicle to collect real-time vehicle location information and compartment temperature data. This data is encrypted and uploaded to a monitoring and processing center, which then calls upon dual channels for cold chain logistics temperature control analysis of the target cold chain goods. The system compares the temperature with a preset safe temperature threshold and matches the target temperature control analysis channel. Temperature control analysis is performed to determine temperature control adjustment strategy parameters and to monitor cold chain logistics temperature control. This addresses the technical problems of existing technologies, such as lagging temperature control monitoring, lack of deep integration with vehicle location and transportation status analysis, inability to distinguish the specific causes of temperature anomalies, and lack of precision and predictability in control strategies. It achieves real-time, accurate, and intelligent identification and monitoring of cold chain transportation temperature control anomalies, improving the reliability, safety, and efficiency of cold chain logistics. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a schematic diagram of a GPS-linked cold chain logistics temperature control monitoring method provided in an embodiment of this application.

[0018] Figure 2 This is a schematic diagram of a GPS-linked cold chain logistics temperature control monitoring system provided in an embodiment of this application.

[0019] Figure labeling: Data acquisition module 10, temperature control analysis channel calling module 20, temperature control analysis channel matching module 30, temperature control strategy parameter determination module 40. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides a GPS-linked method for temperature control monitoring in cold chain logistics, such as... Figure 1 As shown, the method includes: Step S100: Install a vehicle-mounted terminal on the cold chain logistics transport vehicle. The vehicle-mounted terminal integrates a GPS positioning module, a temperature sensor, and a wireless communication module. The GPS positioning module and the temperature sensor collect vehicle location information and compartment temperature data in real time.

[0024] Preferably, a multi-functional vehicle-mounted terminal is installed inside the cab or cargo compartment of the cold chain logistics transport vehicle. The vehicle-mounted terminal integrates a GPS positioning module, a temperature sensor, and a wireless communication module. The GPS positioning module is used to determine the vehicle's current latitude and longitude coordinates, speed, direction, and timestamp in real time. The temperature sensors are arranged in different locations inside the cargo compartment to comprehensively and accurately monitor the real-time temperature of various areas within the cargo compartment. The wireless communication module is typically a 5G cellular network communication module, used to establish a data link between the vehicle-mounted terminal and a remote monitoring and processing center, sending out the collected data and receiving instructions from the center. The vehicle's location information and cargo compartment temperature data are collected in real time through the GPS positioning module and the temperature sensor, and then transmitted in real time or near real time to a remote cloud server or monitoring center via the encrypted mobile network through the wireless communication module.

[0025] Step S200: The vehicle location information and compartment temperature data are encrypted and uploaded to the monitoring and processing center through the wireless communication module. The monitoring and processing center then calls the dual-channel cold chain logistics temperature control analysis of the target cold chain goods, which includes a short-term temperature control analysis channel and a long-term temperature control analysis channel.

[0026] Preferably, vehicle location information and compartment temperature data are encrypted using encryption protocols such as SSL / TLS to prevent sensitive information such as vehicle location, cargo type, and temperature from being stolen or tampered with during transmission, thus ensuring transportation safety. Then, an internet connection is established through a wireless communication module to upload the vehicle location information and compartment temperature data to a monitoring and processing center, which may be a monitoring platform deployed on a cloud server. This platform is used to receive, store, decrypt, process, and analyze all data collected and uploaded by cold chain transport vehicles, and index the specific information of the target cold chain cargo currently being transported by the vehicle. Then, the monitoring and processing center invokes the dual channels for cold chain logistics temperature control analysis of the target cold chain goods, including a short-term temperature control analysis channel and a long-term temperature control analysis channel. Specifically, the short-term temperature control analysis channel is a high-frequency response unit targeting instantaneous or recent conditions, typically based on a PID controller. It takes the real-time deviation between the current temperature and a preset safety threshold as input and calculates and outputs control commands to correct current temperature anomalies, such as increasing the cooling power by 25% within 5 seconds. The long-term temperature control analysis channel is a predictive unit targeting time-series data trends, typically based on time series analysis or machine learning models. It takes historical location, temperature sequence, and future planned routes as input and predictively calculates and outputs strategy parameters to optimize the overall transportation process. For example, based on road conditions and temperature forecasts 200 kilometers ahead, it suggests adjusting the base temperature from -22℃ to -21.5℃ to save energy. The dual channels for cold chain logistics temperature control analysis of the target cold chain goods are not invoked simultaneously but are placed in standby mode. Subsequently, based on the comparison results of real-time temperature data and preset thresholds, the matching target channel at the current moment is dynamically determined to generate the final control strategy.

[0027] Furthermore, step S200 also includes step S210, obtaining a cold chain logistics cargo database through the monitoring and processing center; step S220, obtaining cold chain cargo attribute elements, including cargo type, biochemical change characteristics, microbial inhibition requirements, and storage requirements; step S230, classifying and analyzing the temperature control of each cold chain cargo in the cold chain logistics cargo database according to the cold chain cargo attribute elements to obtain a multi-cargo temperature control analysis dual-channel library; step S240, matching and calling the target cold chain cargo's attribute elements with the multi-cargo temperature control analysis dual-channel library to obtain a cold chain logistics temperature control analysis dual channel.

[0028] Preferably, the monitoring and processing center reads a cold chain logistics cargo database from a connected central database, which stores historical data, experimental data, and expert experience. This database contains structured data on various cold chain cargoes. Then, it extracts the target cold chain cargo attribute elements, including cargo type, biochemical characteristics, microbial inhibition requirements, and storage requirements. Cargo types may include frozen fish, ice cream, vaccines, fresh fruits and vegetables, and dairy products. Biochemical characteristics refer to the sensitivity of the chemical and biological reaction rates occurring inside the cargo to temperature, such as the respiration of fruits and vegetables, protein denaturation in meat, and enzyme activity. Microbial inhibition requirements refer to the temperature conditions required to inhibit the growth and reproduction of specific microorganisms; for example, Listeria grows slowly below 4°C, and Salmonella stops growing below 7°C. Storage requirements include the precise temperature range and humidity range required for the cargo, as well as whether temperature fluctuations are permissible, such as the fact that some pharmaceuticals are very sensitive to short-term temperature deviations.

[0029] Preferably, K-Means clustering or DBSCAN clustering is used to classify and analyze the temperature control of each cold chain cargo in the cold chain logistics cargo database according to the attribute elements of the cold chain cargo. The large number of cargoes in the database are divided into several cargo clusters or categories with similar temperature control requirements. Based on the historical data of cold chain cargo transportation, analysis units are pre-trained for each cargo cluster, including a short-term temperature control analysis channel for PID control and a long-term temperature control analysis channel for prediction based on a time series prediction model. The set of analysis units for all different cargo clusters is used to obtain a multi-cargo temperature control analysis dual-channel library. Finally, the attribute elements of the target cold chain cargo are matched and called against the multi-cargo temperature control analysis dual-channel library. When the real-time data of the cold chain cargo transportation vehicle is uploaded to the monitoring and processing center, the type and temperature requirements of the target cold chain cargo are identified. The attribute elements are used as query conditions to traverse and match in the multi-cargo temperature control analysis dual-channel library, filter the matching cold chain logistics temperature control analysis dual channels, and load them into memory to process the real-time data stream of the target cold chain cargo transportation vehicle, thereby improving the accuracy and energy efficiency of cold chain logistics transportation temperature control.

[0030] Furthermore, step S230 also includes step S231, classifying and identifying each cold chain cargo in the cold chain logistics cargo database according to the cold chain cargo attribute elements to obtain a cold chain logistics cargo attribute element parameter set; step S232, clustering and integrating the cold chain logistics cargo database based on the cold chain logistics cargo attribute element parameter set to obtain a cold chain logistics cargo cluster set; step S233, performing data mining and temperature control analysis on the cold chain logistics cargo cluster set to obtain a multi-cargo short-term temperature control analysis channel set and a multi-cargo long-term temperature control analysis channel set; step S234, combining the multi-cargo short-term temperature control analysis channel set and the multi-cargo long-term temperature control analysis channel set in parallel to obtain the multi-cargo temperature control analysis dual-channel library.

[0031] Preferably, for each cold chain cargo in the cold chain logistics cargo database, it is classified, labeled, and quantified according to its cold chain cargo attribute elements to obtain a cold chain logistics cargo attribute element parameter set, which is a structured vector set containing multiple parameters. Unsupervised clustering algorithms such as K-Means and hierarchical clustering are used to cluster and integrate the cold chain logistics cargo database based on the cold chain logistics cargo attribute element parameter set. That is, the similarity of different goods in the attribute space is calculated, and goods with similar attributes are automatically grouped into the same cluster, thereby obtaining a cold chain logistics cargo cluster set. Then, data mining is performed on each cargo cluster in the cold chain logistics cargo cluster set to extract high-frequency temperature readings and corresponding refrigeration equipment control commands from its historical data. Supervised learning is then used to train a control response unit based on a PID controller, establishing a short-term temperature control analysis channel for each cargo cluster, resulting in a multi-cargo short-term temperature control analysis channel set. Temperature control analysis is then performed on each cargo cluster in the cold chain logistics cargo cluster set, extracting its historical data over a long period, including temperature time series, geographical location series, external weather, and number of door openings and closings. This data is then trained based on time series prediction models such as ARIMA and LSTM networks to establish a long-term temperature control analysis channel for each cargo cluster, used to predict temperature trends over a future period, thus determining a multi-cargo long-term temperature control analysis channel set. Finally, the multi-cargo short-term temperature control analysis channel set and the multi-cargo long-term temperature control analysis channel set are combined in parallel to obtain a multi-cargo temperature control analysis dual-channel library, thereby realizing the automation and refined customization of cold chain logistics transportation temperature control strategies.

[0032] Furthermore, step S233 also includes step A, performing temperature control data mining based on the cold chain logistics cargo cluster set to obtain a historical temperature control dataset for the cold chain logistics cargo cluster; step B, constructing a cold chain logistics temperature control effect index set, and performing safe temperature analysis on the historical temperature control dataset for the cold chain logistics cargo cluster according to the cold chain logistics temperature control effect index set to determine a safe temperature threshold set for the cold chain logistics cargo cluster; step C, classifying the historical temperature control dataset for the cold chain logistics cargo cluster according to the safe temperature threshold set for the cold chain logistics cargo cluster to obtain a short-term cold chain logistics cargo cluster temperature control dataset and a long-term cold chain logistics cargo cluster temperature control dataset; and step D, performing temperature control analysis based on the short-term and long-term cold chain logistics cargo cluster temperature control datasets to obtain a set of short-term and long-term temperature control analysis channels for multiple goods.

[0033] Preferably, temperature control data mining is performed on each cargo cluster in the cold chain logistics cargo cluster set. This involves extracting historical temperature control records of all cargo belonging to that cluster from historical data. These records may include timestamps, temperature values ​​from multiple temperature sensors inside the vehicle, vehicle position / speed, external ambient temperature, refrigeration system status such as compressor power, fan speed, and valve opening, as well as cold chain transport cargo status such as transport time and number of door openings. This results in a historical temperature control dataset for the cold chain logistics cargo cluster.

[0034] Preferably, a set of cold chain logistics temperature control performance indicators is constructed, which may include temperature deviation, maximum temperature fluctuation range, duration of exceeding limits, and cargo loss rate. Temperature deviation is the degree to which historical temperatures deviate from the ideal set value; maximum fluctuation range is the difference between the highest and lowest temperatures in historical data; duration of exceeding limits is the total time the temperature exceeds the safety line; and cargo loss rate is the historical cargo loss situation corresponding to the temperature control records. The set of cold chain logistics temperature control performance indicators is used to perform safe temperature analysis on the historical temperature control dataset of cold chain logistics cargo clusters. This involves reverse analysis of the historical temperature control dataset of cold chain logistics cargo clusters to fit a dynamic safe temperature threshold that ensures optimal transportation performance, and then outputting a set of safe temperature thresholds for cold chain logistics cargo clusters. For example, for frozen meat clusters, when the external temperature is above 30℃, the upper limit of the safe threshold should be -17.5℃; when the external temperature is below 0℃, the upper limit of the safe threshold can be -18.5℃.

[0035] Preferably, the safe temperature threshold set for cold chain logistics cargo clusters is used as the judgment standard to classify the historical temperature control dataset of cold chain logistics cargo clusters. Historical data where all temperature records exceeded the then-current safe threshold are selected as the short-term cold chain logistics cargo cluster temperature control dataset, containing various abnormal situations and the corrective instructions taken at that time. Historical data where all temperature records remained within the safe threshold are selected as the long-term cold chain logistics cargo cluster temperature control dataset, representing the normal transportation process. Then, temperature control analysis is performed based on both the short-term and long-term cold chain logistics cargo cluster temperature control datasets. Specifically, temperature deviations in abnormal data are used as input features, and corrective instructions are used as training labels. A PID controller is trained to generate a corresponding abnormal response controller for each cargo cluster, which outputs a control strategy. This means that according to different temperature exceedances, the optimal control measures are taken, thus forming a multi-cargo short-term temperature control analysis channel set. A Long Short-Term Memory (LSTM) network is trained to predict temperature trends over a future period using historical continuous temperature, location, and environmental data, generating a high-precision temperature predictor for each cargo cluster, thus forming a multi-cargo long-term temperature control analysis channel set.

[0036] Furthermore, step D also includes step D10, determining the cargo cluster compartment temperature dataset and the cargo cluster temperature control adjustment dataset based on the short-term cold chain logistics cargo cluster temperature control dataset; step D20, obtaining the cargo cluster temperature deviation dataset between the cargo cluster compartment temperature dataset and the cold chain logistics cargo cluster safe temperature threshold set; step D30, performing temperature control training and fitting based on the cargo cluster temperature deviation dataset and the cargo cluster temperature control adjustment dataset to obtain a set of PID temperature controllers, and using the set of PID temperature controllers as a set of multi-cargo short-term temperature control analysis channels; step D40, performing temperature control analysis based on the long-term cold chain logistics cargo cluster temperature control dataset to construct a set of multi-cargo long-term temperature control analysis channels.

[0037] Preferably, a cargo cluster compartment temperature dataset and a cargo cluster temperature control adjustment dataset are extracted from the short-term cold chain logistics cargo cluster temperature control dataset. The cargo cluster compartment temperature dataset includes the actual compartment temperature values ​​measured by sensors when an anomaly occurs, while the cargo cluster temperature control adjustment dataset includes the actual control commands executed by the refrigeration system corresponding to the abnormal compartment temperature, such as adjustments to compressor power percentage, valve opening, and fan speed. Then, the difference between the actual temperature of each cargo cluster in the cargo cluster compartment temperature dataset and the corresponding dynamic safety threshold in the cold chain logistics cargo cluster safety temperature threshold set is calculated, outputting a cargo cluster temperature deviation dataset. Next, temperature control training and fitting are performed based on the cargo cluster temperature deviation dataset and the cargo cluster temperature control adjustment dataset. Specifically, using the cargo cluster temperature deviation data as input features and the cargo cluster temperature control adjustment data as training labels, the proportional-integral-derivative parameters of the PID controller model are optimized and fitted using reinforcement learning to determine the optimal PID control parameters that enable the controller's output control commands. This yields a set of PID temperature controllers, which is then used as a set of channels for multi-cargo short-term temperature control analysis. Finally, temperature control analysis is performed based on the long-term cold chain logistics cargo cluster temperature control dataset. Specifically, a temperature predictor is built based on the time series prediction model to predict future temperature trends when the temperature is normal. Then, a temperature trend prediction unit is trained for each cargo cluster and used as a long-term temperature control analysis channel, ultimately obtaining a set of long-term temperature control analysis channels for multiple cargoes.

[0038] Furthermore, step D40 also includes step D41, arranging the long-term cold chain logistics cargo cluster temperature control dataset in time sequence to obtain a long-term cold chain cargo cluster temperature control time sequence dataset; step D42, determining the cargo cluster time sequence temperature dataset, cargo cluster time sequence location dataset, cargo cluster remaining distance dataset, and cargo cluster temperature control adjustment dataset based on the long-term cold chain cargo cluster temperature control time sequence dataset; step D43, performing temperature trend prediction training based on the cargo cluster time sequence temperature dataset, cargo cluster time sequence location dataset, and cargo cluster remaining distance dataset to generate a cargo cluster temperature trend predictor set; step D44, performing temperature control analysis based on the cargo cluster temperature trend predictor set and the cargo cluster temperature control adjustment dataset to construct a multi-cargo long-term temperature control analysis channel set.

[0039] Preferably, the normal transportation data in the long-term cold chain logistics cargo cluster temperature control dataset is aligned and sorted according to timestamps to form a long-term cold chain cargo cluster temperature control time-series dataset. Then, four types of feature datasets are extracted from the long-term cold chain cargo cluster temperature control time-series dataset, including cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, cargo cluster remaining distance dataset, and cargo cluster temperature control adjustment dataset. Among them, the cargo cluster time-series temperature dataset refers to the continuous historical readings of the compartment temperature within a past time window; the cargo cluster time-series location dataset refers to the continuous historical GPS coordinates that perfectly match the temperature reading timestamps, used to infer the impact of local weather, altitude, and road conditions on temperature; the cargo cluster remaining distance dataset refers to the remaining mileage of the vehicle from the destination at each historical time point, used to determine the transportation stage; and the cargo cluster temperature control adjustment dataset refers to the control commands actually executed by the refrigeration system within a past period.

[0040] Preferably, the data from the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, and cargo cluster remaining distance dataset are concatenated into a feature vector as input features. With future temperature as the prediction target, a prediction model is constructed based on a Long Short-Term Memory (LSTM) network and trained using supervised learning. For each cargo cluster, a predictor is trained that can accurately predict future temperatures by integrating historical temperature, location, and travel information, forming a cargo cluster temperature trend predictor set. Finally, temperature control analysis is performed based on the cargo cluster temperature trend predictor set and the cargo cluster temperature control adjustment dataset. The goal is to determine the control strategy to ensure that the predicted future temperature remains as stable as possible within a safe range while minimizing the control energy expenditure. This constructs a model predictive control framework, and the cargo cluster temperature trend predictor simulates the impact of different control commands on future temperatures. An optimization algorithm searches for sequential control commands, ultimately outputting a set of long-term temperature control analysis channels for multiple cargo clusters. For each cargo cluster, the corresponding long-term temperature control analysis channel can receive current time-series data and predict future temperatures, outputting optimal, forward-looking temperature control adjustment strategy parameters.

[0041] Furthermore, step D44 also includes step D441, obtaining a cargo cluster temperature trend prediction dataset based on the output data of the cargo cluster temperature trend predictor set; step D442, using a deep neural network structure to perform correlation temperature control training and iterative feedback optimization on the cargo cluster temperature trend prediction dataset and the cargo cluster temperature control adjustment dataset to obtain a cargo cluster temperature control analyzer set; step D443, connecting and merging the cargo cluster temperature trend predictor set and the cargo cluster temperature control analyzer set to construct the multi-cargo long-term temperature control analysis channel set.

[0042] Preferably, the temperature of each cargo cluster is predicted over a future period using a temperature trend predictor, resulting in a cargo cluster temperature trend prediction dataset, including multiple predicted temperatures. Then, a deep neural network structure is used to perform correlation temperature control training and iterative feedback optimization on the cargo cluster temperature trend prediction dataset and the cargo cluster temperature control adjustment dataset. Specifically, the cargo cluster temperature trend prediction data and the cargo cluster temperature control adjustment data are concatenated into a comprehensive feature vector as input features. A deep neural network is used to learn the mapping relationship between future predicted temperatures and control commands, ensuring that overall energy consumption is minimized and equipment operation is smoothest while ensuring temperature safety. The iterative feedback optimization process is similar to a strong... In the learning process, the control strategy output by the deep neural network is applied to the simulated environment. Ultimately, temperature and energy consumption are used as feedback information to calculate the loss function and backpropagate, iteratively optimizing the weight parameters of the deep neural network. This process is repeated until the deep neural network makes the optimal decision, thereby outputting multiple cargo cluster temperature control analyzers to form a cargo cluster temperature control analyzer set. The cargo cluster temperature trend predictors in the cargo cluster temperature trend predictor set are then connected and merged with the cargo cluster temperature control analyzers in the cargo cluster temperature control analyzer set to form multiple complete long-term cargo temperature control analysis channels, thus forming a multi-cargo long-term temperature control analysis channel set, thereby ensuring the realization of intelligent temperature control.

[0043] Step S300: Obtain the temperature comparison result between the compartment temperature data and the preset safe temperature threshold, and match the temperature comparison result with the dual channels of cold chain logistics temperature control analysis to determine the target temperature control analysis channel.

[0044] Step S300 further includes step S310, when the temperature comparison result is that the temperature data of the carriage exceeds the preset safe temperature threshold, activating the short-term temperature control analysis channel as the target temperature control analysis channel; step S320, if the temperature comparison result is that the temperature data of the carriage is within the preset safe temperature threshold, starting the long-term temperature control analysis channel as the target temperature control analysis channel.

[0045] Preferably, the temperature data of the cargo compartment is compared with a preset safe temperature threshold to obtain the temperature comparison result. The preset safe temperature threshold is set based on the biochemical characteristics of the goods themselves and historical cold chain transportation data. When the temperature comparison result shows that the temperature data of the cargo compartment exceeds the preset safe temperature threshold, the short-term temperature control analysis channel is activated as the target temperature control analysis channel. That is, the PID controller corresponding to the cargo cluster is called, and a strong and rapid correction command is calculated based on the deviation between the current temperature and the threshold, and directly sent to the refrigeration equipment. If the temperature comparison result shows that the temperature data of the cargo compartment is within the preset safe temperature threshold, the long-term temperature control analysis channel is activated as the target temperature control analysis channel. That is, a precise and forward-looking control command is calculated based on the predicted future temperature trend to effectively prevent temperature fluctuations. This ensures that it can respond quickly to emergencies and protect the safety of goods, while also achieving refined management and energy saving during normal temperature periods.

[0046] Step S400: Based on the target temperature control analysis channel, perform temperature control analysis on the vehicle location information and compartment temperature data to determine temperature control adjustment strategy parameters, and use the temperature control adjustment strategy parameters to monitor the temperature control of cold chain logistics.

[0047] Preferably, vehicle location information and passenger compartment temperature data are input into the target temperature control analysis channel for temperature control analysis. If the short-term temperature control analysis channel is activated, the deviation between the current temperature and the safe target temperature is calculated, and then a control strategy is calculated based on PID parameters. If the long-term temperature control analysis channel is activated, the vehicle location information, historical temperature data, and temperature predictor are used to predict the temperature trend over a future period. Different control strategies are simulated through optimization algorithms to determine the optimal solution that simultaneously satisfies the objectives of temperature stability and minimum energy consumption. The temperature control adjustment strategy parameters are then determined, which may include specific control commands, such as setting the compressor power to 75% of the set value, adjusting the electronic expansion valve opening to 50%, and adjusting the condenser fan speed to... The 2000 series directly corresponds to the control interface of the refrigeration system actuator. Finally, the temperature control of cold chain logistics is monitored through temperature control adjustment strategy parameters. That is, the monitoring and processing center sends the temperature control adjustment strategy parameters to the vehicle terminal of the transport vehicle through the wireless communication module. The vehicle terminal receives the instruction and converts the instruction into a signal that the refrigeration unit controller can recognize through the controller LAN inside the vehicle. The refrigeration unit receives the signal and drives the corresponding actuator to act, accurately adjusting the power, opening degree or speed to the target required by the instruction. At the same time, the temperature of the compartment is measured again and uploaded to the monitoring and processing center, thus completing the closed-loop control. This enables real-time, accurate and intelligent identification and monitoring of temperature control anomalies in cold chain transportation, improving the reliability, safety and efficiency of cold chain logistics.

[0048] Furthermore, step S400 also includes step S410, performing cold air circulation impact analysis based on the arrangement and stacking method of the target cold chain goods to obtain the cold air diffusion impact coefficient of the goods; step S420, determining the temperature rise impact factor of the goods based on the cold air diffusion impact coefficient of the goods, and correcting the temperature control adjustment strategy parameters based on the temperature rise impact factor of the goods.

[0049] Preferably, the cold air circulation impact analysis is performed based on the arrangement and stacking method of the target cold chain goods. This involves modeling and analyzing the airflow and heat exchange within the vehicle compartment. Specifically, the arrangement and stacking method of the target cold chain goods is used as input, including the geometry of the goods, stacking density, and distances between the goods and the compartment walls, ceiling, and floor. A fluid dynamics model is used to analyze the impact of cold air circulation, including simulating the path of cold air, dead zones, eddies, and heat exchange efficiency under different stacking methods. The resulting cold air diffusion impact coefficient is used to evaluate the uniformity and efficiency of cold air distribution under the current stacking method. A cold air diffusion impact coefficient close to 1 indicates an ideal stacking method. Good cold air circulation with no serious dead zones; an air diffusion influence coefficient of less than 1 indicates that the stacking method hinders air circulation, resulting in cooling dead zones and low efficiency. Then, based on thermodynamic principles, the influence factor of cargo temperature rise is derived through the cold air diffusion influence coefficient. That is, the worse the air circulation, the lower the heat exchange efficiency, and the more difficult it is to remove the breathing heat generated by the cargo itself or the heat transferred from the outside. The core temperature of the cargo will rise faster and at a greater rate than the temperature at the sensor reading point. Finally, the influence factor of cargo temperature rise is used to correct the temperature control adjustment strategy parameters, adjust the control behavior in advance, achieve proactive compensation, and greatly improve the safety and reliability of temperature control in cold chain transportation logistics.

[0050] In the above text, refer to Figure 1 This paper describes in detail a GPS-linked cold chain logistics temperature control monitoring method according to an embodiment of the present invention. Next, we will refer to... Figure 2 This invention describes a GPS-linked cold chain logistics temperature control monitoring system according to an embodiment of the present invention.

[0051] According to an embodiment of the present invention, a GPS-linked cold chain logistics temperature control monitoring system is used to solve the technical problems existing in the prior art, such as lagging temperature control monitoring, lack of deep integration and analysis with vehicle location and transportation status, inability to distinguish the specific causes of temperature anomalies, and lack of precision and predictability in control strategies. It achieves the technical effect of real-time, accurate, and intelligent identification and monitoring of temperature control anomalies in cold chain transportation, thereby improving the reliability, safety, and efficiency of cold chain logistics. Figure 2 As shown, a GPS-linked cold chain logistics temperature control monitoring system includes: a data acquisition module 10, a temperature control analysis channel calling module 20, a temperature control analysis channel matching module 30, and a temperature control strategy parameter determination module 40.

[0052] The data acquisition module 10 is used to install an on-board terminal on the cold chain logistics transport vehicle. The on-board terminal integrates a GPS positioning module, a temperature sensor, and a wireless communication module. It collects vehicle location information and compartment temperature data in real time through the GPS positioning module and the temperature sensor. The temperature control analysis channel calling module 20 is used to encrypt and upload the vehicle location information and compartment temperature data to the monitoring and processing center through the wireless communication module. The monitoring and processing center calls the dual channels for cold chain logistics temperature control analysis of the target cold chain goods. The dual channels for cold chain logistics temperature control analysis include a short-term temperature control analysis channel and a long-term temperature control analysis channel. The temperature control analysis channel matching module 30 is used to obtain the temperature comparison result between the compartment temperature data and the preset safe temperature threshold, and match the temperature comparison result with the dual channels for cold chain logistics temperature control analysis to determine the target temperature control analysis channel. The temperature control strategy parameter determination module 40 is used to perform temperature control analysis on the vehicle location information and compartment temperature data based on the target temperature control analysis channel, determine the temperature control adjustment strategy parameters, and perform cold chain logistics temperature control supervision through the temperature control adjustment strategy parameters.

[0053] The specific configuration of the temperature control analysis channel invocation module 20 will be described in detail below. The temperature control analysis channel invocation module 20 further includes: obtaining a cold chain logistics cargo database through the monitoring and processing center; obtaining cold chain cargo attribute elements, including cargo type, biochemical change characteristics, microbial inhibition requirements, and storage requirements; classifying and analyzing the temperature control of each cold chain cargo in the cold chain logistics cargo database according to the cold chain cargo attribute elements to obtain a multi-cargo temperature control analysis dual-channel library; and matching and invoking the target cold chain cargo's attribute elements with the multi-cargo temperature control analysis dual-channel library to obtain a cold chain logistics temperature control analysis dual channel.

[0054] The specific configuration of the temperature control analysis channel calling module 20 will be described in detail below. The temperature control analysis channel calling module 20 further includes: classifying and identifying each cold chain cargo in the cold chain logistics cargo database according to the cold chain cargo attribute elements, obtaining a cold chain logistics cargo attribute element parameter set; clustering and integrating the cold chain logistics cargo database based on the cold chain logistics cargo attribute element parameter set, obtaining a cold chain logistics cargo cluster set; performing data mining and temperature control analysis on the cold chain logistics cargo cluster set respectively, obtaining a multi-cargo short-term temperature control analysis channel set and a multi-cargo long-term temperature control analysis channel set; and combining the multi-cargo short-term temperature control analysis channel set and the multi-cargo long-term temperature control analysis channel set in parallel to obtain the multi-cargo temperature control analysis dual-channel library.

[0055] The specific configuration of the temperature control analysis channel calling module 20 will be described in detail below. The temperature control analysis channel calling module 20 further includes: performing temperature control data mining based on the cold chain logistics cargo cluster set to obtain a historical temperature control dataset for the cold chain logistics cargo cluster; constructing a cold chain logistics temperature control effect index set; performing safe temperature analysis on the historical temperature control dataset of the cold chain logistics cargo cluster according to the cold chain logistics temperature control effect index set to determine a safe temperature threshold set for the cold chain logistics cargo cluster; classifying the historical temperature control dataset of the cold chain logistics cargo cluster according to the safe temperature threshold set for the cold chain logistics cargo cluster to obtain a short-term cold chain logistics cargo cluster temperature control dataset and a long-term cold chain logistics cargo cluster temperature control dataset; and performing temperature control analysis based on the short-term and long-term cold chain logistics cargo cluster temperature control datasets to obtain a multi-cargo short-term temperature control analysis channel set and a multi-cargo long-term temperature control analysis channel set.

[0056] The specific configuration of the temperature control analysis channel invocation module 20 will be described in detail below. The temperature control analysis channel invocation module 20 further includes: determining a cargo cluster compartment temperature dataset and a cargo cluster temperature control adjustment dataset based on the short-term cold chain logistics cargo cluster temperature control dataset; obtaining a cargo cluster temperature deviation dataset between the cargo cluster compartment temperature dataset and the cold chain logistics cargo cluster safe temperature threshold set; performing temperature control training and fitting based on the cargo cluster temperature deviation dataset and the cargo cluster temperature control adjustment dataset to obtain a set of PID temperature controllers, and using the set of PID temperature controllers as a multi-cargo short-term temperature control analysis channel set; and performing temperature control analysis based on the long-term cold chain logistics cargo cluster temperature control dataset to construct a multi-cargo long-term temperature control analysis channel set.

[0057] The specific configuration of the temperature control analysis channel calling module 20 will be described in detail below. The temperature control analysis channel calling module 20 further includes: arranging the long-term cold chain logistics cargo cluster temperature control dataset in chronological order to obtain a long-term cold chain cargo cluster temperature control time-series dataset; determining the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, cargo cluster remaining distance dataset, and cargo cluster temperature control adjustment dataset based on the long-term cold chain cargo cluster temperature control time-series dataset; performing temperature trend prediction training based on the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, and cargo cluster remaining distance dataset to generate a cargo cluster temperature trend predictor set; and performing temperature control analysis based on the cargo cluster temperature trend predictor set and the cargo cluster temperature control adjustment dataset to construct a multi-cargo long-term temperature control analysis channel set.

[0058] The specific configuration of the temperature control analysis channel invocation module 20 will be described in detail below. The temperature control analysis channel invocation module 20 further includes: obtaining a cargo cluster temperature trend prediction dataset based on the output data of the cargo cluster temperature trend predictor set; performing correlated temperature control training and iterative feedback optimization on the cargo cluster temperature trend prediction dataset and the cargo cluster temperature control adjustment dataset using a deep neural network structure to obtain a cargo cluster temperature control analyzer set; and connecting and merging the cargo cluster temperature trend predictor set and the cargo cluster temperature control analyzer set to construct the multi-cargo long-term temperature control analysis channel set.

[0059] The specific configuration of the temperature control analysis channel matching module 30 will be described in detail below. The temperature control analysis channel matching module 30 further includes: when the temperature comparison result indicates that the compartment temperature data exceeds a preset safe temperature threshold, activating the short-term temperature control analysis channel as the target temperature control analysis channel; if the temperature comparison result indicates that the compartment temperature data is within the preset safe temperature threshold, activating the long-term temperature control analysis channel as the target temperature control analysis channel.

[0060] The specific configuration of the temperature control strategy parameter determination module 40 will be described in detail below. The temperature control strategy parameter determination module 40 further includes: performing a cold air circulation impact analysis based on the arrangement and stacking method of the target cold chain goods to obtain a cold air diffusion impact coefficient; determining a goods temperature rise impact factor based on the goods cold air diffusion impact coefficient; and correcting the temperature control adjustment strategy parameters based on the goods temperature rise impact factor.

[0061] The GPS-linked cold chain logistics temperature control monitoring system provided in this embodiment of the invention can execute the GPS-linked cold chain logistics temperature control monitoring method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0062] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0063] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, 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 application should be included within the scope of protection of this application.

Claims

1. A GPS-linked method for temperature control monitoring in cold chain logistics, characterized in that, The method includes: A vehicle-mounted terminal is installed on a cold chain logistics transport vehicle. The vehicle-mounted terminal integrates a GPS positioning module, a temperature sensor, and a wireless communication module. The GPS positioning module and the temperature sensor collect vehicle location information and compartment temperature data in real time. The vehicle location information and compartment temperature data are encrypted and uploaded to the monitoring and processing center through the wireless communication module. The monitoring and processing center then calls the dual channels for cold chain logistics temperature control analysis of the target cold chain goods, which include a short-term temperature control analysis channel and a long-term temperature control analysis channel. The temperature comparison results between the temperature data of the carriage and the preset safe temperature threshold are obtained, and the temperature comparison results are matched with the dual channels of the cold chain logistics temperature control analysis to determine the target temperature control analysis channel. Based on the target temperature control analysis channel, the vehicle location information and compartment temperature data are analyzed to determine the temperature control adjustment strategy parameters, and the temperature control of cold chain logistics is monitored through the temperature control adjustment strategy parameters.

2. The GPS-linked cold chain logistics temperature control monitoring method as described in claim 1, characterized in that, The process of calling the dual channels for cold chain logistics temperature control analysis through the monitoring and processing center includes: The monitoring and processing center obtains a database of cold chain logistics goods. Acquire cold chain cargo attribute elements, including cargo type, biochemical change characteristics, microbial inhibition requirements, and storage requirements; Based on the cold chain cargo attribute elements, the cold chain cargo in the cold chain logistics cargo database is classified and its temperature control is analyzed to obtain a dual-channel database for multi-cargo temperature control analysis. Based on the attribute elements of the target cold chain goods, the dual-channel temperature control analysis library for multiple goods is matched and called to obtain the dual-channel temperature control analysis for cold chain logistics.

3. The GPS-linked cold chain logistics temperature control monitoring method as described in claim 2, characterized in that, The obtained multi-cargo temperature-controlled analysis dual-channel warehouse includes: The cold chain goods in the cold chain logistics goods database are classified and identified according to the cold chain goods attribute elements to obtain the cold chain logistics goods attribute element parameter set. Based on the set of attribute elements of cold chain logistics goods, the cold chain logistics goods database is clustered and integrated to obtain a set of cold chain logistics goods clusters. Data mining and temperature control analysis were performed on the cold chain logistics cargo clusters to obtain a set of short-term temperature control analysis channels for multiple cargoes and a set of long-term temperature control analysis channels for multiple cargoes. The multi-cargo short-term temperature control analysis channel set and the multi-cargo long-term temperature control analysis channel set are combined in parallel to obtain the multi-cargo temperature control analysis dual-channel library.

4. The GPS-linked cold chain logistics temperature control monitoring method as described in claim 3, characterized in that, The acquisition of the multi-cargo short-term temperature control analysis channel set and the multi-cargo long-term temperature control analysis channel set includes: Temperature control data mining was performed on the cold chain logistics cargo cluster set to obtain historical temperature control datasets for the cold chain logistics cargo cluster set. Construct a set of cold chain logistics temperature control effect indicators, and perform safe temperature analysis on the historical temperature control dataset of the cold chain logistics cargo cluster according to the set of cold chain logistics temperature control effect indicators to determine the set of safe temperature thresholds for the cold chain logistics cargo cluster. The historical temperature control dataset of cold chain logistics cargo clusters is classified according to the set of safe temperature thresholds for cold chain logistics cargo clusters to obtain short-term cold chain logistics cargo cluster temperature control dataset and long-term cold chain logistics cargo cluster temperature control dataset. Temperature control analysis is performed based on the short-term cold chain logistics cargo cluster temperature control dataset and the long-term cold chain logistics cargo cluster temperature control dataset to obtain a set of short-term temperature control analysis channels for multiple cargoes and a set of long-term temperature control analysis channels for multiple cargoes.

5. A cold chain logistics temperature control monitoring method based on GPS linkage as described in claim 4, characterized in that, The temperature control analysis based on the short-term cold chain logistics cargo cluster temperature control dataset and the long-term cold chain logistics cargo cluster temperature control dataset yields a set of short-term temperature control analysis channels for multiple cargoes and a set of long-term temperature control analysis channels for multiple cargoes, including: Based on the aforementioned short-term cold chain logistics cargo cluster temperature control dataset, determine the cargo cluster compartment temperature dataset and the cargo cluster temperature control adjustment dataset; Obtain the cargo cluster temperature deviation dataset between the cargo cluster compartment temperature dataset and the cold chain logistics cargo cluster safe temperature threshold dataset; Based on the cargo cluster temperature deviation dataset and the cargo cluster temperature control adjustment dataset, temperature control training and fitting are performed to obtain a set of PID temperature controllers, and the set of PID temperature controllers is used as a set of multi-cargo short-term temperature control analysis channels. Temperature control analysis is performed based on the long-term cold chain logistics cargo cluster temperature control dataset to construct a set of long-term temperature control analysis channels for multiple cargoes.

6. The GPS-linked cold chain logistics temperature control monitoring method as described in claim 5, characterized in that, The construction of a multi-cargo long-term temperature control analysis channel set includes: Arrange the long-term cold chain logistics cargo cluster temperature control dataset in chronological order to obtain the long-term cold chain cargo cluster temperature control time-series dataset; Based on the long-term cold chain cargo cluster temperature control time-series dataset, determine the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, cargo cluster remaining distance dataset, and cargo cluster temperature control adjustment dataset; Based on the cargo cluster time-series temperature dataset, cargo cluster time-series location dataset, and cargo cluster remaining distance dataset, temperature trend prediction training is performed to generate a cargo cluster temperature trend predictor set. Temperature control analysis is performed based on the cargo cluster temperature trend predictor set and the cargo cluster temperature control adjustment dataset to construct a set of long-term temperature control analysis channels for multiple cargoes.

7. A GPS-linked cold chain logistics temperature control monitoring method as described in claim 6, characterized in that, The temperature control analysis is performed based on the cargo cluster temperature trend predictor set and the cargo cluster temperature control adjustment dataset to construct a set of long-term temperature control analysis channels for multiple cargoes, including: Based on the output data of the cargo cluster temperature trend predictor set, a cargo cluster temperature trend prediction dataset is obtained; A deep neural network structure is used to perform correlated temperature control training and iterative feedback optimization on the cargo cluster temperature trend prediction dataset and the cargo cluster temperature control adjustment dataset to obtain a cargo cluster temperature control analyzer set. The cargo cluster temperature trend predictor set and the cargo cluster temperature control analyzer set are connected and merged to construct the multi-cargo long-term temperature control analysis channel set.

8. The GPS-linked cold chain logistics temperature control monitoring method as described in claim 1, characterized in that, The determination of the target temperature control analysis channel includes: When the temperature comparison result indicates that the temperature data of the carriage exceeds the preset safe temperature threshold, the short-term temperature control analysis channel is activated as the target temperature control analysis channel. If the temperature comparison result indicates that the temperature data of the carriage is within the preset safe temperature threshold, the long-term temperature control analysis channel is activated as the target temperature control analysis channel.

9. A GPS-linked cold chain logistics temperature control monitoring method as described in claim 1, characterized in that, The method further includes: Based on the arrangement and stacking of the target cold chain goods, an analysis of the impact of cold air circulation is conducted to obtain the cold air diffusion impact coefficient of the goods. Based on the cold air diffusion influence coefficient of the cargo, the cargo temperature rise influence factor is determined, and the temperature control adjustment strategy parameters are corrected based on the cargo temperature rise influence factor.

10. A cold chain logistics temperature control monitoring system based on GPS linkage, characterized in that, The system is used to implement the GPS-linked cold chain logistics temperature control monitoring method according to any one of claims 1 to 9, the system comprising: The data acquisition module is used to install an on-board terminal on the cold chain logistics transport vehicle. The on-board terminal integrates a GPS positioning module, a temperature sensor and a wireless communication module, and collects vehicle location information and compartment temperature data in real time through the GPS positioning module and the temperature sensor. The temperature control analysis channel calling module is used to encrypt and upload the vehicle location information and compartment temperature data to the monitoring and processing center through the wireless communication module, and call the dual channels of cold chain logistics temperature control analysis for the target cold chain goods through the monitoring and processing center. The dual channels of cold chain logistics temperature control analysis include a short-term temperature control analysis channel and a long-term temperature control analysis channel. The temperature control analysis channel matching module is used to obtain the temperature comparison results between the temperature data of the carriage and the preset safe temperature threshold, and to match the temperature comparison results with the dual channels of the cold chain logistics temperature control analysis to determine the target temperature control analysis channel. The temperature control strategy parameter determination module is used to perform temperature control analysis on the vehicle location information and compartment temperature data based on the target temperature control analysis channel, determine the temperature control adjustment strategy parameters, and perform cold chain logistics temperature control supervision through the temperature control adjustment strategy parameters.

Images