Central air conditioning installation method and system based on intelligent sensing mechanism

Abstract

The application provides a central air conditioner installation method and system based on an intelligent sensing mechanism, and the method mainly comprises an installation scheme set acquisition step, a heat source prediction model construction step, an installation scheme dynamic adjustment step and a scheme verification and calibration step. Through a full closed-loop technical framework of "sensing, prediction, optimization and calibration", the central air conditioner installation scheme is cooperatively optimized in terms of thermal comfort, balance, energy consumption and response speed, and an efficient solution is provided for precise deployment of a building intelligent air conditioner system.

Description

Technical Field

[0001] This invention relates to the field of air conditioning installation, specifically to a central air conditioning installation method and system based on an intelligent sensing mechanism. Background Technology

[0002] With the increasing demand for building intelligence and energy conservation and emission reduction, the installation scheme of central air conditioning systems has a more significant impact on indoor thermal environment control and energy consumption. Existing central air conditioning installation methods mainly have the following shortcomings: Traditional installation solutions rely heavily on experience and lack adaptability. They depend on engineers' experience to determine the location and number of indoor units and air vents, lacking precise matching to building structure and thermal characteristics. For example, in mixed spaces like open-plan offices and enclosed meeting rooms, a uniform installation model can easily lead to excessively high or low temperatures in certain areas, making it difficult to prioritize the thermal comfort needs of key areas such as workstations. Furthermore, current technologies rely on static assumptions regarding indoor heat sources such as personnel movement, equipment heat dissipation, and solar radiation, failing to establish dynamic prediction mechanisms that adapt to changes over time and in different scenarios. When heat source distribution changes abruptly, such as during impromptu meetings leading to dense crowds or sudden high equipment loads, the air conditioning system cannot adjust its airflow strategy in time, resulting in decreased temperature uniformity and even localized "heat islands" or "cold islands." Finally, traditional optimization solutions focus on a single objective, such as minimizing energy consumption, neglecting the synergistic needs of thermal comfort, temperature uniformity, and rapid response. For example, simply pursuing energy reduction may lead to the concentration of air vents in non-critical areas, resulting in a delayed cooling rate in office areas and an inability to meet real-time thermal comfort requirements. The lack of a closed-loop verification mechanism limits the reliability of the solution; after installation, deviations between the system's operational performance and simulation predictions are difficult to be fed back into the solution optimization process. Deviations caused by factors such as the actual thermal parameters of the building envelope and equipment performance degradation cannot be calibrated, potentially leading to increased energy consumption and decreased comfort during long-term operation.

[0003] Therefore, in order to solve the problems existing in the prior art, the present invention proposes a central air conditioning installation method and system based on intelligent sensing mechanism. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a central air conditioning installation method and system based on an intelligent sensing mechanism.

[0005] A central air conditioning installation method based on an intelligent sensing mechanism includes the following steps: The steps for obtaining the installation scheme set are as follows: Based on the 3D model of the installation area, the geometric structure and thermal parameters of the installation area are obtained to construct a digital twin. Air conditioning installation data of the same scenario as the digital twin are called from the historical operation database to generate an initial candidate installation scheme set including the location, air outlet direction and quantity of indoor units. The heat source prediction model construction steps are as follows: Based on the three-dimensional model of the installation area and combined with historical heat source data, a dynamic heat source distribution prediction model is established, and the predicted spatial location, predicted intensity, and predicted coverage of the heat source in the current installation area are output as heat source spatial distribution data. The installation scheme is dynamically adjusted step by step. Based on the initial candidate installation scheme set and the heat source spatial distribution data, the environmental perception sensor is simulated to collect real-time temperature, humidity and heat source information. The candidate scheme is simulated and iterated using a multi-objective optimization algorithm and the optimized installation scheme set is output. The scheme verification and calibration steps involve actually installing the air conditioning system according to the optimized installation scheme set, acquiring operating data through the actual installed sensor network, comparing the deviation values ​​between the measured operating data and the simulation results, correcting the digital twin parameters, and generating an updated installation scheme.

[0006] As a further improvement of the present invention, the step of obtaining the installation scheme set includes: extracting the wall dimensions and door and window coordinates as the geometric structure of the installation area through the building information model and mapping the physical structure of the installation area in the digital twin; extracting the thermal conductivity of the material as a thermal parameter; retrieving case datasets in the historical operation database that are similar to the current installation area structure and use; and generating an initial candidate installation scheme set based on the combination of indoor unit installation coordinates, air outlet layout angles and quantities in the case dataset.

[0007] As a further improvement of the present invention, the heat source prediction model construction step includes: inputting the thermal parameters, seasonal time variables and equipment operation schedules and loading infrared thermal map samples of the same scene from the historical heat source database; extracting the location intensity features of densely populated areas and equipment clusters; fusing real-time solar radiation flux data monitored by light intensity sensors; calculating the theoretical temperature rise curves of each region; and outputting time-stamped heat source spatial distribution data. The heat source spatial distribution data includes the core coordinates of the heat source as the predicted spatial location, the temperature intensity gradient as the predicted heat source intensity, and the radiation range boundary as the predicted coverage area data.

[0008] As a further improvement of the present invention, the dynamic adjustment step of the installation scheme includes marking key monitoring areas in the digital twin based on the core coordinates and radiation boundary of the heat source in the heat source distribution data, densely deploying temperature and humidity sensors in the office area with temperature uniformity as a constraint, deploying an infrared thermal imager at the heat source radiation boundary, and collecting airflow speed, heat source intensity and local temperature and humidity data to drive the digital twin to dynamically update the thermal field distribution.

[0009] As a further improvement of the present invention, the dynamic adjustment step of the installation scheme further includes: inputting the initial candidate installation scheme set and heat source spatial distribution data into the optimization engine; setting regional temperature priority weight coefficients, temperature difference thresholds between key areas, and air conditioning thermal efficiency evaluation indicators; generating a three-dimensional temperature field cloud map through computational fluid dynamics simulation based on the initial candidate installation scheme set; evaluating the cooling rate based on the spatial relationship between the air supply path and the core area of ​​the heat source; obtaining the weighted average temperature based on the regional temperature priority weight coefficients; calculating the temperature balance index by statistically summing the squares of the temperature differences at monitoring points; and obtaining the optimized installation scheme set through a non-dominated sorting genetic algorithm.

[0010] As a further improvement of the present invention, the temperature balance index calculation includes: parsing the regional weight coefficient definition table to obtain the priority weight values ​​of the office area and the open area; extracting the average temperature of each zone in the simulated temperature field and calculating the global weighted average temperature according to the weights; calculating the instantaneous difference between the temperature and humidity monitoring point data and the weighted average temperature for each monitoring point; multiplying the difference of the monitoring point in the office area by the weight coefficient and then squaring it, and directly squaring the monitoring point in the open area; finally, calculating the arithmetic mean of all the calculation results and outputting it as the temperature balance quantitative index.

[0011] As a further improvement of the present invention, the scheme verification and calibration steps include: after installing and operating the air conditioning system according to the optimized installation scheme set, collecting actual temperature and humidity distribution, equipment power, and air outlet wind speed data through a sensor network; calculating measured thermal efficiency indicators, temperature balance indicators, and energy consumption indicators; performing item-by-item difference between the measured values ​​and the simulated values; if the absolute value of the difference of any indicator exceeds a preset tolerance threshold, initiating deviation source analysis: detecting deviations in building envelope thermal capacity parameters, heat source intensity mapping errors, or equipment airflow-power consumption curve offsets; correcting the corresponding parameters in the digital twin through a backpropagation algorithm, generating a model correction parameter table, and outputting an updated installation scheme; the air conditioning system includes an indoor air conditioning unit, air outlets, and a sensor network for real-time data detection, the sensor network including temperature and humidity sensors, light intensity sensors, infrared thermal imagers, airflow sensors, and equipment power sensors.

[0012] As a further improvement of the present invention, the generation of the model calibration parameter table includes: when the temperature balance index deviation exceeds the limit, adjusting the heat source radiation range parameter in reverse according to the weight ratio of the office area and the open area; when the thermal efficiency index deviation exceeds the limit, correcting the turbulence coefficient of the airflow organization model according to the spatial topological relationship between the air supply angle and the heat source area; when the energy consumption index deviation exceeds the limit, updating the slope of the energy efficiency curve based on the ratio of the actual power of the equipment to the simulated air volume; and normalizing all calibration parameters through the error distribution model of the historical database to form a calibration parameter comparison table that matches the current building scenario.

[0013] A central air conditioning installation system based on an intelligent sensing mechanism includes: The installation scheme acquisition module obtains the geometric structure and thermal parameters of the installation area based on the 3D model of the installation area to construct a digital twin. It calls the air conditioning installation data of the same scenario as the digital twin in the historical operation database to generate an initial candidate installation scheme set including the location of the indoor unit, the direction and number of air outlets. The heat source prediction model construction module establishes a dynamic heat source distribution prediction model based on the three-dimensional model of the installation area and historical heat source data, and outputs the predicted spatial location, predicted intensity and predicted coverage of the heat source in the current installation area as heat source spatial distribution data. The dynamic adjustment module for installation schemes, based on the initial candidate installation scheme set and the spatial distribution data of heat sources, simulates the deployment of environmental sensing sensors to collect real-time temperature, humidity and heat source information, uses a multi-objective optimization algorithm to simulate and iterate the candidate schemes and outputs an optimized installation scheme set. The scheme verification and calibration module actually installs the air conditioning system according to the optimized installation scheme set, acquires operating data through the actual installation sensor network, compares the deviation value between the measured operating data and the simulation results, corrects the digital twin parameters, and generates an updated installation scheme.

[0014] As a further improvement of the present invention, the environmental sensing sensor includes a temperature and humidity sensor, an infrared thermal imager, a light intensity sensor, an airflow sensor, and a device power sensor.

[0015] The beneficial effects of this invention are: 1. Achieving efficient thermal comfort by prioritizing key areas: Precise mapping of building structure and thermal parameters using digital twins, combined with historical case data, generates initial plans to ensure the spatial compatibility of air conditioning equipment layout with key areas such as office spaces. A dynamic heat source prediction model tracks changes in heat sources such as people, equipment, and solar radiation in real time, allowing for targeted adjustments to vent direction and airflow intensity, thus improving the thermal comfort compliance rate in key areas.

[0016] 2. To improve temperature uniformity and minimize regional temperature differences, a multi-objective optimization algorithm is used, treating temperature uniformity as a hard constraint. A three-dimensional temperature field cloud map is generated through computational fluid dynamics simulation to quantitatively evaluate the temperature distribution uniformity of different schemes. The temperature balance index calculation method, through differentiated weight design, prioritizes reducing the temperature difference contribution of key areas, thereby reducing the overall indoor temperature standard deviation.

[0017] 3. Optimize energy efficiency and reduce system operating energy consumption. Under the premise of meeting thermal comfort and temperature balance, a multi-objective optimization algorithm is used to balance the spatial relationship between the air supply path and the core heat source area, reducing ineffective air supply energy consumption. Combined with real-time data from equipment power sensors and energy efficiency curve correction, the system's operating energy consumption is reduced compared to traditional solutions. Attached Figure Description

[0018] Figure 1 This is a flowchart of a central air conditioning installation method based on an intelligent sensing mechanism according to the present invention. Figure 2 This is a flowchart of the temperature balance index calculation process of the present invention; Figure 3 This is a flowchart of the model calibration parameter table construction process of the present invention; Figure 4 This is a flowchart of the verification and calibration steps of the present invention; Figure 5 This is a block diagram of a central air conditioning installation system based on an intelligent sensing mechanism according to the present invention. Detailed Implementation

[0019] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Identical components are denoted by the same reference numerals. It should be noted that the terms "front," "rear," "left," "right," "upper," and "lower" used in the following description refer to directions in the accompanying drawings, and the terms "bottom surface," "top surface," "inner," and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0020] The central air conditioning installation method based on intelligent sensing mechanism disclosed in this invention realizes intelligent, precise and dynamic optimization of the central air conditioning installation scheme by constructing a full-process technical framework of "digital twin modeling - dynamic heat source prediction - multi-objective optimization iteration - actual measurement closed-loop calibration".

[0021] A central air conditioning installation method based on intelligent sensing mechanism, such as Figures 1 to 4 As shown, it includes the following steps: The steps for obtaining the installation scheme set are as follows: Based on the 3D model of the installation area, the geometric structure and thermal parameters of the installation area are obtained to construct a digital twin. Air conditioning installation data of the same scenario as the digital twin are called from the historical operation database to generate an initial candidate installation scheme set including the location, air outlet direction and quantity of indoor units. In the installation scheme acquisition step, the digital twin constructed based on the 3D model of the installation area can accurately map the building's physical structure and thermal characteristics, solving the problem of insufficient structural adaptability caused by the reliance on experience in traditional installation schemes; calling data of similar scenarios from the historical operation database to generate the initial scheme set reduces the blindness of scheme design and improves the matching degree between the initial scheme and the scenario.

[0022] The heat source prediction model construction steps are as follows: Based on the three-dimensional model of the installation area and combined with historical heat source data, a dynamic heat source distribution prediction model is established, and the predicted spatial location, predicted intensity, and predicted coverage of the heat source in the current installation area are output as heat source spatial distribution data. The heat source prediction model construction steps overcome the limitations of static heat source assumptions by integrating historical heat source data with real-time environmental parameters. It can dynamically output heat source spatial distribution data at different times, reducing the prediction error of heat source location and intensity, and providing an accurate heat source benchmark for subsequent scheme optimization.

[0023] The installation scheme is dynamically adjusted step by step. Based on the initial candidate installation scheme set and the heat source spatial distribution data, the environmental perception sensor is simulated to collect real-time temperature, humidity and heat source information. The candidate scheme is simulated and iterated using a multi-objective optimization algorithm and the optimized installation scheme set is output. The combination of simulated deployment of environmental sensing sensors and multi-objective optimization algorithms enables iterative evolution of the solution: three-dimensional temperature field cloud maps are generated through computational fluid dynamics simulation, which can intuitively present the temperature control effects of different solutions; the application of non-dominated sorting genetic algorithm can balance thermal efficiency, temperature uniformity and energy consumption targets while meeting constraints such as regional temperature priority weights and temperature difference thresholds, thereby improving the speed of temperature compliance in key areas and reducing regional temperature differences.

[0024] The scheme verification and calibration steps involve actually installing the air conditioning system according to the optimized installation scheme set, acquiring operating data through the actual installed sensor network, comparing the deviation values ​​between the measured operating data and the simulation results, correcting the digital twin parameters, and generating an updated installation scheme.

[0025] The scheme verification and calibration steps construct a dynamic correction mechanism by comparing and analyzing measured data and simulation results. When any index deviation exceeds the limit, the digital twin parameters can be corrected through the backpropagation algorithm, so that the model prediction accuracy can be continuously improved. After several iterations, the consistency between simulation and measured data gradually improves.

[0026] Specifically, such as Figures 1 to 4 As shown, the steps for obtaining the installation scheme set include: extracting wall dimensions and door / window coordinates from the building information model as the geometric structure of the installation area and mapping the physical structure of the installation area in the digital twin; extracting the thermal conductivity of the material as a thermal parameter; retrieving case datasets from the historical operation database that are similar to the current installation area structure and purpose; and generating an initial candidate installation scheme set based on the combination of indoor unit installation coordinates, air vent layout angles, and quantities in the case datasets.

[0027] In the building information extraction stage, the BIM model can accurately extract geometric parameters such as wall dimensions (e.g., office partition wall thickness 300mm, load-bearing wall thickness 500mm), and door and window coordinates (e.g., south-facing floor-to-ceiling window coordinates X=10.2m, Y=3.5m, dimensions 2.4m×1.8m), and directly map them into the digital twin, ensuring minimal error in the digital reconstruction of the physical structure. Simultaneously, material thermal conductivity parameters such as reinforced concrete thermal conductivity of 1.74W / m are extracted. K, Thermal conductivity of glass curtain wall: 2.8 W / m Thermal parameters such as K provide crucial physical property support for subsequent thermal field simulations, specifically including: A Building Information Modeling (BIM) processing engine supporting the IFC format is used to import a high-precision BIM model of the target installation area. This engine automatically identifies building envelope components such as walls, doors, and windows by parsing the hierarchical structure of the BIM model from building to floor to room to component, and extracts their basic attribute information such as component ID, type, and material association code. For example, in the BIM model generated by Revit, the attribute sets of the "Wall" and "Door / Window" classes are called through the API interface to filter out non-virtual components and exclude temporary reference lines, annotations, etc., ensuring that the extracted objects are physical entity structures. For refined extraction of wall geometric parameters, key geometric parameters are obtained for wall components through the following sub-steps: Dimensional parameters are extracted by calling the "Width" thickness, "Height" height, and "Length" attributes of the wall in the BIM model. For non-standard straight walls such as curved walls and sloping walls, the axis coordinates are discretized and sampled at intervals of 0.1m to calculate the curve length and radius of curvature. For composite walls such as sandwich insulated walls, the thickness of each material layer is extracted layer by layer, such as 300mm for the outer concrete layer, 50mm for the insulation layer, and 15mm for the inner gypsum board layer.

[0028] Spatial coordinate positioning establishes a three-dimensional coordinate system with a fixed reference point on the first floor of the building, such as the center of the southwest corner column, as the origin. The X-axis is in the east-west direction, the Y-axis is in the north-south direction, and the Z-axis is in the height direction. The three-dimensional coordinates of the start and end points of the wall axis are extracted. For example, the axis of a partition wall in an office area is 5.0m, 3.0m, 0.0m to 5.0m, 8.0m, 3.5m. The coordinates of the connection nodes between the wall and the ground and ceiling are also recorded to ensure that the spatial position is unambiguous.

[0029] Structural feature marking identifies whether a wall is a load-bearing wall by judging its material strength properties. For example, a concrete wall is marked as load-bearing. It also identifies whether the wall contains reserved openings, such as duct penetration holes, and records the center coordinates and dimensions of the openings, such as φ0.3m opening center coordinates 5.0m, 5.0m, 2.5m.

[0030] For precise extraction of door and window geometric parameters, the following operations are performed on door and window components: Coordinate and dimension extraction is performed by extracting the three-dimensional boundary coordinates of door and window openings, such as the lower left corner coordinates of a south-facing window (10.2m, 3.5m, 0.8m) and the upper right corner coordinates (12.6m, 3.5m, 2.6m), to calculate the door / window width as 2.4m and the height as 1.8m. For special types such as sliding doors and rotating windows, the opening direction is additionally extracted, such as the sliding direction of a sliding door along the X-axis and the opening angle range, such as the maximum opening angle of a rotating window (30°).

[0031] The installation attribute association records the installation height of doors and windows (e.g., windowsill 0.8m from the ground), frame material (e.g., aluminum alloy), and glass type (e.g., double-glazed glass), and associates them with the corresponding wall ID to clarify their spatial attachment relationship in the building structure.

[0032] Standardization and error verification of geometric parameters automatically converts imperial units such as inches in the BIM model to meters, retaining three decimal places (e.g., 0.254m instead of 10 inches). Collision detection algorithms verify the spatial relationship between walls and doors / windows, checking that door / window openings are completely contained within their corresponding walls with a deviation not exceeding 0.01m to avoid geometric inconsistencies such as "floating doors / windows" or "wall penetration." For complex spaces like polygonal rooms, the angles and closure of each wall are calculated to ensure the room's outline is free of gaps. Randomly selected 3-5 key structural elements, such as main wall thickness and floor-to-ceiling window width, are measured on-site with a laser ranging accuracy of ±0.005m. If the deviation between the BIM model extracted value and the measured value exceeds 2%, a linear correction formula (correction value = measured value × model value / measured value) is used to calibrate the parameters of this type of component.

[0033] The thermal parameters are extracted by referencing the material association codes of components in the BIM model. The built-in database of thermal performance of building materials contains the thermal conductivity λ, specific heat capacity c, and density ρ of more than 500 common building materials. The thermal conductivity of each material layer of the wall is automatically matched and extracted, such as λ=1.74W / m·K for reinforced concrete and λ=0.18W / m·K for aerated concrete. The heat transfer coefficient K value of door and window glass, such as K=2.7W / m²·K for double-glazed windows, and the linear heat transfer coefficient ψ value of frame material, such as ψ=0.06W / m·K for aluminum alloy window frames.

[0034] Mapping of geometric and thermal properties of digital twins. Based on the processed coordinates and dimensions of the walls, doors, and windows, solid models are generated in digital twin platforms such as Unity and Unreal Engine using parametric modeling tools. The walls are modeled using extrusion, stretching the length and thickness of the walls along the height direction to form a three-dimensional solid. For doors and windows, Boolean operations are used to subtract the geometry of the openings at the corresponding wall positions, and spatial coordinates consistent with the BIM model are assigned to ensure that the spatial mapping error between the digital twin and the actual building is ≤0.05m.

[0035] In the physics engine module of the digital twin, the extracted parameters such as thermal conductivity and heat transfer coefficient are associated with the material property set of the corresponding geometric components. For example, the material node of the "south exterior wall" component is assigned a value of λ=1.74W / m·K, and the "office area window" is assigned a value of K=2.7W / m²·K, so that the digital twin has the physical basis for heat conduction simulation.

[0036] Structured attribute tags such as "wall: thickness 0.3m, material concrete, thermal conductivity 1.74" and "WD-02# window: coordinates 10.2, 3.5, 0.8-12.6, 3.5, 2.6, glass type double-glazed" are embedded in the digital twin to provide queryable structural feature data for subsequent historical case retrieval and solution generation.

[0037] Through the above steps, the digital twin can accurately reproduce the physical structure and thermal characteristics of the installation area, and its geometric parameters are significantly improved to match the actual building, providing a high-fidelity digital foundation for the generation of initial candidate installation schemes.

[0038] The historical case retrieval process employs a three-level similarity matching mechanism: Level 1 matching is based on building structure similarity, such as room outline overlap ≥80%; Level 2 matching is based on functional consistency, such as both being open-plan office areas; and Level 3 matching is based on heat source characteristic similarity, such as equipment density and peak personnel number deviation ≤20%. Based on the matching results, 5-10 optimal cases are selected from the historical database, and their indoor unit installation coordinates (e.g., 2.5m from the west wall, 3.0m from the north wall), air outlet layout angles (e.g., horizontal deflection angle of 15°, vertical tilt angle of 10°), and quantity combinations (e.g., 2 three-horsepower indoor units with 8 air outlets) are extracted. Through parameterized combinations, an initial candidate installation scheme set containing 20-30 schemes is generated, significantly reducing the trial-and-error cost of scheme design.

[0039] Specifically, such as Figures 1 to 4 As shown, the steps for constructing the heat source prediction model include: inputting the thermal parameters, seasonal time variables, and equipment operation schedules, and loading infrared thermal map samples of the same scene from the historical heat source database; extracting the location intensity features of densely populated areas and equipment clusters; fusing real-time solar radiation flux data monitored by light intensity sensors; calculating the theoretical temperature rise curves for each region; and outputting time-stamped spatial distribution data of the heat source. The spatial distribution data of the heat source includes the core coordinates of the heat source as the predicted spatial location, the temperature intensity gradient as the predicted intensity of the heat source, and the radiation range boundary as the predicted coverage area data.

[0040] The heat source prediction model construction steps achieve accurate prediction of heat source distribution through multi-dimensional parameter fusion and dynamic feature extraction, providing a dynamic benchmark for installation scheme optimization.

[0041] The input parameter system for this step covers both static and dynamic parameters: static parameters include building thermal parameters such as the heat transfer coefficient of the building envelope and spatial geometric features such as room depth and window opening ratio; dynamic parameters include seasonal time variables such as the solar altitude angle on a typical summer day from 10:00 to 16:00, equipment operation schedules such as server room full-load operation from 8:00 to 20:00, and real-time solar radiation flux collected by a light intensity sensor, in W / m². By loading over 500 infrared thermal image samples of the same scene from the historical heat source database, deep learning algorithms are used to extract the elliptical distribution characteristics of densely populated areas such as office workstation clusters and the location intensity characteristics of rectangular high-temperature areas of equipment clusters such as server racks, forming a heat source feature library.

[0042] The calculation process first calculates the heat gain in the window area based on solar radiation flux data. For example, when each square meter of glass window receives 1000W of solar radiation at noon, the local temperature rise rate is 0.8℃ / h. This is combined with equipment power (e.g., a single computer 200W, a printer 300W, and personnel heat dissipation 100W per person) to calculate the theoretical heat generation power. Then, historical temperature rise curves from the same period are integrated to generate theoretical temperature rise curves for each region. The final output is time-stamped spatial distribution data of the heat source, including the core location of the heat source represented by coordinates such as X=5.2m, Y=3.8m, the predicted intensity of the heat source represented by a temperature gradient such as 5℃ / m, and the predicted coverage area defined by a 3℃ temperature difference boundary line, such as a circular area with a diameter of 3m. This allows subsequent optimization schemes to accurately match the dynamic changes of the heat source.

[0043] Specifically, such as Figures 1 to 4 As shown, the dynamic adjustment steps of the installation scheme include marking key monitoring areas in the digital twin based on the core coordinates and radiation boundaries of the heat source in the heat source distribution data, densely deploying temperature and humidity sensors in the office area with temperature uniformity as a constraint, deploying an infrared thermal imager at the heat source radiation boundary, and collecting airflow speed, heat source intensity, and local temperature and humidity data to drive the digital twin to dynamically update the thermal field distribution.

[0044] The sensor deployment strategy in the dynamic adjustment steps of the installation plan provides real-time data support for plan optimization by accurately covering key areas and dynamically driving digital twin updates.

[0045] Based on the core coordinates and radiation boundaries of the heat source in the heat source distribution data, key monitoring areas are first marked in the digital twin. For key areas such as office areas, temperature and humidity sensors are densely arranged at a density of one temperature and humidity sensor per 2-3 square meters to ensure that the distance between monitoring points is ≤1.5m and that there is at least one sensor near each workstation. Infrared thermal imagers are deployed at the radiation boundaries of heat sources, such as the edges of equipment heat dissipation areas, and the regional thermal distribution is obtained by scanning at a frequency of 15 minutes / time, with a resolution of 640×512 pixels, which can identify temperature differences of 0.5℃.

[0046] The data collected by the sensors includes real-time temperature accuracy of ±0.3℃ and humidity accuracy of ±2%RH from the temperature and humidity sensors; heat source intensity error of ≤1℃ from the infrared thermal imager; and wind speed data from the airflow velocity sensor ranging from 0.1 to 10 m / s with an accuracy of ±0.05 m / s. This data is uploaded to the digital twin system in real time via a wireless transmission module, driving dynamic updates to the thermal field distribution—the three-dimensional temperature field model is refreshed every 5 minutes, keeping the deviation between the simulation environment and the actual environment within 3%, providing a high-fidelity computational foundation for subsequent optimization algorithms. Simultaneously, redundant deployment of auxiliary sensors in key areas through the sensor network ensures continuous data acquisition and avoids optimization interruptions due to single-point failures.

[0047] Specifically, such as Figures 1 to 4 As shown, the dynamic adjustment step of the installation scheme further includes inputting the initial candidate installation scheme set and heat source spatial distribution data into the optimization engine, setting regional temperature priority weight coefficients, temperature difference thresholds between key areas, and air conditioning thermal efficiency evaluation indicators, generating a three-dimensional temperature field cloud map through computational fluid dynamics simulation based on the initial candidate installation scheme set, evaluating the cooling rate based on the spatial relationship between the air supply path and the core area of ​​the heat source, obtaining the weighted average temperature based on the regional temperature priority weight coefficients, calculating the temperature balance index by the weighted sum of the squares of the temperature differences at monitoring points, and obtaining the optimized installation scheme set through a non-dominated sorting genetic algorithm.

[0048] The multi-objective optimization engine in the dynamic adjustment step of the installation scheme achieves the global optimal solution of the installation scheme by constructing a multi-dimensional evaluation system and intelligent algorithm iteration.

[0049] The input parameters for the optimization engine include an initial set of 20-30 candidate schemes, spatial distribution data of heat sources including timestamps and constraints, regional temperature priority weighting coefficients such as 0.7 for office areas, 0.2 for corridors, and 0.1 for restrooms, a temperature difference threshold of ≤2℃ between key areas, and air conditioning thermal efficiency evaluation indicators such as a cooling rate ≥1℃ / 10min. During the calculation process, each candidate scheme is first simulated using computational fluid dynamics (CFD) simulation. The supply air temperature is set to 16℃, the initial wind speed to 3m / s, and the simulation duration is 1 hour. This generates a three-dimensional temperature field cloud map containing over 5000 monitoring points. The cloud map has a color temperature resolution of 0.1℃, clearly showing temperature stratification and airflow dead zones.

[0050] The thermal efficiency evaluation index is calculated based on the spatial overlap between the air supply path and the core area of ​​the heat source. When the air supply covers more than 70% of the core area of ​​the heat source, the cooling rate is calculated based on the actual simulation value, such as 1.2℃ / 10min; when the coverage is less than 30%, the cooling rate is reduced by 50%. The temperature balance index is calculated using the weighted square difference method to ensure that the temperature difference weight in key areas is higher.

[0051] The application of a non-dominated sorting genetic algorithm achieves multi-objective optimization. The algorithm population size is set to 100, with a crossover probability of 0.8 and a mutation probability of 0.05. After 50 generations of iteration, the top 5 solutions in the Pareto optimal solution set are selected as the optimized installation scheme set. This process improves efficiency by 80% compared to traditional trial-and-error methods and simultaneously satisfies the objectives of thermal comfort, thermal balance, and energy consumption.

[0052] The implementation process of the multi-objective optimization engine is the core of the dynamic adjustment steps of the installation scheme. Through a closed-loop process of "parameter input - simulation calculation - index quantification - algorithm iteration - scheme output," it achieves the global optimal selection of candidate schemes. The specific steps are as follows: The input parameters of the optimization engine are divided into three main categories: basic data, constraints, and target weights. The specific sources and setting rules are as follows: The initial candidate installation scheme set contains 20-30 schemes. Each scheme specifies the three-dimensional coordinates of the indoor unit installation, such as x=5m, y=5m, z=3m, the number of air outlets, such as 4 air outlets + 2 return air outlets, and the air outlet direction parameters: horizontal deflection angle ±30°, vertical tilt angle 5°-15°.

[0053] Spatial distribution data of heat sources, including the core coordinates of heat sources with timestamps such as 8m, 6m, 0m in densely populated areas, 15m, 12m, 0m in equipment areas, temperature intensity gradient such as 2℃ / m, and radiation range boundary such as a circular area with a diameter of 2m enclosed by the 26℃ isotherm.

[0054] The performance parameters of the air conditioning equipment are retrieved from the equipment database, such as the air volume-static pressure curve (e.g., air volume of 300-800 m³ / h corresponding to static pressure of 50-200 Pa), the cooling capacity curve (e.g., cooling capacity of 3.5 kW at an ambient temperature of 25℃), and the energy efficiency ratio (EER) data, as the basis for energy consumption calculation.

[0055] The regional temperature priority weighting coefficient is determined by parsing the user-preset "Regional Weight Definition Table". For example, the weight of key areas in the office area is 0.7, the weight of non-key areas in the corridor is 0.2, and the weight of restrooms is 0.1, ensuring that the optimization process is tilted towards key areas.

[0056] The temperature difference threshold between key areas is set with hard constraints such as ΔT_max=2℃ based on the building's functional requirements. If the temperature difference between the office area and the meeting room exceeds 2℃ in the simulation, the solution is directly judged as infeasible.

[0057] The thermal efficiency evaluation benchmark defines the minimum cooling rate of the core area of ​​the heat source as ≥1℃ / 10min. Schemes with a lower value are eliminated in the initial screening.

[0058] Computational Fluid Dynamics (CFD) simulation modeling and execution: For each scheme in the initial candidate scheme set, CFD simulation is used to simulate the indoor thermal environment and airflow distribution after the air conditioner is put into operation. The specific process is as follows: The simulation boundary conditions are set, with the spatial boundary based on a digital twin. Geometric parameters of walls, doors, and windows are imported, such as an exterior wall thickness of 300mm and window dimensions of 2.4m × 1.8m, and thermal parameters such as a wall thermal conductivity of 1.74W / m·K. The building envelope is set as an adiabatic boundary to simplify the environmental heat transfer effects in short-term simulations. Equipment operating parameters are uniformly set, with a supply air temperature of 16℃, an initial air velocity of 3m / s, and fixed vent sizes based on equipment models (e.g., 0.3m × 0.3m). The return air vent has a natural return air pressure of 0Pa. Heat source parameters convert the spatial distribution data of heat sources into thermal boundary conditions in the simulation, such as setting the heat dissipation in the personnel area at 100W / person and the equipment area at a constant heat flux density of 800W / unit.

[0059] The installation area is divided into structured grids. In key areas such as the office area and the core heat source area, the grid size is 0.1m×0.1m×0.1m, while in non-key areas, the grid size is relaxed to 0.5m×0.5m×0.5m. The total number of grids is controlled between 500,000 and 1,000,000 to ensure a balance between calculation accuracy and efficiency.

[0060] The Navier-Stokes equations and energy equations were solved using the finite volume method. The number of iterations was set to 5000 to ensure convergence of the flow and temperature fields. The simulation lasted for 1 hour, covering the entire cycle from air conditioner startup to stable operation.

[0061] Output results: A three-dimensional temperature field cloud map containing temperature data from 5000+ monitoring points with a resolution of 0.1℃ is generated. An airflow velocity vector map shows the air supply path and vortex region, as well as the temperature change curve of the heat source area over time, providing data support for subsequent index calculations.

[0062] Multi-dimensional evaluation indicators were quantitatively calculated. Based on CFD simulation results, three core indicators—thermal efficiency, temperature uniformity, and energy consumption—were calculated for each group of candidate schemes. The specific calculation method is as follows: Thermal efficiency index Eff_heat: The calculation steps are based on the quantitative basis of the cooling effect of air conditioning on the core area of ​​the heat source: Extract the temperature change curve over time in the core area of ​​the heat source, such as a range with a diameter of 2m, and determine the temperature drop value ΔT within 10 minutes. For example, if the temperature drops from 30℃ to 28.8℃, ΔT = 1.2℃.

[0063] Calculate the spatial overlap between the air supply path and the core area of ​​the heat source: Determine the angle between the airflow direction at the air outlet and the core point of the heat source through vector analysis. If ≤30° is high coverage, and ≥60° is low coverage, the higher the coverage, the greater the weighting coefficient of the cooling rate. For example, when the coverage is 80%, the weighting coefficient is 0.8.

[0064] The final thermal efficiency index = ΔT × coverage weighting coefficient, such as 1.2℃ × 0.8 = 0.96. The higher the value, the better the cooling effect.

[0065] Temperature balance index ΔT_balanced: Analyze the area weight table and determine that the office area has a weight of 0.7 and the open area has a weight of 0.3.

[0066] Extract the average temperature of each zone in the simulated temperature field, such as 25.2℃ in the office area and 26.8℃ in the corridor, and calculate the global weighted average temperature T_weighted=25.2×0.7+26.8×0.3=25.7℃.

[0067] Calculate the instantaneous difference between each monitoring point and T_weighted. The difference between the monitoring points in the office area is multiplied by the weight 0.7 and then squared. For the open area, the square is taken directly. For example, if the difference of a point in the office area is -0.5℃, it is calculated as -0.5×0.7²=0.1225; if the difference of a point in the open area is +1.1℃, it is calculated as 1.21.

[0068] The arithmetic mean of the squared values ​​of all monitoring points is used to obtain the temperature balance index, such as 0.28. The smaller the value, the more balanced the temperature distribution.

[0069] Energy consumption index E_rel: Based on the simulated air volume data, such as an average air volume of 500 m³ / h and the equipment power curve, such as an air volume of 500 m³ / h corresponding to a power of 1.2 kW, the theoretical hourly power consumption of the scheme is calculated to be 1.2 kW × 1 h = 1.2 kWh.

[0070] If the hourly power consumption of the baseline scheme, such as the scheme with the lowest energy consumption in historical cases, is set as E_base (e.g., 1.5 kWh), then the relative energy consumption E_rel = 1.2 / 1.5 = 0.8. The smaller the value, the more energy-efficient it is.

[0071] Iterative optimization of non-dominated sorting genetic algorithm The non-dominated sorting genetic algorithm NSGA-II is used to optimize candidate schemes through multi-objective optimization. The optimal solution is selected through an iterative process of "population initialization - non-dominated sorting - selection - crossover - mutation". The specific process is as follows: Algorithm parameter settings: Population size: 100. Each iteration processes 100 sets of schemes simultaneously, including initial candidate schemes and iteratively generated schemes.

[0072] The genetic operator, with a crossover probability of 0.8, randomly selects two schemes for crossover combination of equipment location and air vent angle parameters, and with a mutation probability of 0.05, randomly changes the number or direction of air vents in a certain scheme by ±5°.

[0073] The termination condition is that after 50 iterations, if the optimal solution for 5 consecutive iterations shows no significant change and the index fluctuation is ≤5%, then the iteration stops.

[0074] The iterative process includes randomly selecting 100 groups of duplicate schemes from 20-30 initial candidate schemes, and calculating the thermal efficiency, temperature balance index, and energy consumption index of each group. Schemes are then ranked according to the Pareto optimality principle: if all indicators of scheme A are better than those of scheme B, then A dominates B, and B is eliminated; undominated schemes proceed to the next level of ranking, until all schemes are ranked. A tournament selection method is used to randomly select schemes from each level for comparison, retaining the schemes with better indicators to enter the crossover stage. The selected schemes undergo parameter recombination, such as combining the indoor unit position of scheme A with the air vent direction of scheme B, and random mutation, such as adjusting the angle of a certain air vent, to generate new schemes to supplement the population. This ranking-selection-crossover-mutation process is repeated, retaining the top 20% of the best schemes in each generation to gradually improve the overall performance of the population.

[0075] Optimal solution selection: After the iteration terminates, from the Pareto optimal solution set of the final population, there are usually 5-8 schemes. According to the principle of "prioritizing thermal efficiency, while taking into account temperature balance and energy consumption", the weight coefficients can be adjusted according to user needs, such as W_heat=0.4, W_balance=0.3, W_energy=0.3. Calculate the comprehensive score, and select the 5 schemes with the highest scores as the optimized installation scheme set output.

[0076] The output optimized installation scheme set contains the following information: Equipment parameters: 3D coordinates of indoor unit installation, number of air outlets (e.g., 2 indoor units with 8 air outlets), horizontal deflection angle of 15° and downward angle of 10° for air outlet direction.

[0077] Each scheme has a thermal efficiency of 0.92, a temperature balance index of 0.22, and a relative energy consumption of 0.85.

[0078] Three-dimensional temperature field cloud maps and airflow path simulation animations visually demonstrate the temperature control effect of the solution.

[0079] Through this process, the optimization engine can achieve a comprehensive optimization goal of improving thermal efficiency by 30%, reducing the temperature balance index by 40%, and reducing energy consumption by 20% while meeting the hard constraint of temperature difference ≤2℃ in key areas. This improves the adaptability of the solution by more than 50% compared with the traditional single-objective optimization method.

[0080] Specifically, such as Figures 1 to 4 As shown, the temperature balance index calculation includes: parsing the regional weight coefficient definition table to obtain the priority weight values ​​of the office area and the open area; extracting the average temperature of each zone in the simulated temperature field and calculating the global weighted average temperature according to the weights; calculating the instantaneous difference between the temperature and humidity monitoring point data and the weighted average temperature; multiplying the difference of the monitoring point in the office area by the weight coefficient and then squaring it, and directly squaring the monitoring point in the open area; finally, calculating the arithmetic mean of all the calculation results as the output of the temperature balance quantitative index.

[0081] The quantitative calculation method of the temperature balance index, through differentiated weight design and precise data processing, achieves an objective evaluation of indoor temperature balance.

[0082] The calculation process consists of five steps: First, the regional weight coefficient definition table is analyzed to determine the priority weight values ​​for key areas such as office areas and meeting rooms (0.6-0.8), and for open areas such as corridors and storage rooms (0.2-0.4). Second, the simulated temperature field is divided into zones using a 50cm×50cm grid, and the average temperature of each zone is extracted (e.g., an average of 24.5℃ for a certain grid in the office area and 26.2℃ for a certain grid in the corridor). Third, the global weighted average temperature is calculated according to the weights (e.g., 24.5×0.7 + 26.2×0.3 = 25.01). ℃; Fourth step, calculate the instantaneous difference between each monitoring point and the weighted average temperature. For example, a point in the office area is 24.8℃, the difference is +0.21℃; a point in the corridor is 26.0℃, the difference is +0.99℃; Fifth step, multiply the difference of the monitoring points in the office area by the weighting coefficient 0.7 and then square it, such as 0.21×0.7²=0.022. For the monitoring points in the open area, directly square it, such as 0.99²=0.98. Finally, calculate the arithmetic mean of all the calculation results, such as 0.022+0.98 / total number of monitoring points, to obtain the temperature balance index, such as 0.35.

[0083] The smaller the index value, the better the temperature uniformity. When the index is ≤0.5, it is considered to meet the temperature uniformity requirements. Through differentiated weighting design, it is ensured that temperature deviations in key areas such as office areas have a greater impact on the index, which is in line with the invention objective of "prioritizing key areas".

[0084] Specifically, such as Figures 1 to 4 As shown, the verification and calibration steps of the scheme include: after installing and operating the air conditioning system according to the optimized installation scheme set, collecting actual temperature and humidity distribution, equipment power, and air outlet wind speed data through a sensor network; calculating measured thermal efficiency, temperature balance, and energy consumption indicators; performing item-by-item difference between the measured values ​​and the simulated values; if the absolute value of the difference of any indicator exceeds a preset tolerance threshold, initiating deviation source analysis: detecting deviations in building envelope thermal capacity parameters, heat source intensity mapping errors, or equipment airflow-power consumption curve offsets; correcting the corresponding parameters in the digital twin through a backpropagation algorithm, generating a model correction parameter table, and outputting an updated installation scheme; the air conditioning system includes an indoor air conditioning unit, air outlets, and a sensor network for real-time data detection, the sensor network including temperature and humidity sensors, light intensity sensors, infrared thermal imagers, airflow sensors, and equipment power sensors.

[0085] The solution verification and calibration steps establish a closed loop of "actual measurement-comparison-tracing-correction," enabling continuous optimization of the digital twin and dynamic updates to the installation plan.

[0086] During system operation, the sensor network, including temperature and humidity, infrared thermal imaging, power, and airflow sensors, collects data every 30 seconds. The actual temperature and humidity distribution is presented as a heat map. The equipment power is accurate to ±5W, and the airflow velocity measurement range is 0-10m / s with an accuracy of ±0.1m / s. Based on this data, three core indicators are calculated: thermal efficiency (the ratio of the actual cooling rate to the target value), temperature balance (calculated through simulated temperature field and monitoring points), and energy consumption (daily power consumption per unit area, kWh / m²).

[0087] When the absolute value of the difference in any indicator exceeds the preset tolerance threshold of ±10% for thermal efficiency, ±0.1 for temperature balance index, and ±15% for energy consumption, deviation source analysis is initiated: by comparing the measured heat capacity parameters of the building envelope (e.g., the actual heat capacity of the wall is 12% higher than the model value), the heat source intensity mapping error (e.g., the actual heat generation of the equipment is 150W higher than the predicted value), and the deviation of the equipment air volume-power consumption curve (e.g., when the actual air volume is 300m³ / h, the power consumption is 80W higher than the model value), the source of the deviation is located.

[0088] The correction process employs a backpropagation algorithm: for deviations in heat capacity parameters, the corresponding parameters in the digital twin are adjusted according to the ratio of measured values ​​to model values, for example, 1.12 times; for errors in heat source intensity, a correction coefficient, such as 1.15, is added to the heat source prediction model; for equipment curve offsets, the airflow-power consumption function is refitted, for example, correcting it from y=0.5x+100 to y=0.6x+120. After correction, a model calibration parameter table is generated, and the installation plan is updated based on the new parameters, improving the system's adaptability to complex environments by more than 30%.

[0089] Specifically, such as Figures 1 to 4 As shown, the generation of the model calibration parameter table includes: when the temperature balance index deviation exceeds the limit, adjusting the heat source radiation range parameter in reverse according to the weight ratio of the office area and the open area; when the thermal efficiency index deviation exceeds the limit, correcting the turbulence coefficient of the airflow organization model according to the spatial topological relationship between the air supply angle and the heat source area; when the energy consumption index deviation exceeds the limit, updating the slope of the energy efficiency curve based on the ratio of the actual power of the equipment to the simulated air volume; and normalizing all calibration parameters through the error distribution model of the historical database to form a calibration parameter comparison table that matches the current building scenario.

[0090] The generation process of the model calibration parameter table, through sub-index deviation processing and normalization calibration, achieves accurate correction of digital twin parameters.

[0091] When the temperature balance index deviates beyond the limit, the heat source radiation range parameter is adjusted in reverse according to the weight ratio of office area and open area, for example, 7:3: If the measured temperature difference in office area is too large, the heat source radiation range is expanded by 10%×0.7 on the basis of the original prediction, while the radiation range in open area is reduced by 5%×0.3, so that the heat source coverage of key areas is more accurate.

[0092] When the thermal efficiency index deviates beyond the limit, the turbulence coefficient of the airflow organization model is corrected according to the spatial topological relationship between the air supply angle and the heat source area: when the angle between the air supply direction and the normal of the heat source area exceeds 30°, the turbulence coefficient is adjusted from 0.025 to 0.03, increasing by 120%, to enhance the airflow diffusion capability; when the angle is less than 15°, the turbulence coefficient is reduced to 0.02, reducing airflow loss.

[0093] When the energy consumption index deviates beyond the limit, the slope of the energy efficiency curve is updated based on the ratio of the actual power of the equipment to the simulated air volume: if the actual power / simulated air volume = 0.8kW / 1000m³ / h, while the model value is 0.6kW / 1000m³ / h, then the slope of the energy efficiency curve will be corrected from 0.6 to 0.8.

[0094] All calibration parameters must be normalized to 95% confidence interval using an error distribution model from a historical database, such as a normal distribution model, to ensure that the correction values ​​are within the allowable error range for similar scenarios. This results in a calibration parameter comparison table that matches the current building scenario, including parameter name, original value, correction value, and correction basis, providing a quantitative basis for subsequent scheme updates.

[0095] A central air conditioning installation system based on an intelligent sensing mechanism, such as Figure 5 As shown, it includes: The installation scheme acquisition module obtains the geometric structure and thermal parameters of the installation area based on the 3D model of the installation area to construct a digital twin. It calls the air conditioning installation data of the same scenario as the digital twin in the historical operation database to generate an initial candidate installation scheme set including the location of the indoor unit, the direction and number of air outlets. The heat source prediction model construction module establishes a dynamic heat source distribution prediction model based on the three-dimensional model of the installation area and historical heat source data, and outputs the predicted spatial location, predicted intensity and predicted coverage of the heat source in the current installation area as heat source spatial distribution data. The dynamic adjustment module for installation schemes, based on the initial candidate installation scheme set and the spatial distribution data of heat sources, simulates the deployment of environmental sensing sensors to collect real-time temperature, humidity and heat source information, uses a multi-objective optimization algorithm to simulate and iterate the candidate schemes and outputs an optimized installation scheme set. The scheme verification and calibration module actually installs the air conditioning system according to the optimized installation scheme set, acquires operating data through the actual installation sensor network, compares the deviation value between the measured operating data and the simulation results, corrects the digital twin parameters, and generates an updated installation scheme.

[0096] Specifically, such as Figure 5 As shown, the environmental sensing sensors include a temperature and humidity sensor, an infrared thermal imager, a light intensity sensor, an airflow sensor, and a device power sensor.

[0097] The foregoing has illustrated and described the basic features, principles, and advantages of the present invention. It should be noted that the present invention is not limited to the above embodiments, but only to some embodiments. Any improvements and additions made without departing from the spirit and scope of the present invention are considered to be within the scope of protection of the present invention.

Claims

1. A central air conditioning installation method based on an intelligent sensing mechanism, characterized in that, Includes the following steps: The steps for obtaining the installation scheme set are as follows: Based on the 3D model of the installation area, the geometric structure and thermal parameters of the installation area are obtained to construct a digital twin. Air conditioning installation data of the same scenario as the digital twin are called from the historical operation database to generate an initial candidate installation scheme set including the location, air outlet direction and quantity of indoor units. The heat source prediction model construction steps are as follows: Based on the three-dimensional model of the installation area and combined with historical heat source data, a dynamic heat source distribution prediction model is established, and the predicted spatial location, predicted intensity, and predicted coverage of the heat source in the current installation area are output as heat source spatial distribution data. The installation scheme is dynamically adjusted step by step. Based on the initial candidate installation scheme set and the heat source spatial distribution data, the environmental perception sensor is simulated to collect real-time temperature, humidity and heat source information. The candidate scheme is simulated and iterated using a multi-objective optimization algorithm and the optimized installation scheme set is output. The scheme verification and calibration steps involve actually installing the air conditioning system according to the optimized installation scheme set, acquiring operating data through environmental sensing sensors, comparing the deviation values ​​between the measured operating data and the simulation results, correcting the digital twin parameters, and generating an updated installation scheme.

2. The central air conditioning installation method based on intelligent sensing mechanism according to claim 1, characterized in that, The steps for obtaining the installation scheme set include: extracting wall dimensions and door / window coordinates from the building information model as the geometric structure of the installation area and mapping the physical structure of the installation area in the digital twin; extracting the thermal conductivity of the material as a thermal parameter; retrieving case datasets from the historical operation database that are similar to the current installation area structure and purpose; and generating an initial candidate installation scheme set based on the combination of indoor unit installation coordinates, air vent layout angles, and quantities in the case datasets.

3. The central air conditioning installation method based on intelligent sensing mechanism according to claim 1, characterized in that, The steps for constructing the heat source prediction model include: inputting the thermal parameters, seasonal time variables, and equipment operation schedules, loading infrared thermal map samples of the same scene from the historical heat source database, extracting the location intensity features of densely populated areas and equipment clusters, fusing real-time solar radiation flux data monitored by light intensity sensors, calculating the theoretical temperature rise curves for each region, and outputting time-stamped spatial distribution data of the heat source. The spatial distribution data of the heat source includes the core coordinates of the heat source as the predicted spatial location, the temperature intensity gradient as the predicted intensity of the heat source, and the radiation range boundary as the predicted coverage area data.

4. A central air conditioning installation method based on an intelligent sensing mechanism according to claim 1 or 3, characterized in that, The dynamic adjustment steps of the installation scheme include marking key monitoring areas in the digital twin based on the core coordinates and radiation boundaries of the heat source in the heat source spatial distribution data, densely deploying temperature and humidity sensors in the office area with temperature uniformity as a constraint, deploying infrared thermal imagers at the heat source radiation boundaries, and collecting airflow speed, heat source intensity, and local temperature and humidity data to drive the digital twin to dynamically update the thermal field distribution.

5. The central air conditioning installation method based on intelligent sensing mechanism according to claim 1, characterized in that, The dynamic adjustment step of the installation scheme further includes inputting the initial candidate installation scheme set and heat source spatial distribution data into the optimization engine, setting regional temperature priority weight coefficients, temperature difference thresholds between key areas, and air conditioning thermal efficiency evaluation indicators, generating a three-dimensional temperature field cloud map through computational fluid dynamics simulation based on the initial candidate installation scheme set, evaluating the cooling rate based on the spatial relationship between the air supply path and the core area of ​​the heat source, obtaining a weighted average temperature based on the regional temperature priority weight coefficients, calculating the temperature balance index by the weighted sum of the squares of the temperature differences at monitoring points, and obtaining the optimized installation scheme set through a non-dominated sorting genetic algorithm.

6. The central air conditioning installation method based on intelligent sensing mechanism according to claim 5, characterized in that, The temperature balance index calculation includes: parsing the regional weight coefficient definition table to obtain the priority weight values ​​of the office area and the open area; extracting the average temperature of each zone in the simulated temperature field and calculating the global weighted average temperature according to the weights; calculating the instantaneous difference between the temperature and humidity monitoring point data and the weighted average temperature; multiplying the difference of the monitoring point in the office area by the weight coefficient and then squaring it, and directly squaring the monitoring point in the open area; finally, calculating the arithmetic mean of all the calculation results as the temperature balance index output.

7. The central air conditioning installation method based on intelligent sensing mechanism according to claim 1, characterized in that, The scheme verification and calibration steps include, after installing and operating the air conditioning system according to the optimized installation scheme set, collecting actual temperature and humidity distribution, equipment power and air outlet wind speed data through environmental sensing sensors. Calculate the measured thermal efficiency index, temperature balance index, and energy consumption index; perform item-by-item difference between the measured values ​​and the simulated values; if the absolute value of the difference of any index exceeds the preset tolerance threshold, initiate deviation source analysis: detect deviations in the thermal capacity parameters of the building envelope, errors in the mapping of heat source intensity, or offsets in the equipment airflow-power consumption curve; correct the corresponding parameters in the digital twin through the backpropagation algorithm, generate a model correction parameter table, and output an updated installation plan; the air conditioning system includes an indoor air conditioning unit, air outlets, and environmental sensing sensors for real-time data detection, including temperature and humidity sensors, light intensity sensors, infrared thermal imagers, airflow sensors, and equipment power sensors.

8. A central air conditioning installation method based on an intelligent sensing mechanism according to claim 7, characterized in that, The generation of the model calibration parameter table includes: when the temperature balance index deviation exceeds the limit, adjusting the heat source radiation range parameter in reverse according to the weight ratio of the office area and the open area; when the thermal efficiency index deviation exceeds the limit, correcting the turbulence coefficient of the airflow organization model according to the spatial topological relationship between the air supply angle and the heat source area; when the energy consumption index deviation exceeds the limit, updating the slope of the energy efficiency curve based on the ratio of the actual power of the equipment to the simulated air volume; and normalizing all calibration parameters through the error distribution model of the historical database to form a model calibration parameter table that matches the current building scene.

9. A central air conditioning installation system based on an intelligent sensing mechanism, applicable to the central air conditioning installation method based on an intelligent sensing mechanism as described in any one of claims 1 to 8, characterized in that, include: The installation scheme acquisition module obtains the geometric structure and thermal parameters of the installation area based on the 3D model of the installation area to construct a digital twin. It calls the air conditioning installation data of the same scenario as the digital twin in the historical operation database to generate an initial candidate installation scheme set including the location of the indoor unit, the direction and number of air outlets. The heat source prediction model construction module establishes a dynamic heat source distribution prediction model based on the three-dimensional model of the installation area and historical heat source data, and outputs the predicted spatial location, predicted intensity and predicted coverage of the heat source in the current installation area as heat source spatial distribution data. The dynamic adjustment module for installation schemes, based on the initial candidate installation scheme set and the spatial distribution data of heat sources, simulates the deployment of environmental sensing sensors to collect real-time temperature, humidity and heat source information, uses a multi-objective optimization algorithm to simulate and iterate the candidate schemes and outputs an optimized installation scheme set. The scheme verification and calibration module actually installs the air conditioning system according to the optimized installation scheme set, acquires operating data through environmental sensing sensors, compares the deviation values ​​between the measured operating data and the simulation results, corrects the digital twin parameters, and generates an updated installation scheme.

10. A central air conditioning installation system based on an intelligent sensing mechanism according to claim 9, characterized in that, The environmental sensing sensors include temperature and humidity sensors, infrared thermal imagers, light intensity sensors, airflow sensors, and equipment power sensors.

Images