Model prediction-based assembled packing box room temperature dynamic regulation and control method and system

Abstract

The invention discloses an assembled packing box room temperature dynamic regulation and control method and system based on model prediction, and relates to the technical field of temperature control. The method comprises the steps of building a heat conduction model based on material and structure information of a target model container room; acquiring heat transfer data of the target model of container room under different illumination, temperature and stacking modes, and correcting to obtain a dynamic heat transfer model; geographic information and a stacking mode are deployed in combination with the target box house, illumination parameters of the dynamic heat transfer model are optimized, and an exclusive heat transfer model is generated; establishing a meteorological baseline according to the historical meteorological data of the deployment position, and obtaining future environmental meteorological data by combining with predicted meteorological information correction; and inputting real-time and preset temperature and future environmental meteorological data to the exclusive model, calculating a time sequence heat difference value in a future time period, and configuring the refrigerating capacity or heating capacity of the temperature control equipment according to the time sequence heat difference value. According to the invention, the accuracy and stability of temperature regulation and control of the assembly type packaging box room are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of temperature control technology, specifically to a method and system for dynamic temperature control of modular prefabricated container houses based on model prediction. Background Technology

[0002] With the rapid development of the prefabricated building industry, modular container houses, due to their convenient assembly and disassembly and high mobility, are widely used in temporary offices on construction sites, temporary resettlement after disasters, and field work camps. The demand for comfortable and energy-efficient indoor temperature control in these container houses is becoming increasingly prominent. Existing container house temperature control technologies mostly adopt fixed threshold triggering control strategies, relying on standardized building heat transfer models to guide equipment operation and achieve basic temperature control functions.

[0003] However, the deployment locations, orientations, surrounding obstructions, and stacking methods of prefabricated container houses vary greatly, resulting in significant differences in their susceptibility to solar radiation and external climate. Traditional methods using general static models cannot accurately reflect dynamic and individualized thermal characteristics. Traditional temperature control systems are passive response controls, only initiating adjustments when the indoor temperature deviates from the set value, which suffers from delays, overshoots, and high energy consumption. They are unable to cope with drastically changing outdoor weather conditions to achieve a balance between stability and energy saving, resulting in insufficient accuracy and stability in temperature control of prefabricated container houses. Summary of the Invention

[0004] This invention provides a method and system for dynamic temperature control of prefabricated container houses based on model prediction, aiming to solve the technical problem of insufficient accuracy and stability of temperature control in prefabricated container houses in the prior art.

[0005] In view of the above problems, the present invention provides a method and system for dynamic temperature control of modular prefabricated container houses based on model prediction.

[0006] In a first aspect, the present invention provides a method for dynamic temperature control of modular prefabricated container houses based on model prediction, including: Based on the material and structural information of the target model container house, a thermal conductivity model of the target model container house is built; The heat transfer data of the target model container house under different light, temperature and stacking methods are obtained, and a dynamic heat transfer model of the target model container house is built based on the heat conduction model. Obtain the deployment geographic information of the target container belonging to the target model, wherein the deployment geographic information includes at least latitude, orientation, and light shading information; Based on the deployment geographic information and the stacking method of the target container, the illumination parameters in the dynamic heat transfer model are limited to obtain the exclusive heat transfer model of the target container. Obtain historical meteorological information of the target container deployment location, and based on the historical meteorological information, obtain meteorological baseline information of the deployment location; Obtain the predicted meteorological information of the target container deployment location, and correct the meteorological baseline information for a future preset period based on the predicted meteorological information to obtain future environmental meteorological information; Obtain the preset temperature information and real-time temperature information of the target container; Based on the current moment and the dedicated heat transfer model, according to the preset temperature information, real-time temperature information and future environmental meteorological information, the time-series heat difference required for the target container to maintain the preset temperature information in the future preset time period is obtained; Based on the time-series heat difference, configure the cooling or heating capacity of the container room temperature control equipment for a future preset time period.

[0007] Secondly, this invention provides a model-predictive-based dynamic temperature control system for modular prefabricated container houses, comprising: The thermal conductivity model building module is used to build a thermal conductivity model of the target model container house based on the material and structural information of the target model container house; The dynamic heat transfer modeling module is used to acquire heat transfer data of the target model container house under different light, temperature and stacking methods, and build a dynamic heat transfer model of the target model container house based on the heat conduction model. The geographic information acquisition module is used to acquire the deployment geographic information of the target container belonging to the target model container, and the deployment geographic information includes at least latitude, orientation, and light shading information; The heat transfer model generation module is used to limit the illumination parameters in the dynamic heat transfer model based on the deployment geographic information and the stacking method of the target container, so as to obtain the exclusive heat transfer model of the target container. The meteorological baseline acquisition module is used to acquire historical meteorological information of the target container deployment location, and based on the historical meteorological information, acquire meteorological baseline information of the deployment location; The weather forecast correction module is used to obtain the forecast weather information of the target container deployment location, and correct the meteorological baseline information for a future preset period based on the forecast weather information to obtain future environmental weather information. The temperature information acquisition module is used to acquire the preset temperature information and real-time temperature information of the target container. The heat demand prediction module is used to obtain the time-series heat difference required for the target container to maintain the preset temperature information within a preset time period in the future, based on the current time and the dedicated heat transfer model, according to the preset temperature information, real-time temperature information and future environmental meteorological information. The temperature control equipment configuration module is used to configure the cooling or heating capacity of the container temperature control equipment within a future preset time period based on the time-series heat difference.

[0008] One or more technical solutions provided in this invention have at least the following technical effects or advantages: This invention provides a model-based prediction-based method and system for dynamic temperature control of modular prefabricated container houses. By integrating the physical characteristics of the container houses, specific geographical information on their deployment, and stacking methods, a highly personalized dynamic heat transfer model is constructed. Combined with historical and predicted meteorological information, a forward-looking heat difference calculation is achieved, accurately configuring the cooling or heating capacity of temperature control equipment. This effectively solves the problems of insufficient accuracy and passive control mode of existing models, improves the accuracy and stability of container house temperature control, and reduces equipment energy consumption and losses, meeting the temperature control needs of modular prefabricated container houses in diverse application scenarios. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A schematic flowchart illustrating the method for dynamic temperature control of modular prefabricated container houses based on model prediction provided in an embodiment of the present invention; Figure 2 A schematic diagram of the model-predictive-based dynamic temperature control system for modular prefabricated container houses provided in an embodiment of the present invention; The components represented by each number in the attached diagram are explained below: The module includes: 11 for building a heat conduction model, 12 for dynamic heat transfer modeling, 13 for geographic information acquisition, 14 for heat transfer model generation, 15 for meteorological baseline acquisition, 16 for meteorological forecast correction, 17 for temperature information acquisition, 18 for heat demand forecasting, and 19 for temperature control equipment configuration. Detailed Implementation

[0011] This invention provides a model-based prediction-based method and system for dynamic temperature control of prefabricated container houses, which addresses the technical problem of insufficient accuracy and stability in temperature control of prefabricated container houses in existing technologies.

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0013] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0014] Example 1, as Figure 1 As shown, this invention provides a method for dynamic temperature control of prefabricated modular container houses based on model prediction. The method includes: S100: Based on the material and structural information of the target model container house, build a thermal conductivity model of the target model container house.

[0015] In this embodiment of the invention, a thermal conductivity model of the target model modular housing is constructed based on its material and structural information. Establishing an accurate thermal conductivity model is the physical foundation of the entire temperature dynamic control method. As a thermal system, the internal temperature change of a modular housing depends on the heat transferred in or lost through the enclosure structure such as walls, doors, and windows. Without a theoretical model that reflects the specific material and structural thermal characteristics, all subsequent predictions and controls will lack a scientific basis and cannot achieve precise control. Therefore, this step aims to construct a calculable, parameterized mathematical model of the modular housing's thermal dynamics based on physical principles, providing a core computational engine for subsequent steps.

[0016] Step S100 in the method provided in this embodiment of the invention includes: Obtain the material and structural information of the target model container house. The material information includes at least the thickness of the color steel plate, the thickness and density of the sandwich insulation material, the thermal conductivity parameters of the color steel plate, the thermal conductivity parameters of the sandwich insulation material, and the glass type. The structural information includes at least the door and window dimensions and the door and window positions. Based on the structural information, the target model container house is decomposed into multiple thermal nodes, which include at least wall nodes and door and window nodes; Based on the material information, calculate the thermal resistance and thermal capacity of the plurality of thermal nodes; wherein, the thermal resistance includes thermal conductivity resistance, surface heat transfer resistance, and radiative heat transfer resistance; Based on the connection relationship between thermal nodes, multiple thermal balance equations are established to obtain the thermal conductivity model of the target type container house.

[0017] First, obtain the material and structural information of the target model container house. The material information includes at least the thickness of the color steel plate, the thickness and density of the sandwich insulation material, the thermal conductivity parameters of the color steel plate and the sandwich insulation material, and the glass type. The structural information includes at least the door and window dimensions and locations. Material information refers to the physical properties of each component of the container house, directly affecting the heat transfer rate. Structural information refers to the geometric dimensions and component layout of the container house, determining the path and area of ​​heat transfer. This is done by reviewing the design drawings, material procurement contracts, and factory technical specifications of the target model container house. If the drawing information is incomplete, actual measurements of a similar model container house can be used to supplement it. It is essential to ensure that the material information covers all enclosure structure materials, and that the structural information clearly defines the precise layout of key components.

[0018] For example, the target model of the container house is a standard 3m × 6m modular prefabricated container house. Material information: 0.5mm thick color steel plate, thermal conductivity 50W / (m²). K); the sandwich insulation material is rock wool, 50mm thick, 120kg / m3 density, and 0.04W / (m3). K); the windows and doors are double-glazed with a thermal conductivity of 0.7 W / (m²). K). Structural information: This type of container house is equipped with a single sliding door and two fixed windows. The sliding door measures 1m × 2m and is located in the middle of the south wall. Each fixed window measures 0.8m × 1m and is located in the upper middle of the east and north walls, respectively. The walls are integrally spliced, the roof is a single-slope structure, and the ground is a precast concrete slab.

[0019] Secondly, based on the structural information, the target model container house is decomposed into multiple thermal nodes, which include at least wall nodes and door / window nodes. A thermal node is the smallest heat transfer unit in the container house's enclosure structure, broken down according to the uniformity of its thermal properties. Each node has a consistent material composition and heat transfer characteristics, facilitating accurate calculation of local heat transfer processes. These nodes are divided into wall nodes and door / window nodes. Wall nodes include the four walls, roof, and floor; door / window nodes include all doors and windows. Thermal nodes are defined based on the symmetry of the container house structure and the uniformity of material distribution. Components with significant differences in heat transfer characteristics are prioritized for separation into independent nodes, ensuring no significant differences in thermal properties within each node. For walls containing doors and windows, the door and window areas are separated separately, with the remaining wall portion treated as independent wall nodes.

[0020] For example, based on the structural information of a standard 3m×6m prefabricated modular container house, it is decomposed into 9 thermal nodes: east wall node, south wall node (excluding the door opening area), west wall node, north wall node (excluding the window opening area), roof node, ground node, door node, east side window node, and north side window node. The area of ​​the south wall node = total south wall area - door opening area = 6m×2.8m - 1m×2m = 14.8m² 2Each door node corresponds to a 1m×2m door area.

[0021] Next, based on the material information, the thermal resistance and heat capacity of the multiple thermal nodes are calculated; wherein, the thermal resistance includes conductive thermal resistance, surface heat transfer thermal resistance, and radiative heat transfer thermal resistance. Thermal resistance characterizes the ability of a material or structure to impede heat transfer; the higher the value, the stronger the thermal insulation performance. Conductive thermal resistance This refers to the material's inherent thermal insulation capacity; surface thermal resistance. This refers to the resistance to heat transfer between the material surface and the air; radiative heat transfer resistance. Thermal resistance refers to the resistance to radiative heat transfer between the material surface and its surroundings; the total thermal resistance R is the sum of these three factors. Heat capacity C characterizes the material's ability to store heat; the larger the value, the more heat the material needs to absorb or release to change its temperature, making it a core parameter for calculating nodal temperature changes. Thermal resistance calculation: thermal conductivity resistance. δ represents the material thickness, λ represents the material's thermal conductivity parameter; surface heat transfer resistance. Referencing the thermal design code for civil buildings, the value is 0.04m on the indoor side. 2 K / W, 0.03m on the outdoor side 2 K / W; thermal resistance of radiative heat transfer ε is the surface emissivity of the material, taken as 0.8. The blackbody radiation coefficient is taken as 5.67 W / (m²). 2 K 4 Total thermal resistance Heat capacity calculation: C = m × c, where m is the nodal mass and c is the specific heat capacity of the material; nodal mass m = nodal volume × material density; if the nodal is composed of multiple materials, calculate the heat capacity of each material separately and then sum them.

[0022] For example, taking the south wall node of a standard 3m×6m prefabricated container house as an example: thermal conductivity and thermal resistance. =1.25m 2 K / W; Surface heat transfer resistance =0.04 + 0.03 = 0.07m 2 K / W; thermal resistance of radiative heat transfer =0.22m 2 K / W; Total thermal resistance R = 1.25 + 0.07 + 0.22 = 1.54 m 2 K / W. Color steel sheet volume = 0.0148m³ 3 Mass m1 = 0.0148 × 7850 = 116.18 kg, specific heat capacity c1 = 460 J / (kg) K), heat capacity C1 = 116.18 kg × 460 J / (kg K)≈53.44kJ / K; rock wool volume=0.74m³ 3 Mass m2 = 0.74 × 120 = 88.8 kg, specific heat capacity c2 = 1000 J / (kg) K), heat capacity C2 = 88.8 kg × 1000 J / (kg K) = 88.8 kJ / K; Total heat capacity of the south wall node C = 53.4 + 88.8 = 142.24 kJ / K.

[0023] Finally, based on the connection relationships between thermal nodes, multiple heat balance equations are established to obtain the thermal conductivity model of the target type of container house. The connection relationships between thermal nodes refer to the heat transfer paths between them, such as convective heat transfer between wall nodes and indoor air nodes, heat conduction between adjacent wall nodes, and radiative heat transfer between door / window nodes and outdoor air. The heat balance equation describes the balance relationship of heat input - heat output = heat stored / released by the node per unit time for a single thermal node; it is a mathematical expression characterizing the temperature change law of the node. The thermal conductivity model is a set of equations formed by combining the heat balance equations of all thermal nodes, which can accurately characterize the overall heat transfer law of the container house. The heat input sources and output destinations of each thermal node are identified; based on the law of conservation of energy, a heat balance equation is established for each thermal node; and the equations of all thermal nodes are combined to form a complete set of equations, which is the thermal conductivity model of the target type of container house.

[0024] For example, taking the south wall node of a standard 3m×6m prefabricated container house as an example, its heat input includes outdoor air convection heat transfer. Outdoor environmental radiative heat exchange Heat output includes heat transfer through convection to indoor air. Heat conduction to the east wall node Heat conduction to the west wall node Based on this, the heat balance equation is established: Where C is the total heat capacity of the south wall node, 142.24 kJ / K; This represents the temperature change rate at the south wall nodes; each heat term can be quantified using the corresponding heat transfer formula, such as the convective heat transfer formula Q=h A ΔT, where h is the heat transfer coefficient, A is the heat transfer area, and ΔT is the temperature difference. Similarly, heat balance equations are established for the remaining 8 hot nodes. By combining the 9 equations, the thermal conductivity model of a 3m×6m standard prefabricated modular container house can be obtained.

[0025] In this embodiment of the invention, by selectively collecting material and structural information of the target model container house, the thermal node is disassembled, thermal property parameters are calculated, and a set of thermal balance equations is constructed. This results in the establishment of a heat conduction model that closely matches the characteristics of the target model container house, overcoming the limitation of general heat transfer models that ignore the individual attributes of the container house. This achieves a high degree of matching with the actual thermal conduction characteristics of the container house, effectively improving the accuracy of heat transfer calculations. Through the refined division of thermal nodes, the error amplification problem in the overall modeling mode is avoided, and the detail of the heat transfer law representation is enhanced. At the same time, the established heat conduction model provides solid theoretical support for the subsequent correction and optimization of dynamic heat transfer models and the customized development of dedicated heat transfer models, ensuring that subsequent model iterations always revolve around the core characteristics of the target model container house.

[0026] S200: Obtain heat transfer data of the target model container house under different light, temperature and stacking methods, and build a dynamic heat transfer model of the target model container house based on the heat conduction model.

[0027] In this embodiment of the invention, heat transfer data of the target model container house under different lighting, temperature, and stacking methods are obtained, and a dynamic heat transfer model of the target model container house is built based on the heat conduction model. The heat conduction model built in S100 is a static theoretical model, which is constructed only based on the material and structural parameters of the container house. It does not consider the impact of dynamic environmental factors such as changes in light intensity, fluctuations in indoor and outdoor temperature, and stacking deployment on the heat transfer process in actual applications, and cannot accurately match the actual operating conditions of prefabricated container houses. At the same time, conventional house temperature control technology is not designed for the common stacking deployment characteristics of container houses, and it is difficult to adapt to its unique heat transfer law. In scenarios such as construction sites and temporary resettlement sites, changes in lighting, temperature, and stacking methods will significantly change the heat transfer characteristics of prefabricated container houses. The calculation results of the static model deviate from the actual heat transfer situation and cannot support subsequent accurate temperature control. Therefore, it is necessary to collect heat transfer data under multiple dynamic operating conditions to correct the static heat conduction model and build a dynamic heat transfer model that fits the actual operating scenario of container houses, so as to achieve dynamic and accurate characterization of the heat transfer process.

[0028] Step S200 in the method provided in this embodiment of the invention includes: Under various lighting conditions, the surface temperature of the target model container, the indoor air temperature, and the solar radiation intensity were measured to obtain light-induced heat transfer data. Under controlled temperature conditions, different indoor and outdoor temperature differences were set for the target model container house, and the steady-state heat flux and the time to reach steady state of the target model container house were measured as temperature heat transfer data; Under simulated actual stacking conditions, the heat transfer effect data between the contact surfaces of the containers that are in contact with each other is measured and used as the stacking heat transfer data. Based on the light heat transfer data, air temperature heat transfer data, and stacked heat transfer data, the parameters of the heat conduction model are corrected to obtain the dynamic heat transfer model.

[0029] First, under various lighting conditions, the surface temperatures of the target model container house (interior and exterior), indoor air temperature, and solar radiation intensity were measured to obtain solar heat transfer data. "Various lighting conditions" refers to scenarios with different solar radiation intensities that might be encountered in the actual deployment of container houses, such as sunny midday, cloudy days, overcast days, and low-angle sunlight in the early morning and late evening. Solar heat transfer data is measured data characterizing the impact of sunlight on the heat transfer of the container house, including the surface temperatures of the container house's envelope, indoor air temperature, and the corresponding solar radiation intensity at different times. This data reflects the heat absorption and transfer patterns of the container house under different lighting intensities. Temperature sensors were deployed on the surface temperatures of the container house's envelope and the interior space at key locations in an open outdoor area or an artificial light source simulation laboratory. Solar radiation intensity monitoring equipment was also installed. Different lighting scenarios were simulated or selected sequentially, and monitoring was continuously conducted under each scenario until the data stabilized. The temperature and corresponding solar radiation intensity at each monitoring point were recorded simultaneously, and the data were compiled into a solar heat transfer dataset.

[0030] For example, measurements were conducted on a 3m×6m standard modular container house under three typical lighting scenarios: Sunny noon scenario: strong solar radiation intensity, with simultaneous recording of the temperature of the outer surface of the south wall, the inner surface of the south wall, the indoor air temperature, and the real-time radiation intensity; Cloudy scenario: fluctuating solar radiation intensity, with continuous monitoring and recording of dynamic data on temperature changes at each monitoring point as a function of radiation intensity; Overcast scenario: weak solar radiation intensity, with recording of temperature parameters and radiation intensity under stable conditions; Finally, complete solar heat transfer data under the three lighting scenarios were compiled.

[0031] Secondly, under controllable temperature conditions, different indoor and outdoor temperature differences were set for the target model container house. The steady-state heat flux and the time required to reach steady state were measured as temperature-based heat transfer data. Controllable temperature conditions refer to the precise control of indoor and outdoor temperatures through equipment such as artificial climate chambers to create different indoor and outdoor temperature difference conditions. This allows for precise isolation of other interfering factors, enabling the study of the impact of temperature differences on the heat transfer of the container house. Steady-state heat flux refers to the heat flow rate at which the heat flow into and out of any area reaches dynamic equilibrium when the temperature at each point does not change over time. It characterizes the heat transfer capacity of the container house under specific temperature differences. Temperature-based heat transfer data are measured data reflecting the heat transfer characteristics of the container house under different indoor and outdoor temperature differences, including steady-state heat flux and the time required to reach thermal steady state. This clarifies the correlation between temperature difference and the heat transfer efficiency of the container house. A standard 3m×6m modular container house is placed in an artificial climate chamber. The indoor temperature is set to a commonly used comfortable temperature for container houses, such as the human body's comfortable ambient temperature of 26℃, through the climate chamber control system. Then, different outdoor temperatures are set sequentially to form a gradient of indoor and outdoor temperature difference conditions. Heat flow meters are installed on the outside of the container house's enclosure structure to monitor changes in heat flow in real time, and the temperature at each monitoring point is recorded. After the heat flow and temperature stabilize, the steady-state heat flow value under this condition and the time from start-up to reaching steady state are recorded. The above operation is repeated to complete the measurement of all temperature difference conditions and to form an air temperature and heat transfer dataset.

[0032] For example, the indoor temperature of the container is set to constant room temperature, and the outdoor temperature is set sequentially to low temperature in winter, normal temperature in spring and autumn, and high temperature in summer, forming three typical indoor-outdoor temperature difference conditions: Condition 1: Low outdoor temperature, resulting in a large temperature difference between indoors and outdoors, and steady-state heat flow and the time to reach steady state are monitored and recorded; Condition 2: Normal outdoor temperature, resulting in a small temperature difference between indoors and outdoors, and the corresponding steady-state heat flow and the time to reach steady state are recorded; Condition 3: High outdoor temperature, resulting in an inverse temperature difference between indoors and outdoors, and steady-state heat flow and the time to reach steady state are recorded simultaneously; finally, complete air temperature and heat transfer data under the three conditions are obtained.

[0033] Furthermore, under simulated actual stacking conditions, the heat transfer impact data between the contact surfaces of the container houses is measured as stacking heat transfer data. Simulating actual stacking conditions means recreating common stacking methods of container houses in actual deployment, such as double-layer stacking or multi-row side-by-side stacking, to build a stacking test environment consistent with the actual scenario. Stacking heat transfer data are measured data characterizing the heat transfer characteristics of the contact surfaces of the container houses under stacking conditions, including the temperature and heat flux density on both sides of the contact surface, which can reflect the additional impact of stacking on the heat transfer of the container houses, such as heat conduction and heat loss at the contact surfaces. Using modular prefabricated container houses of the same model as the target container house, a common double-layer stacking test device was constructed. Temperature sensors and heat flux meters were evenly distributed on the contact surfaces of the upper and lower containers, ensuring that the sensors were in close contact with the contact surfaces. Continuous monitoring was conducted at room temperature, recording the temperature at the bottom of the upper container, the temperature at the top of the lower container, and the heat flux density data of the contact surfaces. If more stacking scenarios need to be covered, multiple rows of parallel stacking devices can be constructed, and the above measurement process can be repeated to compile a complete stacking heat transfer dataset.

[0034] For example, a double-layer stacking test environment of a 3m×6m standard modular prefabricated container house was constructed, with the contact surface being the contact area between the bottom of the upper container house and the top of the lower container house: a total of 5 sets of temperature sensors were arranged at the four corners and the center of the contact surface to simultaneously monitor the temperature of the bottom of the upper layer and the top of the lower layer; a heat flow meter was arranged at the center of the contact surface to monitor the heat flow density of the contact surface; after continuous monitoring until the data stabilized, the temperature values ​​of each sensor and the heat flow density values ​​of the heat flow meter were recorded to form the stacking heat transfer data under this stacking method.

[0035] Finally, based on the aforementioned light-induced heat transfer data, air-temperature heat transfer data, and stacking heat transfer data, the thermal conductivity model is parameter-calibrated to obtain the dynamic heat transfer model. Parameter calibration refers to substituting the measured light, air, and stacking heat transfer data into the static thermal conductivity model and adjusting key parameters such as thermal resistance and heat capacity through mathematical algorithms to make the calculation results consistent with the measured data. The dynamic heat transfer model, based on the static thermal conductivity model, incorporates dynamic influencing factors such as light, air, and stacking, and can adaptively adjust the calculation results according to changes in environmental parameters, accurately characterizing the dynamic heat transfer process of the container. First, the heat transfer data from light, air temperature, and stacking are preprocessed to remove outliers and standardize the data. Then, the preprocessed dataset is substituted into the static heat conduction model built on S100, and the parameters such as thermal resistance and heat capacity in the model are iteratively adjusted using a data fitting algorithm until the deviation between the temperature, heat flow, and other parameters calculated by the heat conduction model and the measured data reaches a stable and reasonable range. Finally, dynamic influencing factors such as light intensity, air temperature difference, and stacking contact thermal resistance are embedded into the corrected model to construct a dynamic heat transfer model that can respond to dynamic changes in the environment.

[0036] For example, three types of heat transfer preprocessing data of a 3m×6m standard modular container house are substituted into its static heat conduction model: Based on the light heat transfer data, the parameters related to radiation heat transfer in the model are adjusted so that the temperature of the south wall surface calculated by the model is consistent with the measured temperature under different light intensities; Based on the air temperature heat transfer data, the thermal resistance parameters in the model are corrected to ensure that the steady-state heat flow calculated by the model matches the measured steady-state heat flow under different temperature differences; Based on the stacking heat transfer data, the stacking contact thermal resistance parameter is added to the model to accurately characterize the heat transfer loss of the contact surface; After completing all parameter adjustments and dynamic factor embedding, the dynamic heat transfer model of this type of container house can be obtained. This dynamic heat transfer model can dynamically output accurate heat transfer calculation results according to the changes in actual light, air temperature and stacking status.

[0037] In this embodiment of the invention, by collecting heat transfer data of prefabricated container houses under different lighting, temperature, and stacking conditions, the static heat conduction model is parameter-corrected and dynamic influencing factors are embedded, successfully constructing a dynamic heat transfer model. This overcomes the limitation of static heat conduction models being unable to respond to dynamic environmental changes, achieving a dynamic and accurate representation of the actual heat transfer process of container houses. Targeted collection of heat transfer data under stacking conditions fully adapts to common stacking deployment scenarios of container houses, differing from the generalized design of conventional house temperature control technologies, thus improving the model's adaptability to the specific application scenarios of container houses. Simultaneously, the dynamic heat transfer model accurately captures the correlation between environmental factors and container house heat transfer, providing a dynamic adaptation foundation for subsequently customizing a dedicated heat transfer model based on deployment geographic information, ensuring that subsequent temperature control strategies fit the actual operating conditions of container houses.

[0038] S300: Obtain the deployment geographic information of the target container belonging to the target model container, wherein the deployment geographic information includes at least latitude, orientation, and light shading information.

[0039] In this embodiment of the invention, the deployment geographic information of the target container house belonging to the target model is obtained. This deployment geographic information includes at least latitude, orientation, and sunlight shading information. Prefabricated container houses are often flexibly deployed in different regions according to the needs of construction sites, temporary resettlement points, etc. The deployment geographic information directly determines the duration, intensity, and shading of solar radiation received, thus significantly affecting heat transfer characteristics. Therefore, it is necessary to obtain the deployment geographic information of the target container house to provide scenario-based parameter support for subsequent customized heat transfer models. The precise latitude of the target container house is obtained through GPS positioning equipment; the orientation of the container house is measured using a compass or electronic orientation instrument, with the wall normal direction as the reference; sunlight shading information is recorded through on-site surveys, including the location and height of surrounding buildings, trees, mountains, and other shading objects, as well as the duration and extent of shading on the walls of each orientation of the container house. Finally, a complete deployment geographic information dataset is compiled.

[0040] For example, taking the deployment of a 3m×6m standard modular container house at a construction site as an example: GPS positioning shows that the latitude of the deployment location is 30°N, a subtropical region with a large solar altitude angle and strong radiation in summer and a small solar altitude angle in winter; the main orientation of the container house is due south, with the south wall facing the direct sunlight, receiving the most radiation; on-site investigation found that there is an 8-meter-high temporary office building 10 meters north of the container house, which will block the sunlight on the north wall from 9 am to 3 pm in winter, and a row of 3-meter-high scaffolding 5 meters east of the container house, which only blocks the sunlight on the bottom of the east wall for a short time at noon in summer. The above latitude, orientation and blocking information are compiled into the deployment geographical information of the target container house.

[0041] In this embodiment of the invention, by accurately acquiring deployment geographic information, the gap of lack of specific scene adaptability in the preceding dynamic model is filled, enabling subsequent model customization to be specifically matched with the regional and surrounding environmental characteristics of the target container house. Unlike the generalized design of conventional house temperature control technology, it fully fits the core characteristics of the mobile deployment of prefabricated container houses, providing a precise basis for the illumination parameters in the subsequent dynamic heat transfer model. At the same time, detailed illumination shading information can help the model accurately predict the actual illumination conditions at different times, reduce the heat transfer calculation deviation caused by shading, and further improve the scene adaptability and accuracy of the subsequent temperature control strategy.

[0042] S400: Based on the deployment geographic information and the stacking method of the target container, the illumination parameters in the dynamic heat transfer model are limited to obtain the exclusive heat transfer model of the target container.

[0043] In this embodiment of the invention, based on the deployment geographic information and the stacking method of the target container houses, the illumination parameters in the dynamic heat transfer model are limited to obtain a dedicated heat transfer model for the target container house. Although the dynamic heat transfer model built by S200 incorporates dynamic influencing factors such as illumination, temperature, and stacking, it is still a general dynamic model adapted to the target container house model and has not been customized for the specific deployment scenario and actual stacking state of a single target container house. The characteristic of prefabricated container houses is mobile deployment; the latitude, orientation, shading conditions, and stacking methods of different deployment locations vary, directly leading to different solar radiation intensity and distribution patterns received by the container houses, thus affecting the heat transfer process. Therefore, it is necessary to combine the deployment geographic information and actual stacking method of the target container houses to precisely limit the illumination parameters of the dynamic heat transfer model, upgrading the general dynamic model to a dedicated heat transfer model that fits the operating scenario of a single target container house, ensuring that the heat transfer calculation is completely matched with the actual operating conditions of the target container house.

[0044] Step S400 in the method provided in this embodiment of the invention includes: Obtain the stacking method of the target container, wherein the stacking method includes at least the stacking contact area; Calculate the deployment azimuth and tilt angle of the target container relative to the sun based on its orientation. Based on the latitude and real-time time, the solar altitude angle and solar azimuth angle are calculated using a solar position algorithm; Based on the deployment azimuth, deployment tilt, solar altitude angle, solar azimuth, and light shading information, sunlight is decomposed into three radiation components: direct, scattered, and ground reflection. Based on these three radiation components, the effective projected radiation intensity of each surface of the target container is calculated. The light shading information is directly used to reduce or eliminate the direct radiation component on the corresponding container surface. Obtain the annual solar activity information of the target container deployment location, and then calculate the annual effective projected radiation intensity of the target container deployment location based on the annual solar activity information; The effective projected radiation intensity throughout the year and the stacking method are updated to the dynamic heat transfer model to obtain the exclusive heat transfer model of the target container.

[0045] First, the stacking method of the target container units is obtained, including at least the stacking contact area. The stacking method refers to the actual stacking configuration of the target container units in deployment, including the number of layers and stacking arrangement, which affects heat transfer on the contact surfaces and light reception on each surface. The stacking contact area refers to the actual contact area between adjacent container surfaces in the stacked state, and is a key parameter for calculating heat transfer loss and light obstruction range. By conducting on-site inspections of the target container unit deployment site, information such as the number of layers and arrangement is recorded. Combined with the container unit size parameters, the actual contact area between adjacent containers is calculated. If stacked vertically, the contact area is typically the projected area of ​​the top / bottom of the container; if stacked side-by-side, the contact area is the contact area of ​​adjacent walls, thus forming complete stacking method information. For example, if the on-site inspection reveals that the target container units are stacked in a double-layer vertical configuration, with the bottom of the upper container unit completely flush with the top of the lower container unit without offset, and considering the container dimensions, the stacking contact area = 6m × 3m = 18m². 2 .

[0046] Secondly, based on the orientation of the target container, the deployment azimuth and tilt angles relative to the sun are calculated. The deployment azimuth is the angle corresponding to the main orientation of the target container, starting at 0° for true north and increasing clockwise. It characterizes the horizontal orientation of the container relative to the sun's trajectory. The deployment tilt angle is the angle between each surface of the target container and the horizontal plane. It characterizes the tilt angle of the container's surface relative to the direction of solar radiation and directly affects the efficiency of solar radiation reception. Using the main orientation of the target container, such as the normal direction of the south wall, as a reference, and combining orientation data measured by a compass, the deployment azimuth is converted. The deployment tilt angle is obtained by measuring the angle between key surfaces such as the roof and walls and the horizontal plane using an inclinometer. For vertical walls, the deployment tilt angle is typically 90°. For example, if the target container faces due south, and due north is 0°, the deployment azimuth angle is 90°; the roof is a single-slope structure with an angle of 15° to the horizontal plane, so the roof deployment tilt angle is 15°; the deployment tilt angle of the south wall, north wall, and other vertical walls is 90°.

[0047] Furthermore, based on the latitude and real-time time, the solar altitude angle and solar azimuth angle are calculated using a solar position algorithm. The solar position algorithm is a mathematical algorithm used to calculate the position of the sun in the celestial coordinate system at a specific latitude and time, such as the SPA solar position algorithm and the PVsyst built-in algorithm. The input parameters are latitude and real-time time. The solar altitude angle is the angle between the sun's rays and the horizontal plane, determining the vertical incident intensity of solar radiation; the larger the angle, the more radiation received per unit area. The solar azimuth angle is the angle between the projection of the sun's rays onto the horizontal plane and true north, with clockwise being positive, used to determine the sun's horizontal orientation relative to the container. The latitude and real-time time of the target container's deployment location are obtained and input into the solar position algorithm; through iterative calculation, the solar altitude angle and solar azimuth angle at that moment are output. For example, inputting the latitude of the target container (30°N) and the real-time time (Beijing time, summer solstice, 12:00) into the SPA solar position algorithm yields: solar altitude angle = 83.4°, solar azimuth angle = 180°.

[0048] Then, based on the deployment azimuth, deployment tilt, solar altitude angle, solar azimuth angle, and illumination shading information, sunlight is decomposed into three radiation components: direct, diffuse, and ground reflection. Based on these three radiation components, the effective projected radiation intensity of each surface of the target container is calculated. The illumination shading information is directly used to reduce or eliminate the direct radiation component on the corresponding container surface. Radiation components refer to the three forms of energy decomposed after solar radiation reaches the ground: direct radiation is sunlight that directly illuminates the object's surface; diffuse radiation is light that reaches the object's surface after being scattered by atmospheric molecules and clouds; and ground reflection radiation is light that reaches the object's surface after being reflected by the ground / surrounding objects. The effective projected radiation intensity refers to the total radiation intensity actually reaching each surface of the container after considering the shading effect; it is the superposition value of the three radiation components, where the direct component needs to be reduced or eliminated based on the shading information. Based on the deployment azimuth angle, deployment tilt angle, solar altitude angle, and solar azimuth angle, solar radiation is decomposed into three components: direct radiation, scattered radiation, and ground reflection using a radiation decomposition model. Combined with the illumination shading information obtained by S300, it is determined whether each surface is shaded, and the direct radiation component of the shaded surface is reduced accordingly. Finally, based on the projected area of ​​each surface, the effective projected radiation intensity after the superposition of the three components is calculated.

[0049] For example, regarding the north wall surface of the target container: based on parameters such as deployment azimuth angle of 90° and solar azimuth angle of 180°, the direct radiation component is calculated to be 800W / m. 2 Scattered radiation component = 100 W / m 2 Ground reflected radiation component = 50 W / m 2 Based on light shading information: During winter, the north wall is completely blocked by the office building to the north from 9:00 AM to 3:00 PM. The direct radiation component of the north wall is eliminated during this period, while the direct radiation component is retained during non-shading periods. Calculate the effective projected radiation intensity: Shading period = 0 W / m² 2 +100W / m 2 +50W / m 2 =150W / m 2 Unobstructed periods = 800W / m 2 +100W / m 2 +50W / m 2 =950W / m 2 .

[0050] In addition, the annual solar motion information for the target container deployment location is obtained, and the annual effective projected radiation intensity for the target container deployment location is calculated based on this information. The annual solar motion information refers to the variation patterns of the solar altitude angle and solar azimuth angle at the target container deployment location throughout the year, covering complete data on the annual solar trajectory. The annual effective projected radiation intensity is a complete dataset integrating the effective projected radiation intensity for each time period throughout the year, reflecting the actual light reception patterns of the target container at each time period. Using a solar position algorithm, the latitude of the target container is input, and the solar altitude angle and solar azimuth angle for typical dates and different time periods throughout the 12 months are calculated to form the annual solar motion information. Combining the radiation component decomposition logic and light shading information, the effective projected radiation intensity for each surface at each time period throughout the year is calculated sequentially, and the data is compiled into an annual effective projected radiation intensity dataset.

[0051] For example, the target container house has a latitude of 30°N. The solar position algorithm is used to calculate the solar movement information throughout the year: the solar altitude angle is the smallest at the winter solstice, about 36.6°, the largest at the summer solstice, about 83.4°, and in the middle at about 60° on the spring and autumn equinoxes. Combined with the north wall shading information, the effective projected radiation intensity of the north wall is calculated for each time period on the 15th of each month of the 12 months of the year. Finally, a dataset of the effective projected radiation intensity of the north wall, south wall, roof and other surfaces covering 365 days and 24 hours of the year is formed.

[0052] Finally, the annual effective projected radiation intensity and the stacking method are updated in the dynamic heat transfer model to obtain a dedicated heat transfer model for the target container. Model parameter updates refer to replacing or supplementing scenario-specific parameters such as the annual effective projected radiation intensity and stacking method into the corresponding parameter modules of the dynamic heat transfer model, making the model adaptable to the specific deployment scenario of the target container. The dedicated heat transfer model is a customized heat transfer model based on the target container's specific deployment geographic information and stacking method. It can accurately characterize the annual dynamic heat transfer pattern of the target container in a specific scenario, possessing uniqueness and scenario adaptability. Based on the S200, the dynamic heat transfer model imports the annual effective projected radiation intensity dataset into the illumination parameter module, replacing the original general illumination parameters; in the heat transfer loss module, the stacking method is input, and a new contact surface heat transfer calculation submodule is added; after completing the parameter update, the dynamic heat transfer model is verified to ensure that the parameters are logically consistent and the calculations are error-free, ultimately obtaining the dedicated heat transfer model for the target container.

[0053] For example, based on a dynamic heat transfer model of a 3m×6m standard container house, the effective projected radiation intensity dataset for the whole year is imported into the model's illumination parameter module, enabling the dynamic heat transfer model to automatically call the effective radiation intensity of the corresponding surface according to different times of the year; a new heat transfer submodule for the stacked contact surface is added to the dynamic heat transfer model, with a stacked contact area of ​​18m² input. 2The contact surface thermal resistance parameters are used to calculate the heat transfer loss at the contact surface between the upper and lower compartments; after verifying that the calculation logic of the model is correct, the specific heat transfer model of the target compartment is obtained.

[0054] In this embodiment of the invention, by integrating deployment geographic information and stacking methods, the lighting parameters of the dynamic heat transfer model are customized and limited, successfully constructing a dedicated heat transfer model for the target container house. This overcomes the limitations of the generalization of the preceding dynamic model, achieving precise adaptation to the specific deployment scenario of the target container house. It fills the gap in conventional housing temperature control technology, which is not designed for the mobile deployment and flexible stacking characteristics of prefabricated container houses. By decomposing the radiation components and combining them with shading information to calculate the effective radiation intensity, and incorporating the annual solar cycle, the model can accurately predict the actual heat transfer conditions at different times of the year, reducing calculation deviations caused by lighting factors. The integration of stacking methods further enhances the model's adaptability to typical container house deployment forms, providing dedicated and reliable model support for subsequent heat difference prediction and the formulation of precise temperature control strategies based on meteorological data.

[0055] S500: Obtain historical meteorological information of the target container deployment location, and based on the historical meteorological information, obtain meteorological baseline information of the deployment location.

[0056] In this embodiment of the invention, historical meteorological information of the target container deployment location is obtained, and meteorological baseline information of the deployment location is obtained based on the historical meteorological information. S400 has constructed a dedicated heat transfer model adapted to the specific deployment scenario of the target container, but it has not yet incorporated the meteorological baseline patterns of the deployment location, thus failing to provide a reliable reference for subsequent meteorological forecast corrections. Therefore, it is necessary to obtain historical meteorological information of the deployment location, extract meteorological baseline information reflecting long-term meteorological patterns, and simultaneously optimize the baseline reliability through confidence level configuration and weighted fusion, providing solid meteorological baseline support for subsequent accurate heat transfer prediction by combining forecast meteorological information.

[0057] Step S500 in the method provided in this embodiment of the invention includes: Based on the meteorological data center, hourly historical meteorological data of the target container deployment location over the past several years are obtained as the historical meteorological information. Extract several sets of temperature, light radiation, and wind speed information for the target container deployment location over the past few years from the historical meteorological information according to seasonal sequence. After outlier removal from the aforementioned sets of temperature information, light radiation information, and wind speed information, several sets of stable temperature information, stable light radiation information, and stable wind speed information are obtained. Interval analysis is performed on the aforementioned sets of stable temperature information, stable light radiation information, and stable wind speed information to obtain temperature baseline information, light radiation baseline information, and wind speed baseline information, which together serve as the meteorological baseline information.

[0058] First, based on the meteorological data center, hourly historical meteorological data from the past several years for the target container house deployment location is obtained as the historical meteorological information. The meteorological data center is a platform with authoritative meteorological data storage and query functions, such as a meteorological data network or a local meteorological bureau data service platform, which can provide historical meteorological data at different regions and time granularities. Hourly historical meteorological data refers to historical meteorological observation data recorded in hourly units, accurately reflecting the dynamic changes of meteorological parameters within a day, meeting the time response requirements of the container house's heat transfer characteristics. Historical meteorological information is the basic data used to extract the meteorological baseline, covering meteorological parameters such as temperature, wind speed, and sunshine duration at the target deployment location over the past several years.

[0059] For example, log in to the meteorological data center, enter the latitude and longitude of the target container deployment location, filter for a time range of the past 3-5 years, select hourly data granularity, and download historical meteorological datasets containing temperature, wind speed, and solar radiation, then organize them into structured historical meteorological information. For instance, enter the target container deployment location (30°N, 114°E), filter for hourly data from 2021-2025, and after downloading and organizing, you will obtain historical meteorological information containing temperature, wind speed, and solar radiation intensity data for 24 time periods each day, totaling 5 × 365 × 24 = 43,800 sets of basic data.

[0060] Secondly, several sets of temperature, solar radiation, and wind speed information from the target container deployment location over several years are extracted from the historical meteorological information according to seasonal sequence. Seasonal sequence refers to the division of historical meteorological data into natural seasons: spring (March-May), summer (June-August), autumn (September-November), and winter (December-February), facilitating the extraction of meteorological patterns across different seasons. Based on the seasonal sequence, the historical meteorological information is categorized and broken down. Within each season, 10 days of complete hourly data are randomly selected each month to form temperature, solar radiation, and wind speed parameter groups for each season. The temporal correspondence of each parameter group is ensured; temperature, wind speed, and solar radiation at the same moment are grouped together, ultimately resulting in multiple sets of core meteorological parameters covering all four seasons.

[0061] For example, the historical meteorological information obtained from 2021 to 2025 is divided into four seasons. In summer (June to August), 10 days are randomly selected each month, and a total of 30 days × 24 hours = 720 sets of data are extracted to form summer temperature information group (720-hour temperature values), summer solar radiation information group (720-hour radiation intensity values), and summer wind speed information group (720-hour wind speed values). Similarly, meteorological parameter groups for spring, autumn, and winter are extracted respectively.

[0062] Furthermore, after outlier removal from the aforementioned sets of temperature, solar radiation, and wind speed information, several sets of stable temperature, solar radiation, and wind speed information are obtained. Outliers refer to abnormal values ​​in historical meteorological data that deviate from the normal data range due to instrument malfunctions, extreme weather events, or other factors, which can interfere with the accuracy of the meteorological baseline. Stable meteorological parameter sets refer to the set of meteorological parameters after outlier removal; the data fluctuations conform to the normal meteorological patterns of the region and can be used for subsequent baseline extraction. First, temperature, solar radiation, and wind speed data for the same season are sorted and analyzed to observe and determine the normal fluctuation range in most datasets. Based on this normal range, reasonable upper and lower limits are set according to the local meteorological normal fluctuation range; most normal data will fall within this range, and data exceeding this range are considered abnormal. Data is screened one by one, and abnormal data exceeding the upper and lower limits are removed. Finally, the completeness of the dataset after outlier removal is checked. If a small number of normal time period data are missing, they can be supplemented by the average of adjacent normal time period data, ultimately obtaining stable meteorological parameter sets.

[0063] For example, taking the summer temperature information group as an example, it contains 720 hours of temperature data. After sorting and organizing, it was found that the vast majority of the data are concentrated between 20℃ and 38℃. Considering the local summer temperature fluctuations, the upper and lower limits for judgment were set to 14.5℃-42.5℃. After screening, three temperature values ​​of 45℃ were found in the data, which were significantly outside the normal range and were judged as abnormal data and removed. After inspection, it was found that the temperature data for two normal periods were missing. They were supplemented by the average temperature of two adjacent normal periods, and finally, a stable summer temperature information group of 719 data points was obtained. Similarly, the abnormal removal and supplementation of summer solar radiation and wind speed data were completed in the same way to obtain a stable solar radiation information group and a stable wind speed information group. Then, the meteorological parameters of other seasons were processed in turn to obtain a stable meteorological parameter group for all seasons.

[0064] Finally, interval analysis is performed on the aforementioned sets of stable temperature, stable solar radiation, and stable wind speed information to obtain temperature baseline information, solar radiation baseline information, and wind speed baseline information, which together serve as the meteorological baseline information. Interval analysis refers to statistical analysis of stable meteorological parameter sets to determine the regular variation ranges and typical values ​​of each meteorological parameter in different seasons and time periods, and to extract the core data of the meteorological baseline. Meteorological baseline information is a set of benchmark data reflecting the long-term regular meteorological patterns of the target deployment location, including temperature baseline, solar radiation baseline, and wind speed baseline, which serves as a reference standard for judging whether the current weather deviates from the norm. Interval analysis is performed on the stable temperature, solar radiation, and wind speed information sets for each season: the average value, median, and 95% confidence interval of the parameters for each time period are calculated, and the range of fluctuation of the average value ± 5% is used as the baseline interval for that time period, with the median as the typical baseline value; the baseline intervals and typical values ​​of each season and time period throughout the year are integrated to form temperature baseline information, solar radiation baseline information, and wind speed baseline information, which together constitute the meteorological baseline information.

[0065] For example, interval analysis of the stable temperature information group in summer yielded a daily average temperature of 30℃, a median of 29.8℃, and a 95% confidence interval of 26-33℃ at 2 PM. The baseline temperature range for this period was determined to be 28.5-31.5℃ (30℃ ± 5%), with a typical baseline value of 29.8℃. Similarly, the baseline range for solar radiation at 2 PM was determined to be 750-850 W / m². 2 Typical value 790W / m 2 The baseline wind speed range is 1.5-3.5 m / s, with a typical value of 2.5 m / s. By integrating data from all periods throughout the year, the meteorological baseline information for this deployment location is finally formed.

[0066] After obtaining the meteorological baseline information of the deployment location, the process also includes: Obtain the current time, and retrieve historical data from the aforementioned sets of stable temperature information, stable light radiation information, and stable wind speed information based on the current time to obtain several sets of stable temperature information, stable light radiation information, and stable wind speed information from the same historical time. Calculate the variances of the several stable temperature information, stable light radiation information, and stable wind speed information respectively, and configure the temperature baseline confidence, light radiation baseline confidence, and wind speed baseline confidence in real time based on the variances; Based on the meteorological baseline information, the current climate type is identified, and according to the climate type, influence weights are assigned to the confidence levels of temperature baseline, solar radiation baseline, and wind speed baseline. Based on the aforementioned influence weights, the confidence scores of the temperature baseline, solar radiation baseline, and wind speed baseline are weighted and fused to obtain the meteorological baseline confidence score.

[0067] First, the current time is obtained. Based on the current time, historical data from the aforementioned sets of stable temperature, stable solar radiation, and stable wind speed information are retrieved to obtain several sets of stable temperature, stable solar radiation, and stable wind speed information from the same historical period. Historical data from the same historical period refers to stable meteorological data from the same season, month, and time period as the current time. This data reflects the regular meteorological patterns at the current time and is used to verify the timeliness of the baseline. The stable data set from the same historical period is the collection of data selected from the stable meteorological parameter sets and forms the basis for calculating the confidence level. Based on the season, month, and time period of the current time, all data from the same period over the past three years are retrieved from the stable temperature, solar radiation, and wind speed information sets to form historical stable temperature data sets, stable solar radiation data sets, and stable wind speed data sets, respectively.

[0068] For example, given the current time is 2 PM on July 15, 2025 (summer, July, 2 PM), retrieving temperature data from the stable temperature information group for 2 PM on July 15, 2022-2024 yields three data points: 30℃, 29.5℃, and 30.2℃, forming a stable temperature data group for the same period; similarly, the stable light radiation data group for the same period is obtained: 780W / m 2 795W / m 2 805W / m 2 Stable wind speed data sets for the same period: 2.3 m / s, 2.6 m / s, 2.4 m / s.

[0069] Next, the variances of the several stable temperature, stable solar radiation, and stable wind speed data are calculated respectively. Based on these variances, the baseline confidence levels for temperature, solar radiation, and wind speed are configured in real time. Variance is a statistical measure reflecting the degree of data dispersion. The smaller the variance, the smaller the data fluctuation, the more stable the historical patterns, and the higher the baseline reliability. Baseline confidence is a quantitative indicator characterizing the reliability of the match between the meteorological baseline and the actual meteorological patterns at the current moment. Its value ranges from 0 to 1; the closer it is to 1, the higher the reliability. It is calculated based on the variance of historical data from the same period. The variances of the historical stable temperature, solar radiation, and wind speed data groups are calculated respectively; confidence level = 1 / (1 + variance). The smaller the variance, the closer the confidence level is to 1. If the variance is 0, it means the data is completely consistent, and the confidence level is set to 1.0.

[0070] For example, the variance of the same stable temperature data set is 0.087, and the confidence level of the temperature baseline is 1 / (1+0.087)≈0.92; the variance of the same stable light radiation data set is 166.67, and the confidence level of the light radiation baseline is 1 / (1+166.67)≈0.006; the variance of the same stable wind speed data set is 0.017, and the confidence level of the wind speed baseline is 1 / (1+0.017)≈0.98.

[0071] Furthermore, based on the meteorological baseline information, the current climate type is identified, and influence weights are assigned to the baseline confidence levels of temperature, solar radiation, and wind speed according to the climate type. The climate type is a specific meteorological scenario identified based on the current meteorological conditions and baseline information, including strong winds, extreme cold, and high-intensity sunshine. Different types have varying degrees of impact on heat transfer in the container. Influence weights are weight coefficients characterizing the degree of influence of different meteorological parameter baseline confidence levels on the total confidence level; the sum of all weights is 1, and they are assigned according to the core influencing factors of the climate type. The climate type is identified by comparing the measured meteorological data at the current moment with the meteorological baseline information; for different climate types, corresponding influence weights are assigned to the baseline confidence levels of temperature, solar radiation, and wind speed: the parameters of the core influencing factors have the highest weights, while the secondary factors have lower weights.

[0072] For example, the current measured wind speed is 5.2 m / s, which is far beyond the wind speed baseline range of 1.5-3.5 m / s, and is identified as strong wind weather. Under strong wind weather, wind speed has the most significant impact on the surface heat exchange of the container house, followed by temperature and light radiation. The impact weights are configured as follows: wind speed baseline confidence weight = 0.6, temperature baseline confidence weight = 0.3, and light radiation baseline confidence weight = 0.1. If it is identified as high-intensity sunshine weather, then the weights are configured as light radiation = 0.6, temperature = 0.3, and wind speed = 0.1.

[0073] Finally, based on the aforementioned influence weights, the confidence scores of the temperature baseline, solar radiation baseline, and wind speed baseline are weighted and fused to obtain the meteorological baseline confidence score. Weighted fusion refers to multiplying the confidence scores of each parameter baseline by their corresponding influence weights and then summing the results to obtain the overall confidence score, which comprehensively reflects the overall reliability of the meteorological baseline. The meteorological baseline confidence score is a comprehensive indicator characterizing the reliability of meteorological baseline information in adapting to the current climate type, with a value range of 0-1, providing a reliability reference for subsequent meteorological forecast corrections. The meteorological baseline confidence score is calculated using the weighted summation formula: Meteorological Baseline Confidence Score = Temperature Baseline Confidence Score × Temperature Weight + Solar Radiation Baseline Confidence Score × Solar Radiation Weight + Wind Speed ​​Baseline Confidence Score × Wind Speed ​​Weight. For example, substituting the baseline confidence scores and influence weights into the formula, the meteorological baseline confidence score is: 0.92 × 0.3 + 0.006 × 0.1 + 0.98 × 0.6 = 0.8646 ≈ 0.86, indicating that the current meteorological baseline information has a high reliability in adapting to windy weather.

[0074] In this embodiment of the invention, by extracting meteorological baseline information of the deployment location and optimizing the confidence level, a reliable meteorological benchmark is provided for subsequent meteorological forecast correction. Through hourly historical data processing and seasonal time-series analysis, the meteorological baseline accurately matches the long-term meteorological patterns of the target deployment location, adapting to the regional adaptation needs of the mobile deployment of prefabricated container houses. Outlier removal and interval analysis improve the stability and accuracy of the baseline data, avoiding interference from abnormal data. Confidence level configuration and weighted fusion dynamically optimize the reliability of the baseline based on the current climate type, enabling the baseline to accurately adapt to different extreme weather scenarios. Overall, this achieves an upgrade of the meteorological baseline from general statistics to scenario-based precise adaptation, laying the foundation for subsequent baseline correction based on predicted meteorological information and achieving accurate heat transfer prediction.

[0075] S600: Obtain the predicted meteorological information of the target container deployment location, and correct the meteorological baseline information for a future preset period based on the predicted meteorological information to obtain future environmental meteorological information.

[0076] In this embodiment of the invention, predicted meteorological information for the target container house deployment location is obtained. Based on the predicted meteorological information, the meteorological baseline information for a preset future period is corrected to obtain future environmental meteorological information. The meteorological baseline information obtained by S500 is a conventional meteorological pattern extracted from historical data. However, the future meteorological conditions of the prefabricated container house deployment scenario may deviate from the historical baseline, and relying solely on the baseline cannot accurately predict the actual future environmental conditions. Furthermore, the confidence level of the meteorological baseline quantifies the reliability of the baseline's adaptation to the current climate type, and the level of confidence directly determines the reference value of the baseline. Therefore, it is necessary to obtain predicted meteorological information for a preset future period, correct the meteorological baseline using this information, and dynamically adjust the correction magnitude according to the baseline confidence level. This ensures that the corrected result better matches the actual future meteorological conditions, providing accurate future environmental data for subsequent heat prediction based on a dedicated heat transfer model.

[0077] Step S600 in the method provided in this embodiment of the invention includes: Obtain forecast meteorological information for a future preset time period and align it with the meteorological baseline information within the future preset time period on the time axis; The predicted meteorological information is used to correct the meteorological baseline information to obtain future environmental meteorological information, wherein the correction magnitude of the predicted meteorological information to the meteorological baseline information is inversely proportional to the confidence level of the meteorological baseline.

[0078] First, the predicted meteorological information for a future preset time period is acquired and aligned with the meteorological baseline information within that preset time period on the timeline. The predicted meteorological information refers to the meteorological forecast data for a specific future time period at the target container house deployment location, released by the meteorological platform. This data includes temperature, solar radiation, and wind speed information and serves as a dynamic basis for correcting historical baselines. The future preset time period refers to the future time range set according to the planning requirements of the container house temperature control strategy, such as the next 24 hours, and must maintain consistency with the time granularity of the meteorological baseline. Timeline alignment means matching each time node of the predicted meteorological information with the baseline data for the corresponding time period in the meteorological baseline, ensuring the time correspondence of the correction operation and avoiding cross-time period deviations. Log in to the meteorological forecasting platform, enter the latitude and longitude of the target container house deployment location, select the future preset time period, and download the hourly predicted meteorological data. Organize the time series of the predicted data, matching each hourly predicted data with the corresponding hourly baseline data in the meteorological baseline acquired by S500, thus completing the timeline alignment.

[0079] For example, the future preset time period is set to 00:00-23:59 on July 16, 2025, that is, the next 24 hours. The hourly forecast meteorological information of the target deployment location during this period is downloaded from the weather network: including the predicted temperature, predicted solar radiation intensity and predicted wind speed for each hour of the day; the forecast data is sorted by time and corresponds one-to-one with the baseline data of each hour on July 16, 2025 in the meteorological baseline to complete the time axis alignment.

[0080] Secondly, the predicted meteorological information is used to correct the meteorological baseline information to obtain future environmental meteorological information. The correction magnitude of the predicted meteorological information to the meteorological baseline information is inversely proportional to the confidence level of the meteorological baseline. The correction magnitude refers to the degree of adjustment of the meteorological baseline by the predicted meteorological information. The correction magnitude is inversely proportional to the confidence level of the meteorological baseline; the higher the baseline confidence level, the smaller the correction magnitude; the lower the baseline confidence level, the larger the correction magnitude. Future environmental meteorological information refers to the final meteorological data, after correction by the predicted meteorological information, that accurately reflects the actual meteorological change trend within a preset future period. It is the core environmental input parameter for subsequent heat transfer prediction. The correction magnitude is calculated as 1 - meteorological baseline confidence level, ranging from 0 to 1. For temperature, light radiation, and wind speed at each time point, correction values ​​are calculated separately: Correction value = typical meteorological baseline value + (predicted meteorological value - typical meteorological baseline value) × correction magnitude. The corrected values ​​are verified for reasonableness to ensure they are within the normal meteorological range for that time period in the local area. The corrected data from all time points are integrated to form the future environmental meteorological information for the preset future period.

[0081] For example, consider the temperature parameter correction at 2 PM within the next 24 hours: Known parameters: typical meteorological baseline value 29.8℃, predicted temperature 32℃, meteorological baseline confidence level 0.86; Correction range = 1 - 0.86 = 0.14; Temperature correction value = 29.8℃ + (32℃ - 29.8℃) × 0.14 ≈ 30.1℃; Reasonableness check: 30.1℃ is within the local summer 2 PM normal temperature range of 25-35℃, and is considered reasonable; Similarly, correcting the solar radiation and wind speed at 2 PM yields a solar radiation correction value of 785.8 W / m². 2 Wind speed correction value = 2.54 m / s; integrate the corrected data from each period of the next 24 hours to finally form the future environmental meteorological information for that period.

[0082] In this embodiment of the invention, by dynamically correcting historical meteorological baselines using predicted meteorological information, a precise transition of meteorological data from historical norms to future realities is achieved. The linkage design between the correction magnitude and the confidence level of the meteorological baseline ensures the rationality of the correction logic: fewer adjustments are made when baseline reliability is high to avoid excessive deviation from historical patterns; more adjustments are made when baseline reliability is low to fully utilize predicted data to compensate for baseline deficiencies. The corrected future environmental meteorological information accurately adapts to the actual future operating conditions of the target container house deployment location, overcoming the limitations of conventional building temperature control technology that relies on static historical meteorological data. This fully meets the dynamic environmental adaptation requirements of mobile deployment of prefabricated container houses, providing high-quality environmental parameter support for subsequent prediction of future heat difference and formulation of precise temperature control strategies based on a dedicated heat transfer model.

[0083] S700: Obtain the preset temperature information and real-time temperature information of the target container.

[0084] In this embodiment of the invention, preset temperature information and real-time temperature information of the target container are obtained. The preset temperature information of the target container serves as a reference for formulating temperature control strategies, while the real-time temperature information is the direct basis for determining whether the current container temperature deviates from expectations. The combination of the two provides decision support for subsequent heat difference calculation and the start and stop of temperature control equipment. The preset temperature information is obtained by manually inputting or retrieving the container-specific temperature scheme built into the system through the temperature control system control terminal, based on the actual usage scenario requirements of the target container. The preset temperature needs to be set in combination with the insulation characteristics of the container and the comfort needs of the users. The real-time temperature information is collected by temperature sensors evenly distributed throughout the container's interior space. The sensor placement must cover the core area of ​​the interior to avoid interference from local heat sources. The collected data is calibrated and transmitted to the temperature control system terminal in real time.

[0085] For example, a 3m×6m standard modular prefabricated container house is used as a temporary dormitory for construction workers. The preset temperature information is set to 26℃ in summer and 18℃ in winter. One temperature sensor is installed in the middle of the container house, below the east window, and inside the south door. The indoor temperature at noon in summer is collected in real time and is 28.2℃, 28.5℃, and 28.3℃ respectively. The average value of 28.3℃ is taken as the real-time temperature information at that moment.

[0086] S800: Based on the current time and the dedicated heat transfer model, according to the preset temperature information, real-time temperature information and future environmental meteorological information, obtain the time-series heat difference required for the target container to maintain the preset temperature information in the future preset time period.

[0087] In this embodiment of the invention, based on the current moment and a dedicated heat transfer model, and according to the preset temperature information, real-time temperature information, and future environmental meteorological information, the time-series heat difference required for the target container to maintain the preset temperature information within a future preset time period is obtained. The previous steps have constructed a dedicated heat transfer model for the target container, obtained future environmental meteorological information, and the preset and real-time temperature information of the container, but these have not yet been integrated and transformed into a direct basis for temperature control execution. Therefore, it is necessary to take the current moment as the starting point, rely on the dedicated heat transfer model, take the real-time temperature as the initial state, the future environmental meteorological information as a dynamic disturbance, and the preset temperature as the control target, and solve for the heat difference required to maintain the preset temperature by constructing an optimized objective function, and extend and predict the heat difference sequence for future time periods, providing a quantitative basis for the precise start-up and power adjustment of the subsequent temperature control equipment.

[0088] Step S800 in the method provided in this embodiment of the invention includes: The real-time temperature information is used as an initial condition and input into the dedicated heat transfer model; Future environmental and meteorological information is used as a known time-series disturbance and input into a dedicated heat transfer model. An optimization objective function is constructed based on the specific heat transfer model and the preset temperature information. The optimization objective function aims to maintain the preset temperature information, and the optimization variable is the heat difference of the input system. Solve the objective function to obtain the heat difference required to maintain the preset temperature information; Continue to predict the heat difference sequence required to maintain the preset temperature information within a future preset time period, and use it as the time-series heat difference.

[0089] First, the real-time temperature information is used as an initial condition and input into the dedicated heat transfer model. The initial condition, i.e., the actual temperature inside the container at the current moment, determines the initial benchmark for subsequent calculations, ensuring that the calculation results are consistent with the actual operating conditions of the container. The real-time temperature information of the target container acquired by the S700 is extracted, and the validity of this temperature data is confirmed. Through the model data interface, the real-time temperature information is entered as an initial state parameter into the dedicated heat transfer model of the target container constructed by the S400, completing the calibration of the model's initial state. For example, the real-time temperature information collected by the S700 is 28.3℃ at noon in summer. After calibration using the average data from three indoor sensors, no anomalies are found. Through the data input interface of the dedicated heat transfer model, 28.3℃ is input as the initial temperature parameter into the dedicated heat transfer model. The dedicated heat transfer model automatically starts the subsequent heat transfer process calculation from this temperature.

[0090] Secondly, future environmental meteorological information is treated as known time-series interference and input into the dedicated heat transfer model. Time-series interference is a set of external environmental influence parameters that change over time, referring to hourly environmental meteorological data within a preset future time period. It is the core external factor affecting the heat transfer process of the container and causing the indoor temperature to deviate from the preset value. The future environmental meteorological information obtained by the S600 is organized and a time-series dataset is constructed according to the time sequence of the preset future time period. This time-series dataset is then imported into the dedicated heat transfer model in batches, with the time step set to match the hourly time granularity of the meteorological data to ensure that the environmental interference is synchronized with the time process. For example, a future 24-hour environmental meteorological time series is organized, including hourly temperature, light radiation, and wind speed data. This series is then imported into the dedicated heat transfer model in hourly order, with the time step set to 1 hour. This allows the dedicated heat transfer model to automatically call the corresponding environmental meteorological parameters when calculating the hourly heat transfer process.

[0091] Furthermore, an optimization objective function is constructed based on the dedicated heat transfer model and the preset temperature information. The optimization objective of this function is to maintain the preset temperature information, and the optimization variable is the heat difference of the input system. The optimization objective function is a mathematical expression constructed based on the dedicated heat transfer model, clearly defining the relationship between the control objective and the optimization variable, and is used to solve for the optimal variable value that satisfies the objective. The optimization objective is to maintain the preset temperature information, that is, to adjust the heat difference so that the indoor temperature of the container remains stable near the preset temperature within a preset time period in the future. The optimization variable is the heat difference of the input system, that is, the amount of heat that the temperature control equipment needs to supplement or dissipate; positive values ​​indicate the need for cooling and heat dissipation, and negative values ​​indicate the need for heating and heat supplementation. Based on the heat transfer equation of the dedicated heat transfer model, and using the preset temperature information as a constraint, the optimization objective function is constructed as follows: Objective function value = Σ(Model calculated temperature at each future time - Preset temperature) 2Minimizing the objective function value means that the indoor temperature is closest to the preset temperature. The heat difference is set as the optimization variable and embedded in the heat transfer equation of the dedicated heat transfer model. The range of the variable's value is defined and combined with the rated power setting of the temperature control equipment, such as -500W to 500W.

[0092] For example, based on the dedicated heat transfer model of the target container, and constrained by a preset summer temperature of 26℃, an optimization objective function is constructed: Where t is the hour number of the next 24 hours, T(t) is the indoor temperature in the t-th hour calculated by the model, and Q is the heat difference variable; the heat difference Q is set to range from -500W to 500W, and Q is embedded into the model's heat transfer equation: ,in The initial temperature is 28.3℃, and W(t) represents the future environmental meteorological parameters at hour t.

[0093] Then, the objective function is solved to obtain the heat difference required to maintain the preset temperature. Solving the function involves using mathematical algorithms to find the optimization variable that minimizes the objective function value, ensuring the solution accurately meets the goal of maintaining the preset temperature. The heat difference, obtained through the substantive solution, represents the amount of heat that needs to be replenished or discharged at a single time point, providing a quantitative basis for the real-time operation of the temperature control equipment. The gradient descent method is used to solve the objective function: the heat difference variable is initialized and substituted into the function to calculate the objective function value; the variable value is adjusted through iterative calculation, gradually reducing the objective function value until it reaches its minimum stable value, at which point the indoor temperature is closest to the preset temperature; the variable value in this state is extracted, representing the heat difference required to maintain the preset temperature at the current moment; the solution is then validated for reasonableness to ensure it remains within the power range of the temperature control equipment.

[0094] For example, the gradient descent method is used to solve the above optimization objective function. The heat difference Q is initialized to 0W. At this time, the temperature calculated by the dedicated heat transfer model is 28.2℃, which deviates greatly from 26℃. By iteratively adjusting the Q value, when Q=320W, the temperature calculated by the dedicated heat transfer model is 26.1℃, which is close to the preset temperature of 26℃, and the objective function value reaches the minimum stable value. Verification shows that 320W is within the power range of -500W to 500W of the temperature control equipment, which is considered reasonable. That is, the heat difference required to maintain the preset temperature at the current moment is 320W, and a positive number means that 320W of heat needs to be discharged by cooling.

[0095] Based on this, the heat difference sequence required to maintain the preset temperature information within a future preset time period is further predicted, serving as the time-series heat difference. The heat difference sequence refers to the set of heat differences required to maintain the preset temperature at each time node within the future preset time period, arranged chronologically to form time-series data. The time-series heat difference is dynamic data containing heat adjustment needs for all future time periods, providing full-time quantitative support for the time-series operation strategy of the temperature control equipment. Based on the above solution logic, according to the time sequence of the future preset time period, such as one node per hour, the optimization objective function for each time node is solved sequentially to obtain the heat difference for each node; the heat differences of all nodes are arranged chronologically to form a complete heat difference sequence; the sequence is smoothed to eliminate abrupt changes between adjacent time periods, ensuring stable operation of the temperature control equipment, ultimately yielding the time-series heat difference.

[0096] For example, the heat difference for each hour is calculated sequentially according to the time series of the next 24 hours: 320W for the 1st hour, 310W for the 2nd hour, 305W for the 3rd hour, ... 350W for the 14th hour, 280W for the 23rd hour, and 270W for the 24th hour. The heat difference is then arranged in chronological order to form a heat difference sequence of 24 data points. The sudden change of 15W between the 14th and 13th hours is eliminated by smoothing and adjusted to 345W, finally yielding the time series heat difference for the next 24 hours. This sequence accurately reflects the amount of heat that needs to be discharged in each period.

[0097] In this embodiment of the invention, by deeply integrating multi-source parameters with a dedicated heat transfer model, the temporal heat difference for a preset future time period is accurately solved and predicted, achieving a crucial transition from environmental and container house status perception to the quantification of temperature control requirements. The gradient descent method ensures the accuracy and engineering feasibility of the heat difference solution, and the temporalized results are adapted to the dynamic heat transfer characteristics of prefabricated container houses. Unlike the fixed power control logic of conventional house temperature control technology, the temporal heat difference provides a precise operational basis for temperature control equipment throughout the entire time period, avoiding problems of over- or under-temperature control. Simultaneously, the solution process based on the dedicated heat transfer model fully aligns with the individual characteristics and deployment scenario of the target container house, further improving the customization and accuracy of the temperature control strategy and providing a data foundation for the intelligent control of subsequent temperature control equipment.

[0098] S900: Based on the time-series heat difference, configure the cooling or heating capacity of the container temperature control equipment for a future preset time period.

[0099] In this embodiment of the invention, the cooling or heating capacity of the container room temperature control equipment is configured based on the time-series heat difference value for a future preset time period. The preceding steps have already obtained the time-series heat difference value for the future preset time period. This data is only a quantitative indicator of the heat demand for container room temperature regulation and has not yet been transformed into an executable control strategy for the temperature control equipment. Therefore, based on the time-series heat difference value and combined with the operating information of the temperature control equipment, it is necessary to calculate the total heat gap and configure the corresponding cooling or heating capacity to generate precise control commands, achieving optimal matching between heat demand and equipment operation, and completing the closed loop from demand quantification to execution control.

[0100] Step S900 in the method provided in this embodiment of the invention includes: Obtain the operating status information of the temperature control equipment in the target container, including the cooling capacity-power curve and the heating capacity-power curve; Based on the time-series heat difference, calculate the total heat deficit within the preset control period; Based on the total heat deficit, the cooling or heating capacity within a preset control cycle is configured as the basis for control. The control basis is reviewed, and the operating condition information is checked to generate control instructions for the temperature control device within a preset control cycle, and these instructions are sent to the temperature control device for execution. The control instructions include at least the operating mode and operating power.

[0101] First, obtain the operating condition information of the temperature control equipment in the target container, including cooling capacity-power curves and heating capacity-power curves. Operating condition information refers to the set of performance parameters of the temperature control equipment under different operating conditions, reflecting the correspondence between the equipment's cooling / heating capacity and input power, and is a key basis for matching heat demand. The cooling capacity-power curve is a function curve showing the change in cooling capacity with input power when the equipment is in cooling mode; the slope of the curve represents the equipment's cooling efficiency, with a higher slope indicating better efficiency. The heating capacity-power curve is a function curve showing the change in heating capacity with input power when the equipment is in heating mode, serving as a benchmark for matching heating demand with power configuration. Consult the manufacturer's technical specifications for the target container's temperature control equipment to extract the core parameters of cooling capacity-power and heating capacity-power; fit the discrete parameters into continuous function curves, clarify the effective value range of the curves, ensuring they fall within the equipment's rated power range; input the curve data into the temperature control system to establish an equipment operating condition parameter database.

[0102] For example, the target container is equipped with a 1-horsepower wall-mounted air conditioner. Referring to the instruction manual, the operating conditions are as follows: In cooling mode, an input power of 500W corresponds to a cooling capacity of 1600W, and an input power of 700W corresponds to a cooling capacity of 2300W. A cooling capacity-power curve is obtained by fitting the curve. Where P is the input power, and the value of P ranges from 500W to 1200W; in heating mode, an input power of 600W corresponds to a heating capacity of 1800W, and the heating capacity-power curve is obtained by fitting the curve. The value of P ranges from 600W to 1300W; the two curves are entered into the temperature control system parameter library.

[0103] Secondly, based on the aforementioned time-series heat difference, the total heat deficit within the preset control cycle is calculated. The preset control cycle refers to the minimum control time unit set to ensure stable operation of the temperature control equipment, typically 1 hour, to avoid frequent start-ups and shutdowns causing damage. The total heat deficit refers to the total heat required to maintain the preset temperature in the container within a single preset control cycle, calculated by integrating or averaging the time-series heat difference within that cycle. If the preset control cycle is determined to be 1 hour, the time-series heat difference data within that cycle is extracted. If the heat difference fluctuation within the cycle is small, the arithmetic mean is taken as the total heat deficit; if the fluctuation is large, the time integration method is used to calculate the total heat value. The attribute of the total heat deficit is clarified: a positive number indicates a cooling deficit, requiring heat to be discharged; a negative number indicates a heating deficit, requiring heat to be replenished.

[0104] For example, the preset control cycle is set to 1 hour, and the time-series heat difference value of the next 14 hours is extracted: the heat difference value of every 10 minutes in this hour is 340W, 345W, 350W, 348W, 342W, and 338W respectively, with small fluctuations. The total heat gap = (340+345+350+348+342+338) / 6≈344W; this value is positive and is determined to be a cooling gap, that is, 344W of heat needs to be discharged in this cycle.

[0105] Next, based on the total heat deficit, the cooling or heating capacity within a preset control cycle is configured as the control basis. Cooling or heating capacity configuration refers to selecting the required cooling or heating power output by the equipment based on the attributes and values ​​of the total heat deficit, combined with the equipment operating condition curve, ensuring a precise match between the output heat and the deficit. The control basis refers to the configured cooling or heating capacity value and the corresponding equipment operating parameters, which serve as the reference for generating control commands. The equipment operating mode is determined based on the attributes of the total heat deficit: positive numbers select cooling mode, and negative numbers select heating mode. The total heat deficit value is substituted into the corresponding operating condition curve to calculate the required input power. The calculated power is checked to see if it is within the equipment's rated power range; if it exceeds this range, the rated extreme value is used; if it is within the range, it is directly adopted. The finally determined cooling / heating capacity and corresponding power are used as the control basis.

[0106] For example, given a total heat deficit of 344W, and selecting the cooling mode, substitute the cooling capacity-power curve. ; Inverse calculation of input power: Input power If the power is lower than the equipment's rated minimum power of 500W, to avoid inefficient operation of the equipment, the rated minimum power of 500W is taken, corresponding to a cooling capacity of 1600W; the control basis for determining this control cycle is: cooling mode, input power 500W, cooling capacity 1600W.

[0107] Finally, the control basis is reviewed, and the operating condition information is examined to generate control instructions for the temperature control equipment within a preset control cycle. These instructions are then sent to the temperature control equipment for execution. The control instructions include at least the operating mode and operating power. Control instructions refer to operational instructions generated based on the control basis and recognizable and executable by the temperature control equipment. Instruction issuance refers to the process of transmitting the control instructions to the temperature control equipment via the communication link between the temperature control system and the equipment, triggering the equipment to operate according to the instructions. Based on the control basis, standardized control instructions are generated, specifying the operating mode, operating power, and operating duration as a preset control cycle. A communication connection is established between the temperature control system and the temperature control equipment via RS485 or a wireless communication module. The control instructions are encapsulated and sent to the equipment, with real-time feedback on instruction reception status. After receiving the instructions, the equipment automatically switches to the corresponding operating mode and operates at the set power. After completing one control cycle, the real-time temperature of the chamber is re-acquired, and the next control cycle begins.

[0108] For example, control instructions are generated based on the control criteria: operating mode: cooling; operating power: 500W; running time: 1 hour; the instructions are sent to the 1 HP wall-mounted air conditioner in the container via a wireless communication module; after receiving the instructions, the air conditioner automatically starts the cooling mode and operates at 500W power; after running for 1 hour, the temperature control system automatically collects the real-time temperature of the container, combines it with the total heat deficit for the next control cycle, and generates new control instructions to achieve continuous regulation.

[0109] In this embodiment of the invention, by deeply integrating the time-series heat difference with the operating information of the temperature control equipment, a closed-loop management system from quantifying heat demand to precisely controlling the equipment is achieved. Based on the configuration logic of the equipment's cooling capacity-power and heating capacity-power curves, energy waste and equipment damage caused by conventional fixed power control are avoided. The preset control cycle ensures the stability of equipment operation and adapts to the dynamic heat transfer characteristics of prefabricated container houses. The generation and issuance of standardized control commands realize the automated execution of the temperature control strategy, significantly improving the intelligence level of the temperature control system. The overall technical solution differs from the generalized temperature control logic of conventional houses, fully meeting the specific needs of container houses in their mobile deployment and confined spaces. While ensuring the stability of the preset temperature, it minimizes temperature control energy consumption and improves the engineering feasibility and economy of the temperature control strategy.

[0110] Through the specific implementation methods described above, the embodiments of the present invention achieve the following technical effects: This invention provides a model-based prediction-based method and system for dynamic temperature control of prefabricated container houses. Targeting the unique application scenarios of mobile deployment and spatial characteristics of prefabricated container houses, it constructs a fully closed-loop intelligent control system from model customization to precise temperature control. This invention overcomes the limitations of conventional building temperature control technologies by progressively constructing static heat conduction models, dynamic heat transfer models, and dedicated heat transfer models. It incorporates specific features such as the stacking method and deployment geographic information of container houses, solving the problem of poor compatibility between general models and the actual heat transfer patterns of container houses, and improving the accuracy of heat transfer calculations. It employs a meteorological data processing logic that uses historical meteorological baselines to extract predicted meteorological data and dynamically correct the confidence level for weighted optimization. This effectively avoids interference from historical abnormal data and prediction biases caused by future meteorological fluctuations, providing high-quality environmental parameter support for the heat transfer model and achieving a leap from historical statistics to accurate future predictions of meteorological data. Based on a dedicated heat transfer model and multi-source parameter fusion, the system solves and predicts the time-series heat difference for a preset period. By combining the cooling and heating power curves of the temperature control equipment, it achieves optimal matching between heat demand and equipment operation, avoiding energy waste, equipment overload, or substandard temperature control caused by traditional fixed-power regulation. This balances temperature control stability and economy. Ultimately, a complete technical chain is formed, encompassing model construction, meteorological correction, heat calculation, and equipment regulation. This enables automated, intelligent, and customized temperature control for prefabricated container houses, improving the comfort of container houses in scenarios such as construction site dormitories and temporary accommodation sites. Simultaneously, it reduces the operating energy consumption and equipment wear of the temperature control system, demonstrating strong engineering feasibility and promotional value.

[0111] Example 2, as Figure 2 As shown, this invention provides a model-predictive-based dynamic temperature control system for modular prefabricated container houses, the system comprising: The thermal conductivity model building module 11 is used to build a thermal conductivity model of the target model container house based on the material and structural information of the target model container house; The dynamic heat transfer modeling module 12 is used to acquire heat transfer data of the target model container house under different light, temperature and stacking methods, and build a dynamic heat transfer model of the target model container house based on the heat conduction model. The geographic information acquisition module 13 is used to acquire the deployment geographic information of the target container belonging to the target model container, and the deployment geographic information includes at least latitude, orientation, and light shading information; The heat transfer model generation module 14 is used to limit the illumination parameters in the dynamic heat transfer model based on the deployment geographic information and the stacking method of the target container, so as to obtain the exclusive heat transfer model of the target container. The meteorological baseline acquisition module 15 is used to acquire historical meteorological information of the target container deployment location, and acquire meteorological baseline information of the deployment location based on the historical meteorological information; The weather forecast correction module 16 is used to obtain the forecast weather information of the target container deployment location, and correct the meteorological baseline information within a preset future period based on the forecast weather information to obtain future environmental weather information. Temperature information acquisition module 17 is used to acquire the preset temperature information and real-time temperature information of the target container; The heat demand prediction module 18 is used to obtain the time-series heat difference required for the target container to maintain the preset temperature information within a preset time period in the future, based on the current time and the dedicated heat transfer model, according to the preset temperature information, real-time temperature information and future environmental meteorological information. The temperature control device configuration module 19 is used to configure the cooling capacity or heating capacity of the container temperature control device within a future preset time period based on the time-series heat difference.

[0112] In one embodiment, the thermal conductivity model building module 11 is further used for: Obtain the material and structural information of the target model container house. The material information includes at least the thickness of the color steel plate, the thickness and density of the sandwich insulation material, the thermal conductivity parameters of the color steel plate, the thermal conductivity parameters of the sandwich insulation material, and the glass type. The structural information includes at least the door and window dimensions and the door and window positions. Based on the structural information, the target model container house is decomposed into multiple thermal nodes, which include at least wall nodes and door and window nodes; Based on the material information, calculate the thermal resistance and thermal capacity of the plurality of thermal nodes; wherein, the thermal resistance includes thermal conductivity resistance, surface heat transfer resistance, and radiative heat transfer resistance; Based on the connection relationship between thermal nodes, multiple thermal balance equations are established to obtain the thermal conductivity model of the target type container house.

[0113] In one embodiment, the dynamic heat transfer modeling module 12 is further configured to: Under various lighting conditions, the surface temperature of the target model container, the indoor air temperature, and the solar radiation intensity were measured to obtain light-induced heat transfer data. Under controlled temperature conditions, different indoor and outdoor temperature differences were set for the target model container house, and the steady-state heat flux and the time to reach steady state of the target model container house were measured as temperature heat transfer data; Under simulated actual stacking conditions, the heat transfer effect data between the contact surfaces of the containers that are in contact with each other is measured and used as the stacking heat transfer data. Based on the light heat transfer data, air temperature heat transfer data, and stacked heat transfer data, the parameters of the heat conduction model are corrected to obtain the dynamic heat transfer model.

[0114] In one embodiment, the heat transfer model generation module 14 is further configured to: Obtain the stacking method of the target container, wherein the stacking method includes at least the stacking contact area; Calculate the deployment azimuth and tilt angle of the target container relative to the sun based on its orientation. Based on the latitude and real-time time, the solar altitude angle and solar azimuth angle are calculated using a solar position algorithm; Based on the deployment azimuth, deployment tilt, solar altitude angle, solar azimuth, and light shading information, sunlight is decomposed into three radiation components: direct, scattered, and ground reflection. Based on these three radiation components, the effective projected radiation intensity of each surface of the target container is calculated. The light shading information is directly used to reduce or eliminate the direct radiation component on the corresponding container surface. Obtain the annual solar activity information of the target container deployment location, and then calculate the annual effective projected radiation intensity of the target container deployment location based on the annual solar activity information; The effective projected radiation intensity throughout the year and the stacking method are updated to the dynamic heat transfer model to obtain the exclusive heat transfer model of the target container.

[0115] In one embodiment, the meteorological baseline acquisition module 15 is also used for: Based on the meteorological data center, hourly historical meteorological data of the target container deployment location over the past several years are obtained as the historical meteorological information. Extract several sets of temperature, light radiation, and wind speed information for the target container deployment location over the past few years from the historical meteorological information according to seasonal sequence. After outlier removal from the aforementioned sets of temperature information, light radiation information, and wind speed information, several sets of stable temperature information, stable light radiation information, and stable wind speed information are obtained. Interval analysis is performed on the aforementioned sets of stable temperature information, stable light radiation information, and stable wind speed information to obtain temperature baseline information, light radiation baseline information, and wind speed baseline information, which together serve as the meteorological baseline information.

[0116] After obtaining the meteorological baseline information of the deployment location, the process also includes: Obtain the current time, and retrieve historical data from the aforementioned sets of stable temperature information, stable light radiation information, and stable wind speed information based on the current time to obtain several sets of stable temperature information, stable light radiation information, and stable wind speed information from the same historical time. Calculate the variances of the several stable temperature information, stable light radiation information, and stable wind speed information respectively, and configure the temperature baseline confidence, light radiation baseline confidence, and wind speed baseline confidence in real time based on the variances; Based on the meteorological baseline information, the current climate type is identified, and according to the climate type, influence weights are assigned to the confidence levels of temperature baseline, solar radiation baseline, and wind speed baseline. Based on the aforementioned influence weights, the confidence scores of the temperature baseline, solar radiation baseline, and wind speed baseline are weighted and fused to obtain the meteorological baseline confidence score.

[0117] In one embodiment, the weather forecast correction module 16 is further configured to: Obtain forecast meteorological information for a future preset time period and align it with the meteorological baseline information within the future preset time period on the time axis; The predicted meteorological information is used to correct the meteorological baseline information to obtain future environmental meteorological information, wherein the correction magnitude of the predicted meteorological information to the meteorological baseline information is inversely proportional to the confidence level of the meteorological baseline.

[0118] In one embodiment, the heat demand forecasting module 18 is further configured to: The real-time temperature information is used as an initial condition and input into the dedicated heat transfer model; Future environmental and meteorological information is used as a known time-series disturbance and input into a dedicated heat transfer model. An optimization objective function is constructed based on the specific heat transfer model and the preset temperature information. The optimization objective function aims to maintain the preset temperature information, and the optimization variable is the heat difference of the input system. Solve the objective function to obtain the heat difference required to maintain the preset temperature information; Continue to predict the heat difference sequence required to maintain the preset temperature information within a future preset time period, and use it as the time-series heat difference.

[0119] In one embodiment, the temperature control device configuration module 19 is further configured to: Obtain the operating status information of the temperature control equipment in the target container, including the cooling capacity-power curve and the heating capacity-power curve; Based on the time-series heat difference, calculate the total heat deficit within the preset control period; Based on the total heat deficit, the cooling or heating capacity within a preset control cycle is configured as the basis for control. The control basis is reviewed, and the operating condition information is checked to generate control instructions for the temperature control device within a preset control cycle, and these instructions are sent to the temperature control device for execution. The control instructions include at least the operating mode and operating power.

[0120] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0121] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0122] This specification and accompanying drawings are merely illustrative examples of the invention and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its scope. Therefore, if such modifications and modifications fall within the scope of the invention and its equivalents, the invention is intended to include these modifications and modifications.

Claims

1. A method for dynamic temperature control of prefabricated modular container houses based on model prediction, characterized in that, The method includes: Based on the material and structural information of the target model container house, a thermal conductivity model of the target model container house is built; The heat transfer data of the target model container house under different light, temperature and stacking methods are obtained, and a dynamic heat transfer model of the target model container house is built based on the heat conduction model. Obtain the deployment geographic information of the target container belonging to the target model, wherein the deployment geographic information includes at least latitude, orientation, and light shading information; Based on the deployment geographic information and the stacking method of the target container, the illumination parameters in the dynamic heat transfer model are limited to obtain the exclusive heat transfer model of the target container. Obtain historical meteorological information of the target container deployment location, and based on the historical meteorological information, obtain meteorological baseline information of the deployment location; Obtain the predicted meteorological information of the target container deployment location, and correct the meteorological baseline information for a future preset period based on the predicted meteorological information to obtain future environmental meteorological information; Obtain the preset temperature information and real-time temperature information of the target container; Based on the current moment and the dedicated heat transfer model, according to the preset temperature information, real-time temperature information and future environmental meteorological information, the time-series heat difference required for the target container to maintain the preset temperature information in the future preset time period is obtained; Based on the time-series heat difference, configure the cooling or heating capacity of the container room temperature control equipment for a future preset time period.

2. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 1, characterized in that, Based on the material and structural information of the target model container house, a thermal conductivity model of the target model container house is constructed, including: Obtain the material and structural information of the target model container house. The material information includes at least the thickness of the color steel plate, the thickness and density of the sandwich insulation material, the thermal conductivity parameters of the color steel plate, the thermal conductivity parameters of the sandwich insulation material, and the glass type. The structural information includes at least the door and window dimensions and the door and window positions. Based on the structural information, the target model container house is decomposed into multiple thermal nodes, which include at least wall nodes and door and window nodes; Based on the material information, calculate the thermal resistance and thermal capacity of the plurality of thermal nodes; wherein, the thermal resistance includes thermal conductivity resistance, surface heat transfer resistance, and radiative heat transfer resistance; Based on the connection relationship between thermal nodes, multiple thermal balance equations are established to obtain the thermal conductivity model of the target type container house.

3. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 1, characterized in that, Acquire heat transfer data of the target model container house under different lighting conditions, temperatures, and stacking methods, and based on the aforementioned heat conduction model, construct a dynamic heat transfer model of the target model container house, including: Under various lighting conditions, the surface temperature of the target model container, the indoor air temperature, and the solar radiation intensity were measured to obtain light-induced heat transfer data. Under controlled temperature conditions, different indoor and outdoor temperature differences were set for the target model container house, and the steady-state heat flux and the time to reach steady state of the target model container house were measured as temperature heat transfer data; Under simulated actual stacking conditions, the heat transfer effect data between the contact surfaces of the containers that are in contact with each other is measured and used as the stacking heat transfer data. Based on the light heat transfer data, air temperature heat transfer data, and stacked heat transfer data, the parameters of the heat conduction model are corrected to obtain the dynamic heat transfer model.

4. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 1, characterized in that, Based on the deployment geographic information and the stacking method of the target container, the illumination parameters in the dynamic heat transfer model are limited to obtain a dedicated heat transfer model for the target container, including: Obtain the stacking method of the target container, wherein the stacking method includes at least the stacking contact area; Calculate the deployment azimuth and tilt angle of the target container relative to the sun based on its orientation. Based on the latitude and real-time time, the solar altitude angle and solar azimuth angle are calculated using a solar position algorithm; Based on the deployment azimuth, deployment tilt, solar altitude angle, solar azimuth, and light shading information, sunlight is decomposed into three radiation components: direct, scattered, and ground reflection. Based on these three radiation components, the effective projected radiation intensity of each surface of the target container is calculated. The light shading information is directly used to reduce or eliminate the direct radiation component on the corresponding container surface. Obtain the annual solar activity information of the target container deployment location, and then calculate the annual effective projected radiation intensity of the target container deployment location based on the annual solar activity information; The effective projected radiation intensity throughout the year and the stacking method are updated to the dynamic heat transfer model to obtain the exclusive heat transfer model of the target container.

5. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 1, characterized in that, Obtain historical meteorological information of the target container deployment location, and based on the historical meteorological information, obtain meteorological baseline information of the deployment location, including: Based on the meteorological data center, hourly historical meteorological data of the target container deployment location over the past several years are obtained as the historical meteorological information. Extract several sets of temperature, light radiation, and wind speed information for the target container deployment location over the past few years from the historical meteorological information according to seasonal sequence. After outlier removal from the aforementioned sets of temperature information, light radiation information, and wind speed information, several sets of stable temperature information, stable light radiation information, and stable wind speed information are obtained. Interval analysis is performed on the aforementioned sets of stable temperature information, stable light radiation information, and stable wind speed information to obtain temperature baseline information, light radiation baseline information, and wind speed baseline information, which together serve as the meteorological baseline information.

6. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 5, characterized in that, After obtaining the meteorological baseline information of the deployment location, the method further includes: Obtain the current time, and retrieve historical data from the aforementioned sets of stable temperature information, stable light radiation information, and stable wind speed information based on the current time to obtain several sets of stable temperature information, stable light radiation information, and stable wind speed information from the same historical time. Calculate the variances of the several stable temperature information, stable light radiation information, and stable wind speed information respectively, and configure the temperature baseline confidence, light radiation baseline confidence, and wind speed baseline confidence in real time based on the variances; Based on the meteorological baseline information, the current climate type is identified, and according to the climate type, influence weights are assigned to the confidence levels of temperature baseline, solar radiation baseline, and wind speed baseline. Based on the aforementioned influence weights, the confidence scores of the temperature baseline, solar radiation baseline, and wind speed baseline are weighted and fused to obtain the meteorological baseline confidence score.

7. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 5, characterized in that, Obtain predicted meteorological information for the target container deployment location, and based on the predicted meteorological information, correct the meteorological baseline information for a future preset time period to obtain future environmental meteorological information, including: Obtain forecast meteorological information for a future preset time period and align it with the meteorological baseline information within the future preset time period on the time axis; The predicted meteorological information is used to correct the meteorological baseline information to obtain future environmental meteorological information, wherein the correction magnitude of the predicted meteorological information to the meteorological baseline information is inversely proportional to the confidence level of the meteorological baseline.

8. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 1, characterized in that, Based on the current moment and a dedicated heat transfer model, and according to the preset temperature information, real-time temperature information, and future environmental meteorological information, the time-series heat difference required for the target container to maintain the preset temperature information within a preset time period is obtained, including: The real-time temperature information is used as an initial condition and input into the dedicated heat transfer model; Future environmental and meteorological information is used as a known time-series disturbance and input into a dedicated heat transfer model. An optimization objective function is constructed based on the specific heat transfer model and the preset temperature information. The optimization objective function aims to maintain the preset temperature information, and the optimization variable is the heat difference of the input system. Solve the objective function to obtain the heat difference required to maintain the preset temperature information; Continue to predict the heat difference sequence required to maintain the preset temperature information within a future preset time period, and use it as the time-series heat difference.

9. The method for dynamic temperature control of prefabricated modular container houses based on model prediction according to claim 1, characterized in that, Based on the aforementioned time-series heat difference, the cooling or heating capacity of the container room temperature control equipment is configured for a future preset time period, including: Obtain the operating status information of the temperature control equipment in the target container, including the cooling capacity-power curve and the heating capacity-power curve; Based on the time-series heat difference, calculate the total heat deficit within the preset control period; Based on the total heat deficit, the cooling or heating capacity within a preset control cycle is configured as the basis for control. The control basis is reviewed, and the operating condition information is checked to generate control instructions for the temperature control device within a preset control cycle, and these instructions are sent to the temperature control device for execution. The control instructions include at least the operating mode and operating power.

10. A model-predictive-based dynamic temperature control system for modular prefabricated container houses, characterized in that, The system is used to implement the model-prediction-based dynamic temperature control method for prefabricated container houses according to any one of claims 1-9, the system comprising: The thermal conductivity model building module is used to build a thermal conductivity model of the target model container house based on the material and structural information of the target model container house; The dynamic heat transfer modeling module is used to acquire heat transfer data of the target model container house under different light, temperature and stacking methods, and build a dynamic heat transfer model of the target model container house based on the heat conduction model. The geographic information acquisition module is used to acquire the deployment geographic information of the target container belonging to the target model container, and the deployment geographic information includes at least latitude, orientation, and light shading information; The heat transfer model generation module is used to limit the illumination parameters in the dynamic heat transfer model based on the deployment geographic information and the stacking method of the target container, so as to obtain the exclusive heat transfer model of the target container. The meteorological baseline acquisition module is used to acquire historical meteorological information of the target container deployment location, and based on the historical meteorological information, acquire meteorological baseline information of the deployment location; The weather forecast correction module is used to obtain the forecast weather information of the target container deployment location, and correct the meteorological baseline information for a future preset period based on the forecast weather information to obtain future environmental weather information. The temperature information acquisition module is used to acquire the preset temperature information and real-time temperature information of the target container. The heat demand prediction module is used to obtain the time-series heat difference required for the target container to maintain the preset temperature information within a preset time period in the future, based on the current time and the dedicated heat transfer model, according to the preset temperature information, real-time temperature information and future environmental meteorological information. The temperature control equipment configuration module is used to configure the cooling or heating capacity of the container temperature control equipment within a future preset time period based on the time-series heat difference.

Images