Temperature control method, system, and electronic device for cold chain transport

Abstract

The present application relates to the technical field of cold chain transportation, and particularly relates to a temperature control method and system for cold chain transportation and an electronic device, the method comprising the following steps: S1, collecting real-time environment data and cargo data and preprocessing; S2, inputting the preprocessed data into a pre-trained deep learning model, analyzing the nonlinear relationship between the data, predicting the temperature control parameters and corresponding energy consumption data and equipment life consumption data, and generating a multi-objective optimization solution set; S3, selecting the final operation parameters from the multi-objective optimization solution set based on the temperature control strategy, and executing through a cold machine; S4, optimizing the deep learning model by taking the data of the whole process as a training sample, and cyclically executing steps S1-S4, the present application can realize accurate and reliable temperature control, taking into account energy efficiency and equipment life, so as to improve the quality of cold chain transportation while realizing more sustainable and efficient operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cold chain transportation, and particularly relates to a temperature control method, system and electronic device for cold chain transportation. BACKGROUND

[0002] Cold chain transportation systems involve the transportation of food, medicine and other temperature-sensitive goods. Cold chain transportation is carried out within a specific temperature range to ensure the quality and integrity of the goods.

[0003] Cold chain transportation is a complex system involving multiple interrelated aspects. Not only the characteristics and needs of the goods need to be considered, but also the transportation environment, equipment, energy and sustainability. Comprehensive analysis and intelligent control of these factors are the key to efficient, reliable and sustainable cold chain transportation.

[0004] Cold chain transportation faces multiple challenges and problems:

[0005] Different goods require different temperature and humidity conditions, and various factors such as external environment, goods type and loading method need to be considered in the regulation process; maintaining constant temperature transportation requires a large amount of energy, which leads to energy waste if not effectively controlled; frequent temperature adjustment causes wear and tear to cooling equipment, affecting equipment life; many existing systems lack real-time monitoring and intelligent adjustment capabilities, and cannot respond to changes in the transportation process in a timely manner.

[0006] Existing cold chain temperature control technology mainly relies on preset temperature parameters and manual monitoring. Although some advanced systems have certain automatic regulation functions, they usually lack the following aspects:

[0007] Existing technology does not fully integrate and analyze all relevant environmental and goods data, resulting in less comprehensive and accurate control decisions; many systems rely on manual settings and adjustments, lacking automatic and intelligent decision-making capabilities; for sudden changes and complex situations during transportation, existing technology reacts slowly and lacks timely and effective adaptive adjustment capabilities; energy efficiency and equipment life are not considered comprehensively, leading to energy waste and premature equipment wear and tear. SUMMARY

[0008] To solve the above problems of existing technology, the present application provides a temperature control method, system and electronic device for cold chain transportation. Through deep learning and multi-objective optimization, the present application not only achieves accurate and reliable temperature control, but also takes into account energy efficiency and equipment life, thereby improving the quality of cold chain transportation while achieving more sustainable and efficient operation.

[0009] A temperature control method for cold chain transportation, comprising the following steps:

[0010] S1, collecting real-time environmental data and cargo data and preprocessing;

[0011] S2, inputting the preprocessed data into a pre-trained deep learning model, analyzing the nonlinear relationship between the data, predicting the temperature control parameters and the corresponding energy consumption data and equipment life consumption data, and generating a multi-objective optimization solution set;

[0012] S3, selecting the final operating parameters from the multi-objective optimization solution set based on the temperature control strategy, and executing through the cold machine;

[0013] S4, optimizing the deep learning model by taking the data of the entire process as training samples, and executing steps S1-S4 cyclically.

[0014] Preferably, the environmental data includes temperature, humidity, weather conditions, traffic conditions, season, geographical location and equipment status; and

[0015] The cargo data includes cargo type, shelf life, volume, weight, packaging method, temperature sensitivity and stacking and layout conditions.

[0016] Preferably, the deep learning model is trained through historical transportation records, and the historical transportation records include environmental data, cargo data, and corresponding energy consumption data and equipment service life data;

[0017] The deep learning model divides the preprocessed data into a training set, a validation set and a test set; the training set data is used for training, and the weights of the deep learning model are optimized through back propagation and gradient descent; during the training process, the generalization performance of the deep learning model is monitored through the validation set, overfitting is detected, and hyperparameters are adjusted; the test set is used for final evaluation of the performance of the deep learning model, to ensure the performance of the deep learning model on unseen data.

[0018] Preferably, the multi-objective optimization solution set is a set of specific numerical solutions including temperature control parameters, energy consumption data and equipment life consumption data, and the multi-objective optimization solution set is used to reveal the mutual relationship between the temperature control parameters, the energy consumption data and the equipment life consumption data.

[0019] Preferably, the selection of the final operating parameters from the multi-objective optimization solution set based on the temperature control strategy comprises:

[0020] S310, determining the priority of the temperature control parameters, the energy consumption data and the equipment life consumption data;

[0021] S320, selecting the final operating parameters for execution from the multi-objective optimization solution set according to the priority;

[0022] S330, fine-tuning the operation parameters according to the real-time data and operation effect in the transportation process.

[0023] Preferably, the S310 comprises:

[0024] S311, analyzing the cargo demand: determining the priority of the preservation demand by identifying the temperature sensitivity, shelf life and value of the cargo;

[0025] S312, analyzing the energy factor: determining the priority of the energy efficiency by analyzing the energy price and availability;

[0026] S313, evaluating the equipment status: checking the status and life of the related equipment to determine the priority of the equipment life.

[0027] Preferably, the S320 comprises:

[0028] S321, applying the priority setting: evaluating and sorting each solution in the multi-objective optimization solution set according to the determined priority;

[0029] S322, selecting the best solution: selecting the solution that best meets the priority as the operation parameter according to the evaluation result.

[0030] Preferably, the training sample comprises:

[0031] Real-time environmental data and cargo data;

[0032] The operation parameters executed in the transportation process and the corresponding energy consumption data and equipment life consumption data.

[0033] A temperature control system for cold chain transportation, comprising:

[0034] A collection module for collecting and preprocessing real-time environmental data and cargo data;

[0035] A data processing module for inputting the preprocessed data into a pre-trained deep learning model, analyzing the nonlinear relationship between the data, predicting the temperature control parameters and the corresponding energy consumption data and equipment life consumption data, and generating a multi-objective optimization solution set;

[0036] An execution module for selecting the final operation parameter from the multi-objective optimization solution set based on the temperature control strategy and executing it through a cold machine;

[0037] An optimization module for optimizing the deep learning model with the data of the entire process as the training sample.

[0038] An electronic device includes a memory for storing at least one instruction and a processor for executing the at least one instruction to implement a temperature control method for cold chain transportation.

[0039] Compared with the prior art, the advantages and beneficial effects of the present application are:

[0040] (1) The present application can comprehensively grasp the complex situation in the transportation process by collecting and analyzing multi-dimensional real-time data, including environment, goods, energy and equipment, etc. The multi-objective optimization solution further reveals the mutual relationship between these factors, making the decision more comprehensive and accurate.

[0041] (2) Based on the prediction and analysis of the deep learning model, the present application can automatically select the best operating parameters from the multi-objective optimization solution; This process covers temperature control, energy efficiency and equipment life, etc. Key factors to ensure the intelligence and accuracy of decision-making;

[0042] (3) The present application can continuously learn and optimize the deep learning model by continuously collecting and analyzing data during the entire transportation process; This adaptive optimization process can respond to various unforeseen changes and challenges in time, improving the robustness and flexibility;

[0043] (4) The present application ensures that the preservation and quality requirements of goods are met by precisely controlling temperature and optimizing energy consumption, while also taking into account energy efficiency and equipment life, thereby achieving comprehensive and sustainable optimization of cold chain transportation;

[0044] The present application realizes a comprehensive, intelligent and adaptive temperature control solution, which not only improves the efficiency and reliability of cold chain transportation, but also provides strong support for the sustainable development of the cold chain industry. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The flowchart of the method of the present application;

[0046] Figure 2 The flowchart of selecting operating parameters in the present application;

[0047] Figure 3 The flowchart of determining priority in the present application;

[0048] Figure 4 The flowchart of selecting operating parameters from the multi-objective optimization solution in the present application;

[0049] Figure 5 The structure block diagram of the system of the present application. DETAILED DESCRIPTION

[0050] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0051] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0052] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0053] When using expressions such as "at least one of A, B, and C," the expression should generally be interpreted in accordance with the meaning commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, systems having A alone, having B alone, having C alone, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.). Similarly, when using expressions such as "at least one of A, B, or C," the expression should generally be interpreted in accordance with the meaning commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, or C" should include, but is not limited to, systems having A alone, having B alone, having C alone, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0054] The accompanying drawings illustrate several block diagrams and / or flowcharts. It should be understood that some blocks, or combinations thereof, in the block diagrams and / or flowcharts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that, when executed by the processor, these instructions can create means for implementing the functions / operations described in these block diagrams and / or flowcharts. The technology of this disclosure can be implemented in hardware and / or software (including firmware, microcode, etc.). Alternatively, the technology of this disclosure can take the form of a computer program product stored on a computer-readable storage medium, which is available for use by or in conjunction with an instruction execution system.

[0055] As Figure 1 shown, a temperature control method for cold chain transportation includes the following steps:

[0056] S1, collecting real-time environmental data and cargo data and preprocessing;

[0057] S2, inputting the preprocessed data into a pre-trained deep learning model, analyzing the nonlinear relationship between the data, predicting the temperature control parameters and their corresponding energy consumption data and equipment life consumption data, and generating a multi-objective optimization solution set;

[0058] S3, selecting the final operating parameters from the multi-objective optimization solution set based on the temperature control strategy, and executing through the cold machine;

[0059] S4, using the data of the entire process as training samples to optimize the deep learning model, and executing steps S1-S4 in a loop.

[0060] The temperature control method of the present application is an integrated, dynamic and adaptive system that combines modern sensing technology and deep learning algorithms.

[0061] Data-driven: first, real-time environmental and cargo data are collected through sensors, which include all factors critical to temperature control; Deep learning analysis: the pre-trained deep learning model can analyze the complex nonlinear relationship between data, predict future temperature requirements and corresponding energy consumption and equipment life consumption; Multi-objective optimization solution set: the model not only predicts a single result, but also generates a solution set that reveals the relationship between temperature control parameters, energy consumption and equipment life; Intelligent decision-making: the most suitable operating parameters are selected from the solution set through the temperature control strategy, and are executed in real time; Continuous learning and optimization: the data of the entire process are fed back to the deep learning model for further training and optimization, achieving self-learning and self-optimization.

[0062] In summary, the present application has the following advantages:

[0063] Intelligent: this method can automatically and intelligently control temperature without human intervention;

[0064] Efficient and energy-saving: through accurate prediction and optimization, energy can be used efficiently while meeting the preservation needs of goods;

[0065] Adaptive: due to the continuous learning and optimization mechanism, it can continuously adapt to changing environments and demands;

[0066] All-round optimization: the present application not only focuses on temperature control, but also considers energy efficiency and equipment life, achieving all-round optimization of cold chain transportation;

[0067] Overall, the temperature control method for cold chain transportation represents an advanced, integrated and adaptive solution that enables intelligent, efficient and sustainable cold chain transportation. The combination of its principles and effects embodies the perfect integration of modern logistics and artificial intelligence technology.

[0068] Preferably, the environmental data includes temperature, humidity, weather conditions, traffic conditions, season, geographical location, and equipment status.

[0069] Environmental data:

[0070] Temperature and humidity: Temperature and humidity are key factors that directly affect the quality of goods. They must always be kept within appropriate ranges to ensure the integrity of goods.

[0071] Weather conditions: Weather (such as heavy rain, snow, high temperature, etc.) can affect traffic and transportation speed, and also have an impact on temperature and humidity.

[0072] Traffic conditions: Traffic congestion or smoothness can affect transportation time, thereby affecting the adjustment of control strategies.

[0073] Season, geographical location: Season and geographical location can affect external temperature and humidity, which must be considered in the temperature control strategy.

[0074] Equipment status: The health and operating status of equipment directly affect cooling efficiency and energy consumption.

[0075] Environmental data: The environmental data collected by the system includes temperature, humidity, weather conditions, traffic conditions, season, geographical location, and equipment status. These data reflect various environmental factors encountered during the transportation of goods, and have important influence on predicting the refrigeration needs of goods and the energy consumption of cold chain equipment.

[0076] Goods data:

[0077] Goods type: Different types of goods require different temperature and humidity conditions.

[0078] Shelf life: The shelf life of goods requires more stringent temperature control.

[0079] Volume, weight: These factors will affect cooling needs and energy consumption.

[0080] Packaging method: Different packaging will have different requirements for temperature and humidity maintenance.

[0081] Temperature sensitivity: The sensitivity of goods to temperature determines the precision and importance of temperature control.

[0082] Stacking and layout: The stacking and layout of the goods can affect the circulation of cold air, thus affecting the cooling efficiency.

[0083] And the goods data includes: goods type, shelf life, volume, weight, packaging method, temperature sensitivity, and stacking and layout.

[0084] Goods data, which reflects the characteristics and status of goods, has a significant impact on predicting the refrigeration needs of goods and the operating status of cold chain equipment.

[0085] These data will be pre-processed, such as cleaning, standardization, normalization, etc., to facilitate the input and analysis of deep learning models.

[0086] Collecting and processing these environmental and goods data enables the system to make accurate refrigeration demand predictions and cold machine operating parameter settings under various environmental and goods conditions. This will greatly improve the efficiency and quality of cold chain transportation, reduce energy consumption, extend equipment life, and ultimately achieve high-quality cold chain transportation results.

[0087] In one embodiment, for a batch of fresh products (goods type) that need to be transported at 2-8℃, assuming their shelf life is 3 days, volume is 1 cubic meter, weight is 1000kg, uses refrigerated packaging (packaging method), is extremely sensitive to temperature (temperature sensitivity), and is stacked in the refrigerated box according to the specified manner (stacking and layout). Now, this batch of goods needs to be transported from Beijing (geographical location, season) to Shanghai, the current temperature in Beijing is 30℃, the humidity is 50%, the weather is sunny, and there is no major traffic congestion (traffic conditions) expected during transportation. The cold chain equipment is in good condition (equipment status). Then, the system will predict the most suitable cold machine operating parameters based on these environmental and goods data, ensuring the freshness of the goods during transportation, while also considering energy consumption and equipment life.

[0088] Preferably, the deep learning model is trained by historical transportation records, which include environmental data, goods data, and corresponding energy consumption data and equipment service life data.

[0089] The deep learning model divides the pre-processed data into training set, validation set and test set; uses the training set data for training, optimizes the weights of the deep learning model through backpropagation and gradient descent; during training, the validation set is used to monitor the generalization performance of the deep learning model, detect overfitting and adjust hyperparameters; the test set is used for final evaluation of the deep learning model performance to ensure the performance of the deep learning model on unseen data.

[0090] Historical transportation records: Historical transportation records are the basis for model training. They include environmental data, cargo data, and corresponding energy consumption data and equipment service life data, providing a rich sample for the model to learn and simulate various situations that occur during actual transportation.

[0091] Training set, validation set, and test set: The preprocessed data is divided into a training set, a validation set, and a test set. The training set is used to train the model; the validation set is used to monitor the model's generalization performance during training, detect overfitting, and adjust hyperparameters; the test set is used to evaluate the model's performance on unseen data after training is complete.

[0092] Backpropagation and gradient descent: Backpropagation and gradient descent are key algorithms for training deep learning models. Backpropagation is used to calculate the gradients of the model's parameters, and gradient descent is used to update the model's weights based on these gradients.

[0093] The following effects can be achieved through deep learning models:

[0094] Efficient prediction: Through training, deep learning models can learn the complex relationships between data and use these relationships for efficient prediction.

[0095] Prevent overfitting: By monitoring the model's generalization performance using the validation set, overfitting can be detected and prevented in a timely manner, ensuring that the model performs well on new data.

[0096] Model evaluation: Through the test set, the model's performance on unseen data can be evaluated to ensure the effectiveness of the model's predictions.

[0097] In one embodiment, if the model's performance on the training set continues to improve during training, but the performance on the validation set begins to decline, overfitting has occurred. At this time, strategies such as early stopping can be used to prevent overfitting; after the model training is complete, the test set can be used to evaluate the final performance of the model. If the model's performance on the test set is also good, it can be considered that the model has good generalization performance and can be used for actual temperature control tasks.

[0098] The deep learning model and its training process in this invention are the core part of intelligent temperature control. It can learn from historical transportation records, simulate and predict various complex situations during actual transportation, and provide accurate and efficient temperature control solutions for cold chain transportation.

[0099] Preferably, the multi-objective optimization solution set is a set of specific numerical solutions including temperature control parameters, energy consumption data, and equipment life consumption data, and the multi-objective optimization solution set is used to reveal the mutual relationship between temperature control parameters, energy consumption data, and equipment life consumption data.

[0100] Multi-objective optimization solution set: In optimization problems, there are often multiple objectives to consider. For example, in this case, temperature control parameters, energy consumption data, and equipment life loss data need to be considered. These objectives are in competition or conflict with each other, for example, to better maintain the freshness of goods, a lower temperature is needed, but this will increase energy consumption. Therefore, a set of solutions is needed that can balance the objectives while meeting all the objectives. This set of solutions constitutes a multi-objective optimization solution set.

[0101] Revealing relationships: Through the multi-objective optimization solution set, the relationships between temperature control parameters, energy consumption data, and equipment life loss data can be revealed. For example, it can be seen that if lower energy consumption is desired, higher temperature needs to be accepted; if the service life of the equipment is longer, higher energy consumption needs to be accepted, etc. Through these relationships, these objectives can be better understood and weighed.

[0102] Through the multi-objective optimization solution set, better decisions can be made. Various decision results can be seen, and the impact of these results on each objective can be seen, so that better decisions can be made.

[0103] Through the revelation of the relationships between various objectives, these objectives and their mutual influence can be better understood. This is very helpful for understanding and improving the cold chain transportation process.

[0104] In one embodiment, reducing the temperature while maintaining the freshness of goods will significantly increase energy consumption, but will not have much impact on the service life of the equipment. This can help make decisions, for example, to accept a slightly higher temperature to save energy, especially in cases where energy prices are high or energy supply is tight.

[0105] Multi-objective optimization solution set is a very important tool that can help understand and weigh multiple conflicting objectives, so as to make the best decision while meeting all objectives.

[0106] In another embodiment, the target temperature inside the refrigerated truck is set to 4°C. This temperature may be for a specific type of goods, such as a certain type of fresh food.

[0107] Energy consumption data: To maintain the above-mentioned target temperature of 4°C, it may consume 0.5 kilowatt-hour (kWh) of electricity per hour. This consumption may vary due to factors such as the efficiency of the cooling equipment, external temperature, etc.

[0108] Equipment life loss data: Running the cooling equipment for one hour may reduce the total life of the equipment by 0.02%. This value may be related to factors such as the quality of the equipment, operating temperature, maintenance, etc.

[0109] Therefore, a set of specific numerical solutions is:

[0110] Temperature control parameter: 4°C

[0111] Energy consumption data: 0.5 kWh / hour

[0112] Equipment life loss data: 0.02% life reduction / hour

[0113] This set of solutions may only be applicable in a specific context, such as a certain type of goods, external temperature, etc. In different contexts, different temperature control parameters, energy consumption data, and equipment life loss data may be required, so multiple sets of such solutions may be included in the solution set to adapt to different transportation needs and conditions.

[0114] Preferably, as Figure 2 indicated, the final operating parameters selected from the multi-objective optimization solution set based on the temperature control strategy include:

[0115] S310, determine the priority of temperature control parameters, energy consumption data, and equipment life loss data;

[0116] In any multi-objective decision-making process, different objectives have different importance or priority. In this temperature control method for cold chain transportation, the priority of temperature control parameters, energy consumption data, and equipment life loss data needs to be determined. These priorities can be determined based on business needs, cost considerations, equipment status, transportation conditions, and other factors.

[0117] S320, select the final operating parameters for execution from the multi-objective optimization solution set according to the priority;

[0118] According to the determined priority, select the final operating parameters for execution from the multi-objective optimization solution set. In this process, an optimal solution needs to be found that meets the priority requirements of all objectives.

[0119] S330, according to the real-time data and operation effect in the transportation process, fine-tune the operating parameters.

[0120] This allows real-time adjustment and optimization of operating parameters when faced with uncertainties and changes in the transportation process.

[0121] Priority-based decision-making can flexibly weigh and adjust different objectives while meeting all objectives. This can help make optimal decisions when faced with complex and dynamic transportation processes.

[0122] Through real-time data and operation effect fine-tuning, operating parameters can be optimized in real time to respond to any changes in the transportation process. This can improve transportation efficiency and quality.

[0123] In one embodiment, it is assumed that in a certain transportation, due to the rise in energy prices, the priority of energy consumption will be increased. In this case, an operating parameter with lower energy consumption will be selected from the multi-objective optimization solution set. Then, during the transportation process, if it is found that the temperature of the goods begins to rise, the operating parameter will be fine-tuned to increase the working frequency of the cold machine to ensure the freshness of the goods.

[0124] Preferably, as shown in Figure 3 S310 includes:

[0125] S311, analyze the freshness requirement: by identifying the temperature sensitivity, shelf life and value of the goods, determine the priority of the freshness requirement;

[0126] The priority of the freshness requirement is determined according to the characteristics of the goods. For example, if the temperature sensitivity of the goods is high, the shelf life is short, and the value is high, the priority of the freshness requirement will be high. This is because such goods require strict temperature control to ensure their freshness and quality during transportation.

[0127] S312, analyze the energy factor: by analyzing the energy price and availability, determine the priority of energy efficiency;

[0128] The priority of energy efficiency is determined according to the price and availability of energy. For example, if the energy price is high or the energy supply is tight, the priority of energy efficiency will be increased. This is because in this case, the transportation cost needs to be reduced by optimizing energy use.

[0129] S313, evaluate the equipment status: check the status and life of the relevant equipment, and determine the priority of the equipment life.

[0130] The priority of the equipment life is determined by checking the status and life of the relevant equipment. For example, if the equipment has been used for a long time, or has failed or worn out, the priority of the equipment life will be increased. This is because in this case, the maintenance and replacement cost of the equipment needs to be considered.

[0131] Through the analysis of the freshness requirement, energy factor and equipment status, the priority can be set according to the actual situation. This makes it possible to better meet various requirements and optimize the transportation process.

[0132] The priority is not fixed, but dynamically adjusted according to the actual situation of goods, energy and equipment. This makes it possible to flexibly respond to changes in the transportation process.

[0133] In one embodiment, it is assumed that a batch of high-value fresh flowers is being transported. These fresh flowers are very sensitive to temperature and need to be transported within a specific temperature range. At the same time, since the shelf life of fresh flowers is short, the priority of preservation requirements is very high. In addition, assuming that the current energy price is low and the equipment is in good condition, the priorities of energy efficiency and equipment life are relatively low. In this case, an operating parameter that ensures the freshness of the flowers will be selected, even if it results in a slight increase in energy consumption.

[0134] Preferably, as shown in FIG. 3, the S320 includes: Figure 4

[0135] S321, application of priority setting: according to the determined priority, each solution in the multi-objective optimization solution set is evaluated and ranked;

[0136] The system will evaluate and rank each solution in the multi-objective optimization solution set according to the previously determined priorities (preservation requirements, energy efficiency, equipment life, etc.). Each solution is an operating parameter, including temperature settings, energy consumption, etc., which will affect the preservation effect of the goods, the efficiency of energy use, and the service life of the equipment.

[0137] The evaluation method is to take a weighted average of the values of each objective function (e.g., preservation effect, energy consumption, equipment life, etc.), and the weight is the priority of each objective. For example, if the priority of preservation requirements is the highest, the weight of preservation effect will be the largest.

[0138] S322, selection of the best solution: according to the evaluation results, the solution that best meets the priority is selected as the operating parameter.

[0139] According to the evaluation results, the system will select the solution that best meets the priority as the operating parameter. If there are multiple solutions with the same evaluation results, the system can select any one of them as the operating parameter. This operating parameter will be used to control the operation of the cold machine to achieve the purpose of optimizing cold chain transportation.

[0140] Through the S320 system, the optimal operating parameter can be dynamically selected according to the actual requirements and environmental conditions, realizing the intelligentization and optimization of the cold chain transportation process. This will greatly improve the efficiency and quality of cold chain transportation, reduce energy consumption and equipment wear and tear, thereby reducing transportation costs and improving the quality of transportation services.

[0141] ​In one embodiment, assume that a batch of strawberries, a kind of goods that is very sensitive to temperature, is being transported. In step S321, the system will get multiple solutions of operating parameters, each with different temperature settings, energy consumption, etc. Then, the system will evaluate and rank each solution according to the set priorities (e.g., freshness requirement is the highest, energy efficiency is the second, and device lifespan is the lowest). In step S322, the system will select the solution with the best evaluation result (i.e., the one that best fits the priorities) as the operating parameters for controlling the operation of the cold machine. In this way, even if the energy consumption increases slightly, the freshness of the strawberries can be ensured, meeting the requirements of transportation.

[0142] Preferably, the training samples include:

[0143] Real-time environmental data and goods data;

[0144] The real-time environmental data and goods data are the inputs of the deep learning model. The environmental data includes temperature, humidity, weather conditions, traffic conditions, season, geographical location, and device status, etc. The goods data includes goods type, shelf life, volume, weight, packaging method, temperature sensitivity, and stacking and layout, etc.

[0145] These data together reflect the specific environment and characteristics of the goods during transportation, which are the key factors for temperature control in cold chain transportation.

[0146] The operating parameters executed during transportation and their corresponding energy consumption data and device lifespan consumption data.

[0147] The operating parameters include specific settings for real-time control of the cold machine, such as setting temperature, humidity, etc. The energy consumption data and device lifespan consumption data corresponding to the operating parameters reflect the effects and costs of these operating parameters.

[0148] By using real-time environmental data, goods data, operating parameters, and their corresponding energy consumption data and device lifespan consumption data as training samples, the deep learning model can more accurately understand and learn the dynamic changes and interrelationships in the cold chain transportation process.

[0149] This not only enables the model to more accurately predict temperature requirements, energy consumption, and device lifespan consumption, but also enables it to more flexibly adapt to different transportation environments and goods requirements, thereby achieving more optimized temperature control.

[0150] In one embodiment, when transporting a batch of fresh food that is extremely sensitive to temperature, the environment suddenly changes, causing the external temperature to rise sharply. At this time, the system will immediately collect real-time environmental temperature, humidity, goods type, etc. data, and combine with previous operating parameters and energy consumption data to predict new operating parameters through the deep learning model.

[0151] The system applies these new operating parameters to the control of the cold machine to ensure that the preservation needs of the goods are met, while also considering the balance between energy efficiency and equipment lifespan.

[0152] By adjusting operating parameters in real-time and continuously optimizing the deep learning model, the system can better handle various uncertainties and changes during transportation, greatly improving the efficiency and quality of cold chain transportation.

[0153] As shown in Figure 5 a temperature control system for cold chain transportation, comprising:

[0154] A collection module for collecting real-time environmental data and goods data and preprocessing;

[0155] The collection module is responsible for real-time monitoring and obtaining environmental data and goods data during transportation. These data include temperature, humidity, weather conditions, traffic conditions, equipment status, and goods type, shelf life, volume, weight, etc. The collection module also needs to preprocess these data, such as denoising, normalization and missing value filling, etc., to ensure the quality and consistency of the data.

[0156] A data processing module for inputting preprocessed data into a pre-trained deep learning model, analyzing the nonlinear relationship between data, predicting temperature control parameters and their corresponding energy consumption data and equipment lifespan loss data, and generating a multi-objective optimization solution set;

[0157] The data processing module is mainly responsible for inputting the preprocessed data from the collection module into the pre-trained deep learning model. Through deep learning technology, the data processing module analyzes the nonlinear relationship between data and predicts future temperature demand, energy consumption and equipment lifespan loss, etc. based on this. These prediction results will be combined into a multi-objective optimization solution set for subsequent decision-making.

[0158] An execution module for selecting final operating parameters from the multi-objective optimization solution set based on temperature control strategies and executing them through the cold machine;

[0159] The execution module selects the most suitable operating parameters from the multi-objective optimization solution set based on temperature control strategies. This selection process involves priority setting and comprehensive evaluation of temperature control parameters, energy consumption data and equipment lifespan loss data. The selected operating parameters will be executed through the cold machine to achieve precise temperature control.

[0160] An optimization module for optimizing the deep learning model using data from the entire process as training samples.

[0161] The optimization module is responsible for monitoring the entire process and continuously optimizing and adjusting the deep learning model with all relevant data as training samples. This continuous learning and optimization ensures that the system can adapt to changing environments and demands, improving the intelligence and flexibility of the system.

[0162] Through the coordinated work of the four modules, the temperature control system can achieve precise, intelligent, and adaptive control of the temperature during cold chain transportation. Not only can it ensure that the quality and preservation needs of goods are met, but it can also achieve efficient use of energy and equipment, thereby improving the efficiency and reliability of the entire cold chain transportation.

[0163] In one embodiment, assume that during the transportation of a batch of high-temperature-sensitive vaccines, a serious traffic jam is encountered suddenly. The acquisition module immediately captures this change and predicts that the traffic jam will cause the transportation time to be extended. The data processing module analyzes the impact of this change on the temperature requirements and generates a new set of multi-objective optimization solutions. The execution module selects new operating parameters from the solution set according to the current energy reserves and equipment status, and makes real-time adjustments through the cold machine. The optimization module records all the data of this process for further optimization of the subsequent deep learning model.

[0164] Through this series of intelligent processing, the system successfully avoids the temperature control failure caused by the traffic jam, ensuring the safe transportation of the vaccines, and also demonstrates the strong intelligence and flexibility of the temperature control system.

[0165] An electronic device, the electronic device comprising a memory and a processor, the memory being used to store at least one instruction, the processor being used to execute at least one instruction to realize a temperature control method for cold chain transportation.

[0166] Those skilled in the art will understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0167] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0168] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0169] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0170] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0171] The memory includes non-persistent memory and / or persistent memory, both of which can be volatile and / or non-volatile. Non-persistent memory can be, for example, random access memory (RAM), which can be volatile and / or non-volatile. Non-volatile memory can be, for example, read-only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, solid-state memory, etc. Memory is an example of computer-readable media.

[0172] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0173] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus that includes a list of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0174] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A temperature control method for cold chain transportation, characterized in that, The method comprises the following steps: S1, collecting real-time environmental data and cargo data and preprocessing; S2, inputting the preprocessed data into a pre-trained deep learning model, analyzing the nonlinear relationship between the data, predicting the temperature control parameters and their corresponding energy consumption data and equipment life consumption data, and generating a multi-objective optimization solution set; The multi-objective optimization solution set is a set of specific numerical solutions including temperature control parameters, energy consumption data and equipment life consumption data, and is used to reveal the mutual relationship between the temperature control parameters, energy consumption data and equipment life consumption data; S3, selecting the final operating parameters from the multi-objective optimization solution set based on the temperature control strategy, and executing through the cold machine; The step of selecting the final operating parameters from the multi-objective optimization solution set based on the temperature control strategy comprises: S310, determining the priority of the temperature control parameters, energy consumption data and equipment life consumption data; S320, selecting the final operating parameters for execution from the multi-objective optimization solution set according to the priority; S330, fine-tuning the operating parameters according to real-time data and operating effects during transportation; The step S310 comprises: S311, analyzing cargo demand: determining the priority of preservation demand by identifying the temperature sensitivity, shelf life and value of the cargo; S312, analyzing energy factors: determining the priority of energy efficiency by analyzing energy prices and availability; S313, evaluating equipment status: checking the status and life of related equipment to determine the priority of equipment life; The step S320 comprises: S321, applying priority setting: evaluating and sorting each solution in the multi-objective optimization solution set according to the determined priority; S322, selecting the best solution: selecting the solution that best meets the priority as the operating parameter according to the evaluation result; S4, optimizing the deep learning model with the data of the entire process as training samples, and executing steps S1-S4 in a loop.

2. The temperature control method according to claim 1, characterized by, The environmental data includes temperature, humidity, weather conditions, traffic conditions, season, geographical location and equipment status; and The cargo data includes cargo type, shelf life, volume, weight, packaging method, temperature sensitivity and stacking and layout conditions.

3. The temperature control method according to claim 1, wherein The deep learning model is trained through historical transportation records, which include environmental data, cargo data, and corresponding energy consumption data and equipment life data; The deep learning model divides the preprocessed data into training set, validation set and test set; the training set data is used for training, and the weights of the deep learning model are optimized through back propagation and gradient descent; during the training process, the generalization performance of the deep learning model is monitored through the validation set, overfitting is detected, and hyperparameters are adjusted; the test set is used for final evaluation of the performance of the deep learning model to ensure the performance of the deep learning model on unseen data.

4. The temperature control method of claim 1, wherein The training samples include: Real-time environmental data and cargo data; The operating parameters executed during transportation and their corresponding energy consumption data and equipment life consumption data.

5. A temperature control system for cold chain transportation for implementing the method of temperature control for cold chain transportation according to any one of claims 1-4, characterized in that, It comprises: A collection module for collecting real-time environmental data and cargo data and preprocessing; A data processing module is configured to input the preprocessed data into a pre-trained deep learning model, analyze the nonlinear relationship between the data, predict the temperature control parameters and corresponding energy consumption data and equipment life consumption data, and generate a multi-objective optimization solution set; An execution module is configured to select final operation parameters from the multi-objective optimization solution set based on the temperature control strategy, and perform the operation through a cooling machine; An optimization module is configured to optimize the deep learning model by taking the data of the entire process as training samples.

6. An electronic device, comprising: The electronic device includes a memory and a processor, the memory is configured to store at least one instruction, and the processor is configured to execute the at least one instruction to implement the temperature control method for cold chain transportation as claimed in any one of claims 1 to 4.

Images