Temperature control method, device and equipment for three-dimensional refrigeration house, medium and product

Abstract

The invention provides a temperature control method, device and equipment of a three-dimensional refrigeration house, a medium and a product, and belongs to the technical field of refrigeration house warehousing, and the method comprises the steps that a refrigeration house digital twinborn model is built based on a three-dimensional geometric structure of the three-dimensional refrigeration house, and the refrigeration house digital twinborn model carries out transient simulation on the temperature based on computational fluid mechanics; receiving a real-time warehousing plan; performing temperature regulation on the three-dimensional refrigeration house based on the real-time warehousing plan and the real-time temperature state of the three-dimensional refrigeration house by using a refrigeration house digital twin model; wherein the refrigeration house digital twin model takes a real-time temperature state as an initial condition and takes goods in a real-time warehousing plan as a transient heat source for transient simulation. The temperature influence of the goods on the three-dimensional refrigeration house in the warehousing plan is considered, and the temperature control precision is improved.

Description

Technical Field

[0001] This application relates to the field of cold storage technology, and in particular to a temperature control method, device, equipment, medium and product for a three-dimensional cold storage. Background Technology

[0002] Currently, temperature control in automated cold storage facilities generally employs a feedback control method based on a set temperature. This means that when the temperature sensor inside the storage detects a temperature higher than the set value, the cooling load is calculated based on the difference between the current and set temperatures, and then the cooling capacity is activated or increased. The calculation of the cooling load is typically based on a steady-state heat transfer model. However, traditional steady-state heat transfer models neglect the impact of changes in the goods themselves on the storage temperature, making it impossible to accurately predict the temperature change over time. This error is particularly pronounced when different types of goods are stored together. Summary of the Invention

[0003] This application provides a temperature control method, device, equipment, medium, and product for a three-dimensional cold storage, aiming to solve the problem of large temperature deviations obtained by existing cold load calculation methods based on traditional steady-state heat transfer models.

[0004] Firstly, this application provides a temperature control method for an automated cold storage facility, comprising: A digital twin model of the cold storage is built based on the three-dimensional geometric structure of the cold storage. The digital twin model of the cold storage is used to perform transient temperature simulation based on computational fluid dynamics. Receive real-time inbound plans; Using a digital twin model of cold storage, the temperature of the automated cold storage is regulated based on the real-time inbound plan and the real-time temperature status of the cold storage. The digital twin model of cold storage uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as the transient heat source for transient simulation.

[0005] In one embodiment, when using a digital twin model of the cold storage to adjust the temperature of the automated cold storage based on the real-time inbound plan and the real-time temperature status of the cold storage, each control cycle includes the following steps: Input the real-time inbound plan and real-time temperature status into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model; The control sequence of the refrigeration system is determined based on the refrigeration load prediction curve. The control sequence includes multiple refrigeration control strategies arranged in time. The first cooling control strategy in the control sequence is sent to the cooling system for execution, and the real-time temperature status is updated based on the adjusted temperature.

[0006] In one embodiment, after updating the real-time temperature state based on the adjusted temperature in each control cycle, the method further includes: Determine the error between the adjusted temperature and the predicted temperature at the same time point determined by the cooling load prediction curve; The model parameters of the digital twin model of the cold storage are corrected based on the error.

[0007] In one embodiment, in the cold storage digital twin model, the cargo area is configured as a porous media domain or a solid domain.

[0008] In one embodiment, the real-time inbound plan includes at least one type of goods, quantity of goods, inbound time, and storage location.

[0009] In one embodiment, the real-time warehousing plan and real-time temperature status are input into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model, specifically including: The cold storage digital twin model assigns the thermophysical properties of the goods type to the area in the porous medium domain or solid domain corresponding to the storage location of the goods type, and the start time of the assignment is the entry time of the goods type into the warehouse. The digital twin model of cold storage determines transient heat sources based on the thermophysical properties of porous media or solid domains; The digital twin model of the cold storage is based on real-time temperature status and transient heat sources to perform transient simulation and obtain the predicted results of temperature field changes inside the storage. The digital twin model of the cold storage determines the corresponding refrigeration load prediction result based on the prediction result of the temperature field change inside the storage, and obtains the refrigeration load prediction curve.

[0010] Secondly, this application also provides a temperature control device for an automated cold storage facility, comprising: The model building module is used to build a digital twin model of the cold storage based on the three-dimensional geometry of the cold storage. The digital twin model of the cold storage performs transient temperature simulation based on computational fluid dynamics. The receiving module is used to receive real-time inbound plans; The adjustment module is used to adjust the temperature of the automated cold storage based on the real-time inbound plan and the real-time temperature status of the automated cold storage using a digital twin model of the cold storage. The digital twin model of the cold storage uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as the transient heat source for transient simulation.

[0011] Thirdly, this application also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned temperature control methods for a three-dimensional cold storage.

[0012] Fourthly, this application also provides a non-transitory computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-described temperature control methods for a three-dimensional cold storage.

[0013] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements any of the above-described temperature control methods for a three-dimensional cold storage. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is one of the flowcharts illustrating the temperature control method for the automated cold storage provided in this application; Figure 2 This is the second flowchart illustrating the temperature control method for the automated cold storage provided in this application; Figure 3 This is one of the flowcharts provided in this application for obtaining the refrigeration load prediction curve output by the digital twin model of the cold storage; Figure 4 This is a schematic diagram of the temperature control device for the automated cold storage provided in this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0018] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.

[0019] Most existing automated cold storage systems use feedback control for temperature control. Feedback control is a reactive strategy and cannot cope with the severe thermal shock caused by the entry of large quantities of hot goods into the storage, resulting in large temperature fluctuations and poor control quality. Furthermore, after goods are put into storage, the system usually operates at maximum power until the temperature drops to the set point. This method cannot reduce the refrigeration power in advance according to the actual cooling trend, resulting in over-cooling and energy waste.

[0020] Although existing steady-state heat transfer models can predict and control temperature in advance, they ignore the impact of changes in the goods themselves on the storage temperature and cannot accurately predict the temperature change over time. The temperature error is even greater when different types of goods are stored together.

[0021] Based on the above, this application provides a temperature control method, apparatus, equipment, medium, and product for a three-dimensional cold storage facility. The following is a detailed description in conjunction with... Figures 1 to 5 This application will be described in detail.

[0022] It should be noted that the temperature control method for the automated cold storage provided in this application embodiment is based on the temperature control device of the automated cold storage. The temperature control method for the automated cold storage is based on building a digital twin model of the cold storage based on the three-dimensional geometric structure of the cold storage. When using the digital twin model of the cold storage for transient simulation, the influence of the goods in the storage plan on the temperature of the automated cold storage is considered, which improves the accuracy of temperature control. At the same time, the predictive mechanism is used to perform forward-looking intelligent temperature regulation to solve the energy waste problems caused by control lag and over-cooling, and realizes the optimized control combining feedforward and feedback.

[0023] This application describes the temperature control method of a three-dimensional cold storage facility using a temperature control device as the executing entity. The temperature control of the three-dimensional cold storage facility is executed by the three-dimensional cold storage control system.

[0024] Figure 1 This is one of the flowcharts illustrating the temperature control method for the automated cold storage provided in this application. Figure 2 This is the second flowchart illustrating the temperature control method for the automated cold storage provided in this application.

[0025] like Figure 1 As shown, the temperature control method for the automated cold storage provided in this application includes: S110: Based on the three-dimensional geometric structure of the cold storage, a digital twin model of the cold storage is built. The digital twin model of the cold storage is based on computational fluid dynamics (CFD) to perform transient temperature simulation.

[0026] Please combine Figure 2 The automated cold storage control system first establishes a digital twin model of the cold storage based on its three-dimensional geometric structure. The three-dimensional geometric structure of the automated cold storage refers to the actual physical layout inside the cold storage, including but not limited to the building boundaries, internal shelving system, goods stacking areas, aisles, and the geometric shapes and positional relationships of refrigeration equipment (such as evaporators and their fans). The automated cold storage control system uses 3D modeling software or tools to construct a high-fidelity three-dimensional geometric model in digital space based on the actual structural dimensions and equipment models of the cold storage.

[0027] A cold storage digital twin model is a virtual mapping of an automated cold storage facility in digital space. It not only contains the geometric structure information of the cold storage but also has the ability to simulate its physical behavior. Specifically, the cold storage digital twin model is based on computational fluid dynamics (CFD) to perform transient temperature simulation, thereby establishing a high-precision transient CFD digital twin model.

[0028] Transient simulation in Computational Fluid Dynamics (CFD) refers to the use of CFD software or algorithms to dynamically predict and analyze the airflow state, heat transfer process, and temperature field changes over time within a cold storage facility by solving fluid flow and heat transfer control equations (such as the Navier-Stokes equations and energy equations). Unlike steady-state heat transfer model simulations, transient simulations can reflect the dynamic changes in the temperature field and airflow organization over time under different operating conditions (such as goods entering the cold storage and the start-up and shutdown of refrigeration equipment), thus capturing the details of temperature fluctuations within the cold storage. For example, when a heat load enters the cold storage, transient simulations can dynamically simulate the rate and range of temperature rise within the storage facility and how the airflow diffuses heat. Therefore, a digital twin model of the cold storage can accurately reflect the thermophysical behavior inside the cold storage, providing a high-precision virtual testing environment for subsequent prediction and control.

[0029] S120: Receive real-time inbound plans.

[0030] Please combine Figure 2 An inbound plan refers to information obtained from the cold storage's warehouse management system or other data sources regarding goods that will be entering the automated cold storage facility within a certain period. This information may include, but is not limited to, the type of goods (e.g., frozen meat, fresh vegetables, pharmaceuticals), the quantity of goods, the estimated inbound time, and the planned storage location. A real-time inbound plan reflects the latest inbound arrangements, allowing the automated cold storage's refrigeration system to respond promptly.

[0031] Real-time inbound plans can be received in various ways, such as through data interaction with the warehouse management system's API interface, reading from the database, or through information transmission via IoT devices.

[0032] By receiving real-time inbound plans, information on future events that could affect the heat load of cold storage is obtained, laying a data foundation for proactive control.

[0033] S130: Utilizing a digital twin model of the cold storage, temperature regulation is performed on the automated cold storage based on real-time inbound plans and the real-time temperature status of the cold storage. Specifically, the digital twin model uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as a transient heat source for transient simulation.

[0034] Real-time temperature status refers to the temperature data inside the cold storage facility that is collected in real time by temperature sensors deployed within the facility (such as a distributed temperature sensor network). Real-time temperature status can be an average temperature value or temperature distribution data for different areas within the cold storage facility.

[0035] Initial conditions refer to the initial state of the temperature field and airflow field inside the model before transient simulation. Initial conditions are used to initialize the digital twin model of the cold storage so that it is consistent with the current thermal state of the physical three-dimensional cold storage.

[0036] Once goods in the real-time warehousing plan enter the automated cold storage facility, they release heat into the storage area. The rate of this heat release varies as the goods' temperature decreases, constituting a transient heat source for the automated cold storage. The digital twin model of the cold storage dynamically simulates this heat release process to predict temperature changes in the automated cold storage over a future period.

[0037] The digital twin model of cold storage combines these initial conditions and transient heat sources to perform transient simulation, so as to predict the future dynamic change trend of the internal temperature field of the automated cold storage. Based on the future dynamic change trend of the temperature field, the operation of the refrigeration system of the automated cold storage is controlled (e.g., adjusting the compressor start-up and shutdown, evaporator fan speed, electronic expansion valve opening, etc.) to adjust the internal temperature of the automated cold storage to the set target range.

[0038] Digital twin models of cold storage can proactively predict future cooling loads and temperature changes in automated cold storage facilities, and make active temperature adjustments based on this, rather than passively waiting for the temperature to exceed the limit before making feedback adjustments. This model-based temperature pre-optimization method fundamentally changes the traditional design mode that relies on experience, and can effectively reduce temperature fluctuations and improve the accuracy of temperature control.

[0039] This application embodiment builds a digital twin model of the cold storage based on the three-dimensional geometric structure of the cold storage. When using the digital twin model for transient simulation, the influence of goods in the warehousing plan on the temperature of the cold storage is considered, which improves the accuracy of temperature control. At the same time, the predictive mechanism is used to perform forward-looking intelligent temperature regulation, which solves the energy waste caused by control lag and over-cooling. It realizes active and precise regulation by combining feedforward and feedback, which significantly improves the quality and stability of temperature control in the cold storage.

[0040] In one possible implementation, please see Figure 2 In step S130, when adjusting the temperature of the automated cold storage based on the real-time inbound plan and the real-time temperature status of the automated cold storage using the cold storage digital twin model, each control cycle includes the following steps: S1310: Input the real-time storage plan and real-time temperature status into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model.

[0041] Specifically, the cold storage digital twin model uses the current real-time temperature state as the initial condition for its transient simulation, ensuring that the simulation starts from the same thermodynamic state as the physical cold storage. At the same time, the cold storage digital twin model transforms the goods in the real-time inbound plan into transient heat sources, that is, it simulates the impact of the goods' own temperature changes, latent heat of phase change, and heat exchange processes with the environment on the internal heat load of the cold storage after these goods enter the cold storage.

[0042] By performing computational fluid dynamics (CFD) transient simulations using a digital twin model of the cold storage facility, the changing trend of the internal temperature field of the automated cold storage facility over a future period (e.g., the next few hours) and the resulting load demand on the refrigeration system are predicted, thus obtaining a refrigeration load prediction curve. This refrigeration load prediction curve reflects the continuous or discrete change of the total heat load that the automated cold storage facility needs to overcome to maintain the target temperature over a future period. For example, the curve might show a trend of a sharp increase in load at a certain point in time due to the arrival of goods, followed by a gradual decrease. The refrigeration load prediction curve of the automated cold storage facility is determined by using the continuous or discrete curve of the total heat load changing over time.

[0043] S1320: Determine the control sequence of the refrigeration system based on the refrigeration load prediction curve. The control sequence includes multiple refrigeration control strategies arranged in time.

[0044] After obtaining the refrigeration load prediction curve, the automated cold storage control system will determine the control sequence of the refrigeration system based on the curve and through optimization algorithms such as model predictive control.

[0045] A refrigeration system typically includes key components such as a compressor unit, evaporator fan, and electronic expansion valve. A control sequence is a series of optimal operating instructions for each actuator in the refrigeration system over a period of time. Because the control sequence is arranged in time, it is a time series that includes the refrigeration control strategies to be taken at different future points in time.

[0046] A refrigeration control strategy refers to the specific settings or operating instructions for each actuator in the refrigeration system (e.g., the number of compressors operating, the number and speed of evaporator fans, the opening degree of the electronic expansion valve, etc.) at a specific moment or time period. For example, a refrigeration control strategy might specify that in the first 10 minutes, 3 compressors will be turned on, all fans will run at 80% speed, and the electronic expansion valve opening will be 75%; in the next 10 minutes, the strategy might adjust based on load changes to turn on 2 compressors and reduce the fan speed to 60%, etc. The determination of the control sequence aims to enable the cold storage to achieve the lowest energy consumption or other optimization goals while meeting temperature control objectives (such as set temperature and temperature uniformity).

[0047] S1330: The first cooling control strategy of the control sequence is sent to the cooling system for execution, and the real-time temperature status is updated based on the adjusted temperature, that is, the adjusted temperature is used as the initial condition for the next control cycle.

[0048] Once the control sequence is determined, the automated cold storage control system extracts the first refrigeration control strategy from the sequence—that is, the optimal control command for the current control cycle or the next short time step—and sends it to the refrigeration system for execution. This sending process can utilize control signals (such as analog signals, digital signals, or communication protocol commands) to transmit the commands to the controllers or actuators of the refrigeration system.

[0049] After the refrigeration system operates according to the received control strategy for a period of time, the temperature inside the automated cold storage will change. The automated cold storage control system will then collect the actual temperature data inside the cold storage again through sensors and update the real-time temperature status based on the adjusted temperature. This update operation means recording the latest temperature measurement value as the starting condition for prediction and optimization in the next control cycle, thus forming a closed-loop control process.

[0050] This application embodiment achieves dynamic temperature regulation of the automated cold storage through an iterative process of prediction-execution-update, enabling the automated cold storage to adapt to different storage conditions and improving its level of intelligence.

[0051] In one possible implementation, please see Figure 2 In step S130, after updating the real-time temperature status based on the adjusted temperature in each control cycle (step S1330), the following is also included: S1340: Determine the error between the adjusted temperature and the predicted temperature at the same time point determined by the cooling load prediction curve.

[0052] In each control cycle, after the automated cold storage control system executes the current refrigeration control strategy and updates the real-time temperature status, it compares the currently measured adjusted temperature (i.e., the latest real-time temperature status) with the predicted temperature at the corresponding time point obtained by the cold storage digital twin model based on the refrigeration load prediction curve at the beginning of the current control cycle, thereby determining the error between them. The error can be the absolute difference, relative difference, or other statistical indicators of temperature.

[0053] S1350: Correct the model parameters of the digital twin model of cold storage based on errors.

[0054] The model parameters of the cold storage digital twin model are fine-tuned using the error (i.e., model calibration) to further improve prediction accuracy and achieve a closed-loop process of prediction-feedback optimization. Then, the system enters the next control cycle, returning to step S1310 to achieve rolling forward optimization control.

[0055] After determining the error, the automated cold storage control system will use the error to correct the model parameters of the cold storage digital twin model. The correction process typically employs adaptive algorithms or machine learning techniques, such as Kalman filtering, extended Kalman filtering, recursive least squares, or parameter identification methods based on optimization algorithms.

[0056] Model parameters include, but are not limited to, heat transfer coefficient, air leakage rate, sensor calibration deviation, and refrigeration equipment performance parameters. The heat transfer coefficient may include the heat loss coefficient of the cold storage enclosure structure and the evaporator heat exchange efficiency. The air leakage rate refers to the changes in air leakage that may occur due to frequent opening or aging of the cold storage door seals. Sensor calibration deviation is used to compensate for sensor measurements. Refrigeration equipment performance parameters refer to the slight drift that may occur in the performance of components such as compressors, fans, and expansion valves during actual operation.

[0057] By calibrating these model parameters, the predictive capabilities of the cold storage digital twin model more closely reflect the actual operating conditions of the automated cold storage, thereby reducing model errors and improving the accuracy of subsequent predictions. For example, if the actual temperature is found to be consistently higher than the predicted temperature, it may mean that the heat loss of the cold storage is greater than the model estimates. In this case, the heat loss coefficient in the model will be adjusted accordingly to make the next prediction more accurate.

[0058] This application's embodiments introduce a rolling optimization and feedback correction mechanism to continuously learn and adapt to the dynamic changes and uncertainties in cold storage operation, and correct deviations caused by model errors or environmental disturbances in real time. This not only significantly improves the prediction accuracy and robustness of the cold storage digital twin model, enabling it to better cope with the complexity and variability of the actual environment, but also enhances the adaptability and long-term operational stability of the entire control system, providing a reliable guarantee for achieving continuous, efficient, and energy-saving temperature control.

[0059] In one possible implementation, the cargo area in the cold storage digital twin model is configured as a porous media domain or a solid domain.

[0060] The cargo area refers to the space in the digital twin model of a cold storage facility that simulates the actual interior of the cold storage for storing or stacking goods, such as the volume occupied by goods on shelves, in pallets, or in loose piles.

[0061] A porous media domain is a continuous medium comprising a solid framework and interconnected pores of fluid (typically air). Configuring cargo areas as porous media domains is suitable for stacked boxes or packaged goods, bulk agricultural products, or granular materials, where tiny gaps exist after close stacking, allowing for slow airflow and heat exchange.

[0062] The solid domain is a region composed of solid material with no fluid flow within it. This configuration is suitable for large, single-item cargo or highly compacted packaged goods. Large, single-item cargo includes large blocks of frozen meat or ice, where internal airflow is negligible. Highly compacted packaged goods have almost no internal airflow when stacked very tightly, or their internal heat transfer is mainly accomplished through solid conduction. The solid domain primarily simulates the heat conduction process within the cargo, as well as convective and radiative heat transfer between the cargo surface and the surrounding air.

[0063] To simulate the heat exchange processes of the different types of goods, the cold storage digital twin model endows the porous media domain and solids with realistic thermophysical properties, including the goods' density, specific heat capacity, and thermal conductivity. This allows the model to accurately calculate the heat storage and release processes within the goods, as well as the resistance of the goods to airflow. These parameters can be matched from a pre-set database based on the type of goods entering the warehouse (e.g., frozen food, fruits and vegetables, pharmaceuticals) or indirectly estimated through real-time data on the goods' temperature and humidity obtained from IoT devices. The thermophysical properties of the goods can realistically reflect their dynamic thermal inertia.

[0064] This application's embodiments configure the cargo area in the cold storage digital twin model as a porous medium domain or a solid domain, and endow it with realistic thermophysical properties. This can greatly improve the simulation accuracy of the cold storage digital twin model for the thermophysical behavior of cargo, enabling the model to accurately capture the dynamic thermal inertia of cargo. As a result, it can more accurately predict changes in the temperature field and heat load inside the cold storage in transient simulations, providing more reliable and refined data support for subsequent refrigeration system control. This effectively solves the prediction error problem caused by traditional models ignoring the dynamic thermal inertia of cargo.

[0065] In one possible implementation, such as Figure 3 As shown, in step S1310, the real-time warehousing plan and real-time temperature status are input into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model, specifically including: S1311: The digital twin model of cold storage assigns the thermophysical properties of the goods type to the area in the porous medium domain or solid domain corresponding to the storage location of the goods type. The start time of the assignment is the entry time of the goods type.

[0066] The cold storage digital twin model first identifies the type of goods, such as frozen meat, vegetables, and pharmaceuticals. For each type of goods, it queries a pre-set database or obtains its corresponding thermophysical properties through IoT devices. Subsequently, the cold storage digital twin model precisely assigns these specific thermophysical properties to the geometric area in the model corresponding to the storage location of that goods.

[0067] The start time for the assignment is precisely set to the warehousing time of the goods type. This means that in the CFD transient simulation, the thermophysical properties of these goods will only be activated and begin to affect the thermodynamic equilibrium in the model when the simulation time reaches the warehousing time. This dynamic assignment method ensures that the model can accurately reflect the transient thermal load shock caused by the warehousing of goods.

[0068] S1312: The digital twin model of cold storage determines the transient heat source based on the thermophysical properties of porous media or solid domains.

[0069] Once the cargo area is assigned the corresponding thermophysical properties and activated, the cold storage digital twin model can determine the transient heat source based on the thermophysical properties of the porous media domain or the solid domain.

[0070] S1313: The digital twin model of cold storage performs transient simulation based on real-time temperature status and transient heat sources to obtain the prediction results of temperature field changes inside the storage.

[0071] After determining the transient heat source, the cold storage digital twin model will use the real-time temperature state as the initial condition for transient simulation, and combine the transient heat source to perform computational fluid dynamics (CFD) transient simulation.

[0072] Transient simulations cover a predicted time range (e.g., several hours into the future) and dynamically calculate the detailed changes in air velocity, pressure, and temperature field inside the automated cold storage facility over time by continuously solving fluid flow and heat transfer equations. The simulation yields predicted temperature field changes within the cold storage, which can be represented as temperature values ​​at various points within the cold storage at different predicted time points, or as average temperature or temperature change curves at key measuring points. These predicted temperature field changes accurately reflect the impact of events such as the arrival of goods on the temperature distribution and uniformity within the cold storage facility.

[0073] S1314: The digital twin model of the cold storage determines the corresponding refrigeration load prediction result based on the prediction result of the temperature field change in the cold storage, and obtains the refrigeration load prediction curve.

[0074] Specifically, when determining the refrigeration load forecast, the total amount of heat that refrigeration equipment such as evaporators needs to remove from the cold storage environment to maintain or adjust the cold storage temperature to the target setpoint is determined. This heat includes all heat from the external environment (through the enclosure structure), internal equipment, infiltration airflow, and transient heat sources (goods).

[0075] The refrigeration load forecast result is a sequence that changes over time. The set of these sequence points constitutes the refrigeration load forecast curve, which clearly depicts the trend of the refrigeration capacity required by the refrigeration system to maintain the cold storage temperature within the target range over a period of time in the future.

[0076] The embodiments of this application efficiently and accurately convert real-time warehousing plans and real-time temperature status into parameters usable by the digital twin model, and generate cooling load prediction curves through transient simulation, thereby greatly improving the accuracy and timeliness of the system's prediction of future heat load.

[0077] In summary, this application effectively penetrates deep into the shelving by actively guiding airflow, reducing short circuits and dead zones, and significantly improving temperature uniformity. This uniform temperature field eliminates the need for the refrigeration system to overcool localized hotspots, potentially reducing system energy consumption by 5%-15%.

[0078] Based on the above, this application also provides a temperature control device for an automated cold storage facility. The temperature control device for the automated cold storage facility and the aforementioned temperature control method for the automated cold storage facility can be referred to and corresponded to each other.

[0079] As an example, such as Figure 4 As shown, the temperature control device for the automated cold storage provided in this application includes: The model building module 410 is used to build a digital twin model of the cold storage based on the three-dimensional geometry of the cold storage. The digital twin model of the cold storage performs transient temperature simulation based on computational fluid dynamics. Receiver module 420 is used to receive real-time inbound plans; The adjustment module 430 is used to adjust the temperature of the automated cold storage based on the real-time inbound plan and the real-time temperature status of the automated cold storage using a cold storage digital twin model. The cold storage digital twin model uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as the transient heat source for transient simulation.

[0080] This application embodiment builds a digital twin model of the cold storage based on the three-dimensional geometric structure of the cold storage. When using the digital twin model for transient simulation, the influence of goods in the warehousing plan on the temperature of the cold storage is considered, which improves the accuracy of temperature control. At the same time, the predictive mechanism is used to perform forward-looking intelligent temperature regulation, which solves the energy waste caused by control lag and over-cooling. It realizes active and precise regulation by combining feedforward and feedback, which significantly improves the quality and stability of temperature control in the cold storage.

[0081] In one possible implementation, the adjustment module 430 specifically includes: The refrigeration load prediction module 4310 is used to input the real-time storage plan and real-time temperature status into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model. The control sequence determination module 4320 is used to determine the control sequence of the refrigeration system based on the refrigeration load prediction curve. The control sequence includes multiple refrigeration control strategies arranged in time. The strategy distribution module 4330 is used to distribute the first cooling control strategy of the control sequence to the cooling system for execution, and update the real-time temperature status based on the adjusted temperature.

[0082] This application embodiment achieves dynamic temperature regulation of the automated cold storage through an iterative process of prediction-execution-update, enabling the automated cold storage to adapt to different storage conditions and improving its level of intelligence.

[0083] In one possible implementation, the adjustment module 430 further includes: Error determination module 4340 is used to determine the error between the adjusted temperature and the predicted temperature at the same time node determined by the cooling load prediction curve; The calibration module 4350 is used to calibrate the model parameters of the cold storage digital twin model based on errors.

[0084] This application's embodiments introduce a rolling optimization and feedback correction mechanism to continuously learn and adapt to the dynamic changes and uncertainties in cold storage operation, and correct deviations caused by model errors or environmental disturbances in real time. This not only significantly improves the prediction accuracy and robustness of the cold storage digital twin model, enabling it to better cope with the complexity and variability of the actual environment, but also enhances the adaptability and long-term operational stability of the entire control system, providing a reliable guarantee for achieving continuous, efficient, and energy-saving temperature control.

[0085] In one possible implementation, the cooling load prediction module 4310 is specifically used for: The cold storage digital twin model assigns the thermophysical properties of the goods type to the area in the porous medium domain or solid domain corresponding to the storage location of the goods type, and the start time of the assignment is the entry time of the goods type into the warehouse. The digital twin model of cold storage determines transient heat sources based on the thermophysical properties of porous media or solid domains; The digital twin model of the cold storage is based on real-time temperature status and transient heat sources to perform transient simulation and obtain the predicted results of temperature field changes inside the storage. The digital twin model of the cold storage determines the corresponding refrigeration load prediction result based on the prediction result of the temperature field change inside the storage, and obtains the refrigeration load prediction curve.

[0086] The embodiments of this application efficiently and accurately convert real-time warehousing plans and real-time temperature status into parameters usable by the digital twin model, and generate cooling load prediction curves through transient simulation, thereby greatly improving the accuracy and timeliness of the system's prediction of future heat load.

[0087] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call logic instructions in the memory 530 to execute a temperature control method for the automated cold storage, the method including: A digital twin model of the cold storage is built based on the three-dimensional geometric structure of the cold storage. The digital twin model of the cold storage is used to perform transient temperature simulation based on computational fluid dynamics. Receive real-time inbound plans; Using a digital twin model of cold storage, the temperature of the automated cold storage is regulated based on the real-time inbound plan and the real-time temperature status of the cold storage. The digital twin model of cold storage uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as the transient heat source for transient simulation.

[0088] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0089] On the other hand, this application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer is able to execute the temperature control method for the three-dimensional cold storage provided in the above embodiments. The method includes: A digital twin model of the cold storage is built based on the three-dimensional geometric structure of the cold storage. The digital twin model of the cold storage is used to perform transient temperature simulation based on computational fluid dynamics. Receive real-time inbound plans; Using a digital twin model of cold storage, the temperature of the automated cold storage is regulated based on the real-time inbound plan and the real-time temperature status of the cold storage. The digital twin model of cold storage uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as the transient heat source for transient simulation.

[0090] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the temperature control method for the three-dimensional cold storage provided in the above embodiments, the method comprising: A digital twin model of the cold storage is built based on the three-dimensional geometric structure of the cold storage. The digital twin model of the cold storage is used to perform transient temperature simulation based on computational fluid dynamics. Receive real-time inbound plans; Using a digital twin model of cold storage, the temperature of the automated cold storage is regulated based on the real-time inbound plan and the real-time temperature status of the cold storage. The digital twin model of cold storage uses the real-time temperature status as the initial condition and the goods in the real-time inbound plan as the transient heat source for transient simulation.

[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A temperature control method for a three-dimensional cold storage facility, characterized in that, include: A digital twin model of the cold storage is built based on the three-dimensional geometric structure of the cold storage, and the digital twin model of the cold storage is used to perform transient temperature simulation based on computational fluid dynamics; Receive real-time inbound plans; Using the aforementioned cold storage digital twin model, the temperature of the automated cold storage is adjusted based on the real-time inbound plan and the real-time temperature status of the automated cold storage; wherein, the cold storage digital twin model uses the real-time temperature status as the initial condition and uses the goods in the real-time inbound plan as a transient heat source for transient simulation.

2. The temperature control method for an automated cold storage facility according to claim 1, characterized in that, When using the digital twin model of the cold storage to adjust the temperature of the automated cold storage based on the real-time inbound plan and the real-time temperature status of the automated cold storage, each control cycle includes the following steps: The real-time inbound plan and the real-time temperature status are input into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model. The control sequence of the refrigeration system is determined based on the refrigeration load prediction curve, and the control sequence includes multiple refrigeration control strategies arranged in time. The first cooling control strategy of the control sequence is sent to the cooling system for execution, and the real-time temperature status is updated based on the adjusted temperature.

3. The temperature control method for a three-dimensional cold storage facility according to claim 2, characterized in that, After updating the real-time temperature state based on the adjusted temperature in each control cycle, the following further applies: Determine the error between the adjusted temperature and the predicted temperature at the same time point determined by the cooling load prediction curve; The model parameters of the cold storage digital twin model are corrected based on the error.

4. The temperature control method for a three-dimensional cold storage facility according to claim 2, characterized in that, In the digital twin model of the cold storage, the cargo area is configured as a porous media domain or a solid domain.

5. The temperature control method for an automated cold storage facility according to claim 4, characterized in that, The real-time inbound plan includes at least one type of goods, quantity of goods, inbound time, and storage location.

6. The temperature control method for an automated cold storage facility according to claim 5, characterized in that, The real-time inbound plan and the real-time temperature status are input into the cold storage digital twin model to obtain the refrigeration load prediction curve output by the cold storage digital twin model, specifically including: The cold storage digital twin model assigns the thermophysical properties of the goods type to the area in the porous medium domain or solid domain corresponding to the storage location of the goods type, and the start time of the assignment is the entry time of the goods type into the warehouse; The digital twin model of the cold storage determines the transient heat source based on the thermophysical properties of the porous media domain or solid domain; The digital twin model of the cold storage performs transient simulation based on the real-time temperature status and the transient heat source to obtain the predicted results of the temperature field change inside the storage. The digital twin model of the cold storage determines the corresponding refrigeration load prediction result based on the predicted temperature field change result inside the storage, and obtains the refrigeration load prediction curve.

7. A temperature control device for a three-dimensional cold storage facility, characterized in that, include: The model building module is used to build a digital twin model of the cold storage based on the three-dimensional geometric structure of the cold storage. The digital twin model of the cold storage performs transient temperature simulation based on computational fluid dynamics. The receiving module is used to receive real-time inbound plans; The adjustment module is used to adjust the temperature of the automated cold storage based on the real-time inbound plan and the real-time temperature status of the automated cold storage using the cold storage digital twin model; wherein, the cold storage digital twin model uses the real-time temperature status as the initial condition and uses the goods in the real-time inbound plan as a transient heat source for transient simulation.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the temperature control method for the automated cold storage as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, wherein a computer program is stored on the non-transitory computer-readable storage medium, characterized in that, When the computer program is executed by the processor, it implements the temperature control method for the automated cold storage as described in any one of claims 1 to 6.

10. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the temperature control method for the automated cold storage as described in any one of claims 1 to 6.

Images