Air conditioning equipment installation method and system based on BIM

Abstract

The application provides a BIM-based air conditioning equipment installation method and system, wherein, the application firstly analyzes the physical size, performance parameters of the air conditioning equipment and the spatial structure data of the building, generates multiple installation paths according to the analysis results, and selects the optimal solution path, then carries out visual processing on the on-site construction guidance to generate virtual guidance content and provides voice prompts to obtain interactive help information, then monitors the installation process and uploads it to the cloud building information model environment platform to generate monitoring data flow, then combines the thermodynamic relationship between the air conditioning equipment and the surrounding environment, constructs a thermodynamic prediction model, and controls the unmanned aerial vehicle to patrol the installation quality of the air conditioning equipment to generate a three-dimensional model and a quality inspection report; the technical scheme provided by the application improves the accuracy and efficiency of the installation path planning, realizes comprehensive monitoring of the installation process, and improves the accuracy and comprehensiveness of the installation quality detection.

Description

Technical Field

[0001] This invention relates to the field of air conditioning equipment installation technology, and in particular to a BIM-based air conditioning equipment installation method. Background Technology

[0002] In modern building construction, the installation of air conditioning equipment is a complex and critical task, involving various factors such as equipment size, performance parameters, and the spatial structure of the building. Traditionally, the planning of air conditioning equipment installation paths relies on the experience of engineers and manual measurements. This method is not only inefficient but also prone to errors, leading to frequent adjustments during installation, which increases construction time and costs. In addition, traditional on-site guidance mainly relies on paper drawings or simple electronic documents, which are difficult to provide intuitive operation guidance. Especially in complex construction site environments, workers often find it difficult to accurately understand and execute the installation steps. This limitation of information transmission seriously affects construction efficiency and quality.

[0003] Existing monitoring methods and technical tools have many limitations, which significantly affect the quality and efficiency of air conditioning equipment installation. First, current installation path planning methods lack intelligence and automation, rely on manual judgment and experience, are prone to deviation, and cannot fully consider all possible influencing factors, such as space constraints and optimal airflow distribution, which may lead to suboptimal installation solutions. Summary of the Invention

[0004] This invention provides a BIM-based air conditioning equipment installation method and system to address the problems in existing technologies that lack intelligence and automation, rely on manual judgment and experience, are prone to deviations, and fail to fully consider all possible influencing factors.

[0005] In a first aspect, embodiments of the present invention provide a BIM-based air conditioning equipment installation method, comprising:

[0006] Analyze the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building. Based on the analysis results, plan the installation path of the air conditioning equipment, generate multiple installation paths, and select the optimal solution path from among the multiple installation paths.

[0007] Based on the optimal solution path, the on-site construction guidance is visualized, the on-site environmental features in the visualization results are identified, virtual guidance content is generated according to the identification results, and voice prompts are provided for the virtual guidance content to obtain interactive help information;

[0008] Based on the interactive help information, key parameters during the installation of the air conditioning equipment are monitored, and the monitoring results are uploaded to the cloud-based building information modeling environment platform to generate a monitoring data stream.

[0009] Based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, a thermodynamic prediction model is constructed.

[0010] Using the aforementioned thermodynamic prediction model, a drone equipped with a high-resolution camera and lidar system is controlled to inspect the installation quality of the air conditioning equipment, generating a 3D model and a quality inspection report.

[0011] Optionally, the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building, are analyzed. Based on the analysis results, the installation path of the air conditioning equipment is planned, generating multiple installation paths. The optimal solution path is then selected from these multiple installation paths, including:

[0012] Using a building information modeling environment, we collect and integrate data on the physical dimensions and performance parameters of air conditioning equipment and the spatial structure of buildings, and introduce environmental factors as auxiliary inputs to obtain a comprehensive dataset.

[0013] Based on the comprehensive dataset, a virtual simulation scene is constructed in the building information modeling environment. The virtual simulation scene is used to analyze various environmental factors. Multiple installation paths are generated based on the analysis results. The priority between the installation paths is dynamically balanced through an adaptive weight adjustment mechanism to obtain the optimal set of installation paths.

[0014] A multi-level evaluation is performed on the optimal installation path set to assess the length of each installation path, its impact on the existing structure, the expected airflow optimization results, and the possibility of encountering difficulties during construction, thereby generating a risk coefficient assessment report.

[0015] Based on the set of optimal installation paths and the risk coefficient assessment report, a decision analysis is performed on each installation path, and the optimal solution path is selected based on the analysis results.

[0016] Optionally, based on the comprehensive dataset, a virtual simulation scene is constructed in a building information modeling environment. This virtual simulation scene is used to analyze various environmental factors. Based on the analysis results, multiple installation paths are generated, and an adaptive weight adjustment mechanism is used to dynamically balance the priorities among these installation paths to obtain an optimal set of installation paths, including:

[0017] Based on the comprehensive dataset, a virtual simulation scene is constructed in the building information modeling environment. The installation process of air conditioning equipment is simulated using the virtual simulation scene. Based on the simulation results, the space limitations, installation difficulty, and airflow distribution effect of the air conditioning equipment during the installation process are calculated, and calculation results are generated.

[0018] Based on the calculation results, an in-depth analysis of space limitations, installation difficulty, and airflow distribution effects is conducted, and multiple installation paths are generated based on the analysis results.

[0019] Based on the multiple installation paths, an adaptive weight adjustment mechanism is introduced to dynamically balance the priorities among the installation paths, while adjusting the weight adjustment parameters of each installation path to generate a set of installation paths after weight adjustment.

[0020] Based on the weighted optimized installation path set, a path selection strategy in a multi-objective reinforcement learning framework is initialized. The multi-objective reinforcement learning framework is then used to evaluate and select the weighted optimized installation path set. The path selection strategy is updated based on historical project data and real-time feedback to generate an optimized installation path set. The path selection strategy is pre-built based on historical project data and includes installation path selection patterns and experience from historical successful cases.

[0021] Optionally, based on the optimal solution path, the on-site construction guidance is visualized, the on-site environmental features in the visualization results are identified, virtual guidance content is generated based on the identification results, and voice prompts are provided for the virtual guidance content to obtain interactive help information, including:

[0022] The air conditioning equipment is installed according to the optimal solution path, and the installation process of the air conditioning equipment is visualized to generate a visual view;

[0023] The air conditioning equipment is installed according to the optimal solution path, and the installation process of the air conditioning equipment is visualized to generate a visual view. A convolutional neural network is used to identify the on-site environmental features in the visual view, and virtual guidance content is generated based on the identification results.

[0024] Based on the virtual guidance content, a spatial positioning algorithm is applied in combination with real-time sensor data to locate and correct the installation position of the air conditioning equipment, and an installation position correction instruction is generated.

[0025] Based on the virtual guidance content and installation location correction instructions, a dynamic interactive model is created, voice prompts are generated using the dynamic interactive guidance model, and the voice prompts are added to the virtual guidance content to generate interactive help information;

[0026] Based on the dynamic interactive guidance model, natural language processing technology is applied to generate voice prompts, resulting in interactive help information.

[0027] Optionally, based on the virtual guidance content, a spatial positioning algorithm combined with real-time sensor data is applied to locate and correct the installation position of the air conditioning equipment, generating an installation position correction instruction, including:

[0028] By applying spatial positioning algorithms and combining real-time sensor data, the installation location of the air conditioning equipment is determined, and spatial coordinates and attitude information are obtained.

[0029] Based on the spatial coordinates and attitude information, machine learning algorithms are used to analyze historical installation data and current environmental conditions to predict installation locations outside the preset target, and potential problem warning information is generated based on the prediction results.

[0030] Based on the potential problem warning information, simulation technology is applied to simulate the installation at different locations in a virtual simulation scenario, evaluate the feasibility and advantages and disadvantages of various simulation results, generate installation plan suggestions based on the evaluation results, and output installation location correction instructions based on the installation plan suggestions.

[0031] Based on the optimized installation scheme suggestions and spatial coordinates and attitude information, the installation position is dynamically corrected, the installation path in the virtual guidance content is adjusted according to the actual site conditions, and an installation position correction instruction is generated.

[0032] Optionally, based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, a thermodynamic prediction model is constructed, including:

[0033] An initial thermodynamic relationship model is constructed based on the monitoring data stream uploaded to the cloud-based building information modeling environment platform;

[0034] The operating status of the air conditioning equipment under different working conditions and the interaction between the air conditioning equipment and the surrounding environment are simulated to generate simulation results under various working conditions.

[0035] Based on the simulation results, a machine learning algorithm is applied to train the initial thermodynamic relationship model to obtain the trained thermodynamic relationship model.

[0036] Based on the trained thermodynamic relationship model, combined with digital twin technology, a virtual mapping system for the air conditioning equipment is created. The virtual mapping system is used to synchronize the actual operating status of the air conditioning equipment and predict the performance changes of the air conditioning equipment within a preset time period, generating a dynamic prediction report.

[0037] Based on the dynamic prediction report, the operating status of the air conditioning equipment and the interaction between the air conditioning equipment and the surrounding environment are predicted and processed. Static and dynamic factors are calculated to generate an optimized thermodynamic prediction model.

[0038] Optionally, using the aforementioned thermodynamic prediction model, a drone equipped with a high-resolution camera and lidar system is controlled to inspect the installation quality of the air conditioning equipment, generating a 3D model and a quality inspection report, including:

[0039] Using the aforementioned thermodynamic prediction model, the installation quality of the air conditioning equipment is planned and processed for inspection, the key areas and key indicators of the inspection task are determined, and an inspection task plan is generated.

[0040] According to the flight path in the inspection task plan, the drone equipped with a high-resolution camera and lidar system is controlled to inspect the installation quality of the air conditioning equipment and obtain the original inspection data, which includes on-site images and three-dimensional point cloud data.

[0041] The original inspection data is identified and modeled using image recognition algorithms and 3D reconstruction technology to generate a 3D model.

[0042] Based on the three-dimensional model and the preset quality standards, a comprehensive evaluation of the installation quality of the air conditioning equipment is conducted, and an initial quality inspection report is generated.

[0043] The initial quality inspection report is optimized using natural language processing technology to generate an optimal quality inspection report, which includes marked problem areas and improvement suggestions.

[0044] Secondly, embodiments of the present invention provide a BIM-based air conditioning equipment installation system, comprising:

[0045] The analysis module is used to analyze the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building. Based on the analysis results, the installation path of the air conditioning equipment is planned, multiple installation paths are generated, and the optimal solution path is selected from the multiple installation paths.

[0046] The identification module is used to visualize the on-site construction guidance based on the optimal solution path, identify the on-site environmental features in the visualization results, generate virtual guidance content based on the identification results, and provide voice prompts for the virtual guidance content to obtain interactive help information;

[0047] The monitoring module is used to monitor key parameters during the installation of the air conditioning equipment based on the interactive help information, upload the monitoring results to the cloud building information modeling environment platform, and generate a monitoring data stream.

[0048] The module is used to construct a thermodynamic prediction model based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment.

[0049] The control module is used to control a drone equipped with a high-resolution camera and a lidar system to inspect the installation quality of the air conditioning equipment using the thermodynamic prediction model, and to generate a three-dimensional model and a quality inspection report.

[0050] Thirdly, embodiments of the present invention provide a computing device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a BIM-based air conditioning equipment installation method as described in any of the first aspects.

[0051] Fourthly, embodiments of the present invention provide a computer storage medium storing computer program instructions thereon, wherein the computer program instructions, when executed by a processor, implement a BIM-based air conditioning equipment installation method as described in any one of the first aspects.

[0052] In this embodiment of the invention, the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building, are analyzed. Based on the analysis results, the installation path of the air conditioning equipment is planned, generating multiple installation paths. The optimal solution path is selected from these multiple installation paths. Based on the optimal solution path, the on-site construction guidance is visualized, and the on-site environmental features in the visualization results are identified. Virtual guidance content is generated based on the identification results, and voice prompts are provided for the virtual guidance content to obtain interactive help information. Based on the interactive help information, key parameters during the installation process of the air conditioning equipment are monitored, and the monitoring results are uploaded to a cloud-based building information modeling environment platform to generate a monitoring data stream. Based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, a thermodynamic prediction model is constructed. Using the thermodynamic prediction model, a drone equipped with a high-resolution camera and a lidar system is controlled to inspect the installation quality of the air conditioning equipment, generating a 3D model and a quality inspection report. The technical solution provided by this invention improves the accuracy and efficiency of installation path planning, enhances the intuitiveness and interactivity of on-site construction guidance, realizes comprehensive monitoring of the installation process, supports subsequent data analysis and feedback mechanisms, optimizes the thermodynamic performance of the air conditioning equipment, and improves the accuracy and comprehensiveness of installation quality inspection.

[0053] Furthermore, a highly realistic virtual simulation scenario is constructed in the Building Information Modeling (BIM) environment to simulate the installation process of air conditioning equipment. By calculating space constraints, installation difficulty, and airflow distribution effects, this simulation scenario can not only accurately reflect the actual installation environment, but also serve as a basis for subsequent optimization, providing a more realistic and detailed reference. Based on this, a method combining genetic algorithms and particle swarm optimization, along with differential evolution algorithms, is adopted to conduct in-depth analysis of space constraints, installation difficulty, and airflow distribution effects, generating multiple optimized installation paths. This method can not only explore a large solution space, but also quickly converge to the potential optimal solution, significantly improving the path optimization effect.

[0054] To further ensure the optimal balance among multiple objectives, an adaptive weight adjustment mechanism is introduced to dynamically balance the priorities among the optimized installation paths. A Bayesian optimization algorithm is then applied to finely tune the weight adjustment parameters, ensuring that each path is fairly evaluated across multiple dimensions and avoiding over-optimization of a single objective. Subsequently, the path selection strategy in the multi-objective reinforcement learning framework is initialized. Based on historical project data, a strategy containing installation path selection patterns and experiences from successful cases is pre-constructed. The multi-objective reinforcement learning framework evaluates and selects the set of optimized installation paths after weight adjustment. The path selection strategy is continuously updated based on historical project data and real-time feedback, making the final selected path more closely aligned with actual construction conditions and exhibiting higher feasibility and adaptability.

[0055] Ultimately, the generated set of optimized installation paths not only meets physical and technical feasibility requirements but is also optimized for specific installation environments. These paths undergo multi-level evaluation and selection to ensure optimal performance in practical applications, providing a solid foundation for subsequent installation guidance. The entire process significantly improves the accuracy, efficiency, and adaptability of air conditioning equipment installation path planning by comprehensively utilizing a variety of advanced technologies and algorithms.

[0056] These or other aspects of the invention will become more apparent from the following description of the embodiments. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart illustrating a BIM-based air conditioning equipment installation method provided in an embodiment of the present invention;

[0059] Figure 2 A schematic diagram of a BIM-based air conditioning equipment installation system provided in an embodiment of the present invention;

[0060] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present invention. Detailed Implementation

[0061] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0062] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0063] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Figure 1 A flowchart of a BIM-based air conditioning equipment installation method is provided as an embodiment of the present invention, such as... Figure 1 As shown, the method includes:

[0065] Step 101: Analyze the physical dimensions and performance parameters of the air conditioning equipment and the spatial structure data of the building. Based on the analysis results, plan the installation path of the air conditioning equipment, generate multiple installation paths, and select the optimal solution path from the multiple installation paths.

[0066] In this step, a Building Information Modeling (BIM) environment is used to plan the installation path of the air conditioning equipment. BIM is a digital tool that can create and manage all information related to a building. Through BIM, the spatial structure of the building can be accurately simulated to ensure that the installation path meets the actual conditions. Genetic Algorithm (GA) is an optimization search technique used to analyze the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building, to generate multiple possible installation paths. Each path is evaluated, taking into account factors such as space constraints, installation difficulty, and airflow distribution effects. Finally, the optimal solution path, that is, the path that best meets the technical and physical requirements, is selected.

[0067] For example, in a new office building project, BIM software was used to import CAD drawings of air conditioning equipment and a 3D model of the building. Through a genetic algorithm, five possible installation paths were automatically calculated and proposed. Taking into account factors such as floor height, load-bearing wall location and existing ventilation duct layout, one of the paths was selected as the optimal solution after evaluation. This path not only avoids the main load-bearing structure, but also ensures the best airflow distribution, while reducing construction difficulty.

[0068] Step 102: Based on the optimal solution path, visualize the on-site construction guidance, identify the on-site environmental features in the visualization results, generate virtual guidance content based on the identification results, and provide voice prompts for the virtual guidance content to obtain interactive help information;

[0069] In this step, based on the selected optimal solution path, augmented reality (AR) technology is used to provide intuitive visual guidance for on-site construction. AR devices (such as smart glasses or tablets) overlay virtual guidance content onto the actual construction site to help workers understand and execute installation steps more accurately. Convolutional neural networks (CNNs) are used to identify on-site environmental features, such as building structure, existing facility layout, and obstacle locations, to ensure that the virtual guidance content accurately matches the actual situation. In addition, natural language processing (NLP) can generate voice prompts to respond to workers' verbal inquiries or feedback, providing dynamically adjusted guidance suggestions and forming interactive help information.

[0070] At the construction site of the aforementioned office building project, technicians wore smart glasses equipped with AR functionality. When they reached a designated location, the smart glasses displayed the specific installation location and connection method of the air conditioning equipment and provided voice prompts for the next steps. If workers encountered any questions, they could ask the system via voice, and the system would adjust the guidance content in real time to ensure that workers always received the most accurate assistance. For example, if a worker was unsure of the location of a certain pipe, he only needed to say "find the condensate drain pipe," and the system would highlight the nearest condensate drain pipe and provide detailed connection instructions.

[0071] Step 103: Based on the interactive help information, monitor the key parameters during the installation of the air conditioning equipment, upload the monitoring results to the cloud-based building information modeling environment platform, and generate a monitoring data stream;

[0072] In this step, an Internet of Things (IoT) sensor network is used to collect a series of key parameters during the installation process, including temperature, humidity, pressure, vibration, air quality, location information, electrical parameters, mechanical stress, and fluid flow. These sensors are distributed at key locations on the construction site, collect data in real time, and perform preliminary processing on-site through edge computing technology to reduce data transmission volume. Subsequently, the monitoring results are uploaded to the cloud BIM platform to generate a real-time monitoring data stream, which can be remotely viewed and analyzed by the project manager and other relevant personnel to ensure the transparency and controllability of the installation process.

[0073] During the installation of the office building project, multiple IoT sensors were deployed around the entire air conditioning system to monitor key parameters such as temperature, humidity, and pressure. Edge computing nodes were responsible for processing the data from the sensors, filtering out unnecessary information, and uploading important changes to the cloud BIM platform in real time. The project manager could access this platform from the office via a web browser to view the real-time updated data stream, promptly detect any anomalies, and make corresponding adjustments. For example, if the humidity in a certain area exceeds the expected range, the system will immediately issue an alarm to remind staff to check for leaks.

[0074] Step 104: Based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, construct a thermodynamic prediction model;

[0075] In this step, a thermodynamic relationship model between the air conditioning equipment and the surrounding environment is constructed based on the generated real-time monitoring data stream. This involves analyzing the heat generated by the air conditioning equipment during operation and its interaction with the surrounding environment. Through machine learning algorithms, patterns and trends can be learned from a large amount of historical and real-time data to predict future thermodynamic behavior and generate a thermodynamic prediction model. This model can be used to estimate the energy efficiency and operating performance of the air conditioning system, identify potential problems in advance, and optimize maintenance plans.

[0076] For office building air conditioning systems that have already been installed, data from various sensors are continuously collected and analyzed, especially parameters such as temperature, humidity, and fluid flow. The thermodynamic prediction model trained by machine learning algorithms can predict the energy efficiency performance of the air conditioning system under different seasons and weather conditions. For example, during the high temperatures of summer, the model predicts that the air conditioning load will increase significantly and recommends preventive maintenance in advance to ensure the stable operation of the system during peak periods. In addition, the model can also identify which areas have less than ideal airflow distribution and require adjustment of the location or number of air vents.

[0077] Step 105: Using the thermodynamic prediction model, control a drone equipped with a high-resolution camera and lidar system to inspect the installation quality of the air conditioning equipment, and generate a three-dimensional model and a quality inspection report.

[0078] In this step, based on the generated thermodynamic prediction model, a drone equipped with a high-resolution camera and a LiDAR system is used to conduct installation quality inspection. The drone flies along a predetermined path, collects on-site images and 3D point cloud data, generates a high-precision 3D model, and then compares the generated 3D model with the original design drawings to detect possible deviations or problems and generate a detailed quality inspection report. This automated inspection method not only saves time and labor costs, but also covers the inspection area more comprehensively, ensuring that the installation quality meets the design requirements.

[0079] After the office building project was completed, the engineering team deployed a drone equipped with a high-resolution camera and LiDAR system to inspect the entire air conditioning system along a pre-set path. The photos taken by the drone and the generated 3D model were uploaded to a cloud platform for comparison with the initial design drawings. Through automated image recognition algorithms, the system detected a slight misalignment at a duct connection and marked it in the quality inspection report. Technicians quickly corrected the issue based on the report, ensuring that all installation details strictly adhered to design standards, thereby improving the overall project quality.

[0080] Traditional air conditioning equipment installation path planning relies on engineers' experience and manual measurement, which is not only inefficient but also prone to errors, leading to frequent adjustments during installation and increasing construction time and costs. Therefore, this invention provides a specific embodiment where step 101 involves analyzing the physical dimensions and performance parameters of the air conditioning equipment, as well as the building's spatial structure data. Based on the analysis results, the installation path of the air conditioning equipment is planned, generating multiple installation paths. The optimal solution path is then selected from these multiple paths. Specifically, this includes the following steps:

[0081] Step 201: Using the Building Information Modeling (BIM) environment, collect and integrate the physical dimensions and performance parameters of the air conditioning equipment and the spatial structure data of the building, and introduce environmental factors as auxiliary input to obtain a comprehensive dataset;

[0082] In this step, a Building Information Modeling (BIM) environment is used to collect and integrate the physical dimensions and performance parameters of the air conditioning equipment, as well as the building's spatial structure data. BIM is a digital tool that can create and manage all information related to a building, including 3D models, attribute data, and associated information. Through the BIM platform, the building's spatial structure can be accurately simulated, ensuring that subsequent analysis is based on actual conditions. Furthermore, environmental factors (such as temperature and humidity) are introduced as auxiliary inputs to account for the impact of external conditions on the installation process. After being processed and standardized, this data forms a comprehensive dataset, providing comprehensive information support for subsequent path planning.

[0083] For example, in a new office building project, BIM software was first used to import CAD drawings of the air conditioning equipment and a 3D model of the building. Then, detailed specifications and technical parameters of the air conditioning equipment, such as cooling capacity and power consumption, were collected. At the same time, environmental factors at the construction site, such as average temperature and humidity levels, were also recorded. All this information was integrated into a comprehensive dataset for subsequent path optimization analysis.

[0084] Step 202: Based on the comprehensive dataset, construct a virtual simulation scene in the building information modeling environment, analyze various environmental factors using the virtual simulation scene, generate multiple installation paths based on the analysis results, and dynamically balance the priorities among the installation paths through an adaptive weight adjustment mechanism to obtain the optimal set of installation paths;

[0085] In this step, a virtual simulation scenario is built in the BIM environment based on the generated comprehensive dataset to simulate the installation process of air conditioning equipment. This simulation scenario not only reflects the actual spatial structure of the building, but also includes the physical dimensions and performance parameters of the equipment. A combination of genetic algorithm (GA) and particle swarm optimization (PSO) is used to conduct in-depth analysis of various factors (such as space constraints, installation difficulty, and airflow distribution effects) and generate multiple optimized installation paths. In order to ensure that the priority of each path is reasonably allocated, an adaptive weight adjustment mechanism is introduced to dynamically adjust the weights according to different optimization objectives, and finally form an optimized set of installation paths.

[0086] In the BIM environment of the office building project, a detailed virtual simulation scene was created, which included the specific location and connection method of the air conditioning equipment. Ten possible installation paths were proposed using GA and PSO algorithms. Each path was evaluated, taking into account factors such as floor height, load-bearing wall location and existing ventilation duct layout. An adaptive weight adjustment mechanism ensured that the path selection considered both the shortest path and construction difficulty and airflow optimization. Ultimately, a set of multiple feasible paths, including the optimal solution, was formed.

[0087] Step 203: Perform a multi-level evaluation on the optimal installation path set, evaluating the length of each installation path in the optimal installation path set, the degree of impact on the existing structure, the expected airflow optimization results, and the possibility of encountering difficulties during construction, and generate a risk coefficient assessment report;

[0088] In this step, a multi-level evaluation is conducted based on the optimal set of installation paths. The evaluation mainly includes path length, the degree of impact on the existing structure, the expected airflow optimization results, and the likelihood of difficulties encountered during actual construction. Through quantitative and qualitative analysis, the advantages and disadvantages of each path are determined. To quantify potential risks, a risk assessment algorithm is introduced to calculate a corresponding risk coefficient for each path. The final risk coefficient assessment report provides a scientific basis for decision-making, helping to select the most suitable installation path.

[0089] For example, for ten candidate paths in an office building project, a multi-level evaluation was conducted. The evaluation results showed that some paths, although shorter, would have a significant impact on the existing structure; while other paths were more conducive to airflow optimization, but were more difficult to construct. Through risk assessment algorithms, the risk coefficient of each path was calculated, and one path was found to be balanced in all aspects and had the lowest risk coefficient. This path was selected as the preliminary recommended solution, and the relevant evaluation results were recorded in detail in the risk coefficient evaluation report for further decision-making reference.

[0090] Step 204: Based on the set of optimal installation paths and the risk coefficient assessment report, perform decision analysis on each installation path, and select the optimal solution path based on the analysis results;

[0091] In this step, based on the generated optimized installation path set and the risk coefficient assessment report generated in step 203, a comprehensive decision analysis is conducted on each installation path by combining the Analytic Hierarchy Process (AHP) and the Fuzzy Comprehensive Evaluation Method (FCE). The AHP is used to establish an evaluation index system and clarify the importance weight of each factor; the Fuzzy Comprehensive Evaluation Method takes into account the uncertainty and subjectivity in the evaluation process and provides a more flexible evaluation method. By combining these two methods, each path can be comprehensively and systematically evaluated, and the optimal solution path, that is, the path that best meets the technical and economic requirements, can be selected.

[0092] In the office building project, the Analytic Hierarchy Process (AHP) was used to establish an evaluation index system that included path length, structural impact, airflow optimization, and construction difficulty. The importance weight of each index was determined. Then, the fuzzy comprehensive evaluation method was applied to comprehensively consider the opinions of different experts and the actual site conditions. Each candidate path was scored. After rigorous evaluation and comparison, a path was finally selected as the optimal solution. This path not only avoided the main load-bearing structure and ensured the best airflow distribution, but also reduced the construction difficulty, making the entire installation process more efficient and safer.

[0093] Furthermore, the present invention also provides a specific embodiment. Step 202 involves constructing a virtual simulation scene in a building information modeling environment based on the comprehensive dataset, analyzing various environmental factors using the virtual simulation scene, generating multiple installation paths based on the analysis results, and dynamically balancing the priorities among the installation paths through an adaptive weight adjustment mechanism to obtain an optimal set of installation paths. Specifically, this includes the following steps:

[0094] Step 301: Based on the comprehensive dataset, construct a virtual simulation scene in the building information modeling environment, use the virtual simulation scene to simulate the installation process of air conditioning equipment, calculate the space limitations, installation difficulty and airflow distribution effect of the air conditioning equipment during the installation process based on the simulation results, and generate calculation results;

[0095] In this step, a virtual simulation scenario is built in the Building Information Modeling (BIM) environment based on the generated comprehensive dataset. The BIM environment can not only accurately simulate the spatial structure of the building and the physical dimensions and performance parameters of the air conditioning equipment, but also reflect the actual installation conditions by combining environmental factors (such as temperature and humidity). Through this virtual simulation scenario, the installation process of the air conditioning equipment can be simulated in detail, and the spatial constraints, installation difficulty and expected airflow distribution effect of each potential path can be calculated. The final calculation provides an intuitive and detailed basis for subsequent path optimization.

[0096] In a new office building project, a comprehensive dataset was imported using BIM software to create a detailed virtual simulation scenario. This scenario simulated the entire process of air conditioning equipment from transportation to final installation, including how the equipment enters the building, the specific paths it takes through the floors, and the steps to connect to the ventilation system. The simulation automatically calculated the spatial constraints, installation difficulty, and airflow distribution effect of each possible path, ensuring that all simulation results were based on actual construction conditions. For example, one path, although shorter, required passing through a narrow corridor, increasing the installation difficulty; while another path was more conducive to maintaining good airflow distribution.

[0097] Step 302: Based on the calculation results, conduct an in-depth analysis of space limitations, installation difficulty, and airflow distribution effects, and generate multiple installation paths based on the analysis results;

[0098] In this step, based on the virtual simulation scene constructed in the previous step, a combination of genetic algorithm (GA), particle swarm optimization (PSO) and differential evolution algorithm (DE) is used to conduct in-depth analysis of space constraints, installation difficulty and airflow distribution effects. These algorithms work together to explore a large solution space, quickly converge to multiple potential optimal solutions, and generate multiple installation paths.

[0099] In the virtual simulation scenario of the office building project, GA, PSO, and DE algorithms were applied to propose fifteen possible installation paths. These paths were evaluated in detail, taking into account factors such as floor height, load-bearing wall location, and existing ventilation duct layout. Some paths, although shorter, required the demolition of part of the structure, increasing the construction difficulty; while other paths were more conducive to maintaining good airflow distribution and reducing the need for later adjustments. Through this multi-algorithm combination optimization method, an initial optimized installation path set containing fifteen candidate paths was formed.

[0100] Step 303: Based on the multiple installation paths, an adaptive weight adjustment mechanism is introduced to dynamically balance the priorities among the installation paths, and the weight adjustment parameters of each installation path are adjusted to generate a set of installation paths after weight adjustment.

[0101] In this step, based on the generated initial set of optimized installation paths, an adaptive weight adjustment mechanism is introduced to dynamically balance the priorities among the optimized paths. This mechanism automatically adjusts the weights of different optimization objectives according to the changes in the importance of factors discovered during the simulation process, ensuring that each path can be fairly evaluated in multiple dimensions. At the same time, a Bayesian optimization algorithm is applied to finely tune the weight adjustment parameters, further improving the robustness and efficiency of the optimization process, and finally forming a set of optimized installation paths after weight adjustment.

[0102] For the fifteen candidate paths in the office building project, an adaptive weight adjustment mechanism was introduced. The weights were dynamically adjusted based on the changes in the importance of space constraints, installation difficulty, and airflow distribution effects discovered during the simulation. For example, when it was found that some paths were short but extremely difficult to install, the weight of "path length" was reduced and the weight of "installation difficulty" was increased. At the same time, a Bayesian optimization algorithm was applied to finely tune the weight adjustment parameters to ensure that each path was fairly evaluated across multiple dimensions. Ultimately, a set of installation paths with adjusted weights was formed, in which each path achieved an optimal balance between different optimization objectives.

[0103] Step 304: Use a multi-objective reinforcement learning framework to evaluate and select the optimized installation path set after weight adjustment, update the preset path selection strategy based on historical project data and real-time feedback, and generate the optimal installation path set based on the updated path selection strategy.

[0104] In this step, based on the generated set of optimized installation paths with adjusted weights, the path selection strategy in the Multi-Objective Reinforcement Learning (MORL) framework is initialized. The MORL framework can continuously learn and update the path selection strategy based on historical project data and real-time feedback, making the final selected path more in line with the actual construction conditions. The path selection strategy is pre-built based on historical project data and includes installation path selection patterns and experiences from historical successful cases. This ensures that the selection of new paths not only considers the specific situation of the current project, but also draws on past successful experiences and lessons. Through the evaluation and selection of the MORL framework, the optimal set of installation paths is finally generated, providing the most optimized guidance for actual installation.

[0105] In the office building project, a path selection strategy in the MORL framework was initialized based on a weighted set of optimized installation paths. This strategy referenced data from several successful past projects, especially those similar to the current project. The MORL framework was used to comprehensively evaluate fifteen candidate paths, considering factors such as space constraints, installation difficulty, and airflow distribution. As the simulation progressed, the path selection strategy was continuously adjusted based on real-time feedback, ultimately selecting an optimal path. This path not only avoided the main load-bearing structure and ensured optimal airflow distribution but also reduced construction difficulty, making the entire installation process more efficient and safer. In addition, the MORL framework recorded the experience gained from this selection, providing valuable reference material for similar projects in the future.

[0106] Because on-site construction guidance is not precise and real-time enough, workers lack dynamic and interactive help information during on-site operations, which increases the risk of operational errors. To solve the above problems, the present invention provides a specific embodiment. Step 102 involves visualizing the on-site construction guidance based on the optimal solution path, identifying on-site environmental features in the visualization results, generating virtual guidance content based on the identification results, and providing voice prompts for the virtual guidance content to obtain interactive help information. Specifically, this includes the following steps:

[0107] Step 401: Install the air conditioning equipment according to the optimal solution path, and visualize the installation process of the air conditioning equipment to generate a visualization view;

[0108] In this step, based on the selected optimal solution path, the installation process of the air conditioning equipment is visualized in an augmented reality (AR) environment. AR is a technology that can overlay computer-generated information onto the user's real-world field of vision, allowing the user to see virtual elements in the actual scene. Through AR devices (such as smart glasses, tablets, etc.), virtual guidance content (such as equipment location, connection method, etc.) is overlaid onto the actual construction site, providing intuitive visual guidance for the installation workers and generating initial virtual guidance content to help workers understand and perform the installation steps more accurately.

[0109] In an office building project, detailed installation guidance was created in an AR environment based on the optimal path selected by the MORL framework. When workers wearing smart glasses arrived at the designated location, they could see the specific installation location and connection method of the air conditioning equipment clearly marked. These virtual markers were seamlessly integrated with the actual environment, ensuring that workers could quickly find the correct installation point, reducing the time wasted in searching for the location, and improving installation accuracy.

[0110] Step 402: Install the air conditioning equipment according to the optimal solution path, visualize the installation process of the air conditioning equipment, generate a visualization view, and use a convolutional neural network to identify the on-site environmental features in the visualization view, and generate virtual guidance content based on the identification results;

[0111] In this step, based on the generated initial virtual guidance content, a convolutional neural network (CNN) is used to identify on-site environmental features, such as building structure, existing facility layout, and obstacle location. CNN is a deep learning model that excels at processing image data and can accurately identify and classify various features in the on-site environment. In this way, more accurate virtual guidance content is generated, ensuring that the virtual guidance is completely matched with the actual construction site and improving the accuracy of the guidance.

[0112] During the installation of the office building project, AR devices were used to collect real-time images of the construction site. CNN was then used to analyze these images to identify the location of the building structure, ventilation ducts, electrical wires, and other obstacles. Based on this information, the virtual guidance was adjusted. For example, some connection points were repositioned to avoid obstacles, or the installation path was modified to adapt to the actual structure. In this way, even if the site conditions deviated from the original plan, the most accurate guidance could be obtained, avoiding incorrect installation.

[0113] Step 403: Based on the virtual guidance content, apply a spatial positioning algorithm combined with real-time sensor data to locate and correct the installation position of the air conditioning equipment, and generate an installation position correction command;

[0114] In this step, based on the generated virtual guidance content, a spatial positioning algorithm is applied in combination with real-time sensor data to accurately locate and correct the installation position. The Internet of Things (IoT) sensor network acquires real-time spatial coordinates and attitude information to ensure the positional accuracy of each installation point. The spatial positioning algorithm dynamically adjusts the installation path in the virtual guidance content according to this real-time data and generates installation position correction instructions to adapt to possible minor deviations or changes, ensuring the accuracy of the installation process.

[0115] In the office building project, multiple IoT sensors are distributed at key locations on the construction site to monitor parameters such as temperature, humidity, and pressure in real time. These data are processed through edge computing nodes, and spatial positioning algorithms use this real-time data, combined with virtual guidance, to make multiple fine adjustments to the installation location. For example, when it is found that the actual location of a certain pipe deviates slightly from the preset path, a new correction instruction is immediately generated to guide the adjustment of the installation direction and ensure that the final location fully meets the design requirements.

[0116] Step 404: Based on the virtual guidance content and installation position correction instructions, create a dynamic interactive model, use the dynamic interactive guidance model to generate voice prompts, and add the voice prompts to the virtual guidance content to generate interactive help information;

[0117] In this step, based on the generated virtual guidance content and installation position correction instructions, a dynamic interactive model is created using augmented reality (AR) and mixed reality (MR) technologies. This model not only demonstrates the correct installation steps but also automatically adjusts the displayed content according to the operation progress, providing continuous visual and tactile feedback. This ensures that the optimal operating procedure is always followed, reducing the risk of errors. Based on the generated dynamic interactive guidance model, natural language processing (NLP) technology is applied to generate voice prompts and provide interactive help information. NLP technology enables the system to understand workers' verbal inquiries or feedback and respond in real time, providing dynamically adjusted guidance suggestions. In this way, immediate help and support can be obtained, ensuring that the most accurate operating guidance is always available, thereby improving work efficiency and quality.

[0118] During the installation process of the office building project, a dynamic interactive model was created and displayed using AR / MR devices. When the installation of a component begins, the model automatically switches to the corresponding step and guides the installation by highlighting key operation areas. If the installation deviates from the predetermined path, the model will immediately provide prompts and corrective suggestions. In addition, haptic feedback is provided, such as vibration reminders to pay attention to certain details, ensuring that each step is completed accurately. The system can also be interacted with via voice. For example, if the connection method of a certain pipe is uncertain, saying "find the condensate pipe" will immediately highlight the nearest condensate pipe and provide detailed connection instructions. Furthermore, if any problems or questions arise, a simple question will provide the best solution based on the current operation progress and historical data. This interactive help information not only improves communication efficiency but also enhances installation confidence, ensuring a smooth installation process.

[0119] Furthermore, the present invention also provides a specific embodiment in which step 403, based on the virtual guidance content, applies a spatial positioning algorithm combined with real-time sensor data to locate and correct the installation position of the air conditioning equipment, and generates an installation position correction command, specifically including the following steps:

[0120] Step 501: Apply a spatial positioning algorithm combined with real-time sensor data to locate the installation position of the air conditioning equipment and obtain spatial coordinates and attitude information;

[0121] In this step, based on the generated virtual guidance content, spatial positioning algorithms (such as SLAM, GPS, etc.) are applied in conjunction with real-time sensor data (such as temperature, humidity, pressure, vibration, air quality, location information, electrical parameters, mechanical stress, and fluid flow) to accurately locate the installation position of the air conditioning equipment. Real-time spatial coordinates and attitude information are acquired through an Internet of Things (IoT) sensor network to ensure the positional accuracy of each installation point, generating precise spatial coordinates and attitude information, providing accurate foundational data for subsequent steps.

[0122] In the office building project, AR devices and multiple IoT sensors distributed on the construction site are used to monitor the environmental parameters around the air conditioning equipment in real time. Through spatial positioning algorithms, the specific installation location of the air conditioning equipment can be accurately located, and its three-dimensional spatial coordinates and attitude information can be obtained. For example, when the air conditioning equipment is moved to a designated location, its coordinates and attitude will be updated immediately to ensure that the installation location is completely consistent with the design drawings, reducing the risk of rework due to position deviation.

[0123] Step 502: Based on the spatial coordinates and attitude information, use machine learning algorithms to analyze historical installation data and current environmental conditions, predict installation locations outside the preset target, and generate potential problem warning information based on the prediction results;

[0124] In this step, based on the spatial coordinates and attitude information generated in step 1, machine learning algorithms (such as supervised learning or unsupervised learning) are used to analyze historical installation data and current environmental conditions to predict potential installation challenges. These challenges include, but are not limited to, issues related to space constraints, structural strength, and airflow optimization. By analyzing patterns and trends in historical data, potential risks can be identified in advance, and early warning information for potential problems can be generated to help avoid these problems in advance.

[0125] During the installation process of the office building project, installation data from similar past projects were collected and analyzed using machine learning algorithms in conjunction with the current environmental conditions of the construction site. The results showed that the location of load-bearing walls in certain areas may affect the installation path, and high humidity levels during specific time periods may cause corrosion problems at equipment connections. Based on this, potential problem warning information was generated, reminding people to pay special attention in these areas and proposing corresponding preventive measures, such as choosing more robust brackets or taking moisture-proof measures.

[0126] Step 503: Based on the potential problem warning information, apply simulation technology to simulate the installation at different installation locations in a virtual simulation scenario, evaluate the feasibility and advantages and disadvantages of various simulation results, generate installation plan suggestions based on the evaluation results, and output installation location correction instructions based on the installation plan suggestions.

[0127] In this step, based on the potential problem warning information generated in the previous step, simulation technology (such as multiphysics simulation) is applied to simulate different installation schemes in an augmented reality (AR) environment. In this way, the feasibility and advantages and disadvantages of each scheme can be evaluated. Factors considered include space constraints, installation difficulty, airflow distribution effect, etc. Finally, an optimized installation scheme recommendation is generated to provide a scientific basis for actual construction and ensure that the selected scheme meets both technical and physical requirements and has high feasibility.

[0128] In the office building project, based on potential problem warning information, multiple different installation schemes were simulated in the AR environment. For example, for the possible load-bearing wall problem, two schemes were simulated: one that bypasses the load-bearing wall and the other that passes directly through it but with reinforcement measures. By comparing the space limitations, installation difficulty and airflow distribution effect of the two schemes in detail, a path that bypasses the load-bearing wall was finally recommended. This path not only avoids the main structure, but also ensures the best airflow distribution, while reducing the construction difficulty.

[0129] Step 504: Based on the optimized installation scheme suggestion and spatial coordinates and attitude information, dynamically correct the installation position, adjust the installation path in the virtual guidance content according to the actual site conditions, and generate an installation position correction instruction;

[0130] In this step, the installation position is dynamically corrected based on the generated optimized installation plan suggestions and the obtained spatial coordinates and attitude information. The installation path in the virtual guidance is adjusted according to the actual site conditions (such as actual size deviations, temporary obstacles, etc.) to ensure that the installation process always follows the optimal path. Finally, an installation position correction instruction is generated to guide workers to make necessary adjustments and ensure the accuracy of the installation position.

[0131] During the actual installation process of the office building project, the installation position was continuously fine-tuned based on the optimized installation plan and real-time spatial coordinates and posture information. For example, when it was found that the actual position of a certain pipe deviated slightly from the preset path, a new correction instruction was immediately generated to guide the adjustment of the installation direction and ensure that the final position fully met the design requirements. In addition, if temporary obstacles appeared on site, the path was automatically replanned to avoid obstacles while maintaining the optimal installation path, ensuring that the entire installation process proceeded smoothly.

[0132] While some projects have begun using sensor networks to monitor key parameters during installation, this data is typically only available locally, lacking real-time data analysis and feedback mechanisms. This makes it impossible to adjust installation strategies promptly to address changes on-site. Therefore, this invention provides a specific embodiment where step 103, based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, constructs a thermodynamic prediction model, specifically including the following steps:

[0133] Step 601: Based on the monitoring data stream uploaded to the cloud-based Building Information Modeling Environment Platform, construct an initial thermodynamic relationship model;

[0134] In this step, based on real-time monitoring data streams uploaded to the cloud-based Building Information Modeling (BIM) platform, including key parameters such as temperature, humidity, pressure, vibration, air quality, location information, electrical parameters, mechanical stress, and fluid flow rate, the thermodynamic relationship between the air conditioning equipment and its surrounding environment is modeled. By analyzing these key parameters, an initial thermodynamic relationship model is constructed to describe the heat generated by the air conditioning equipment during operation and its interaction with the surrounding environment, providing a foundational model for subsequent simulations and predictions.

[0135] In the office building project, real-time data collected by multiple IoT sensors was uploaded to a cloud-based BIM platform. This data included key parameters such as temperature, humidity, and airflow velocity around the air conditioning equipment. Based on this data, an initial thermodynamic relationship model was constructed, which detailed the thermodynamic behavior of the air conditioning equipment under different operating conditions and its interaction with the surrounding environment. For example, the model showed how the equipment affected indoor air quality and energy consumption under high temperature and high humidity conditions.

[0136] Step 602: Simulate the operating status of the air conditioning equipment under different working conditions and the interaction between the air conditioning equipment and the surrounding environment to generate simulation results under various working conditions;

[0137] In this step, multiphysics simulation technology (such as CFD, FEA, etc.) is applied to simulate the operating state of air conditioning equipment under different working conditions and its interaction with the surrounding environment. Multiphysics simulation technology can consider multiple physical phenomena (such as fluid mechanics, heat conduction, etc.) at the same time, generate simulation results under various working conditions, and provide rich data support for subsequent machine learning training.

[0138] In the BIM environment of the office building project, multiphysics simulation software was used to simulate the operating status of the air conditioning equipment under different conditions such as high temperature in summer, low temperature in winter, and transitional seasons. The simulation results showed that under high temperature conditions in summer, the cooling effect of the air conditioning equipment decreased significantly, requiring the addition of additional cooling devices; while under low temperature conditions in winter, the heating function of the equipment performed well, but the energy consumption was high. These simulation results provided important reference for subsequent optimization.

[0139] Step 603: Based on the simulation results, apply a machine learning algorithm to train the initial thermodynamic relationship model to obtain the trained thermodynamic relationship model;

[0140] In this step, based on the generated simulation results, machine learning algorithms (such as supervised learning or unsupervised learning) are applied to train the initial thermodynamic relationship model. By analyzing the patterns and trends in historical and real-time data, key factors affecting the performance of air conditioning equipment can be identified, and a trained thermodynamic relationship model can be established to predict the operating status of air conditioning equipment under different conditions and its interaction with the surrounding environment.

[0141] Machine learning algorithms were used to train simulation results and actual operating data in the office building project. Through the analysis of a large amount of historical and real-time data, several key factors were identified, such as outdoor temperature, indoor occupancy density, and ventilation system efficiency. Based on these factors, a trained thermodynamic relationship model was generated, which can accurately predict the operating status and energy efficiency of air conditioning equipment under various conditions. For example, the model predicted that on a certain date, due to the rise in external temperature, the air conditioning load would increase by about 20%, and suggested adjusting the cooling capacity in advance to meet peak demand.

[0142] Furthermore, traditional quality inspections rely heavily on manual checks, which are not only time-consuming and labor-intensive but also difficult to guarantee the comprehensiveness and accuracy of the inspections. Especially in large and complex construction projects, manual inspections are prone to overlooking details, affecting the final installation quality. Therefore, this invention provides a specific embodiment. Step 105 utilizes the thermodynamic prediction model to control a drone equipped with a high-resolution camera and a lidar system to inspect the installation quality of the air conditioning equipment, generating a 3D model and a quality inspection report. This specifically includes the following steps:

[0143] Step 701: Using the thermodynamic prediction model, perform inspection task planning for the installation quality of the air conditioning equipment, determine the key areas and key indicators of the inspection task, and generate the inspection task plan.

[0144] In this step, based on the generated thermodynamic prediction model, the installation quality of the air conditioning equipment is planned and processed for inspection. By analyzing the data in the thermodynamic prediction model, key areas and indicators that may affect the performance of the equipment (such as airflow distribution, temperature control, etc.) can be identified, thereby determining the key areas and key indicators for inspection and finally generating a detailed inspection task plan to provide guidance for subsequent drone inspections.

[0145] In an office building project, a thermodynamic prediction model was used to analyze the operating status of the air conditioning equipment. It was found that there might be problems with uneven airflow or poor temperature control in certain areas. Based on these analysis results, an inspection task plan was generated, which clarified the areas that needed to be inspected (such as the location of air outlets and pipe connection points) and key indicators (such as temperature, humidity, and airflow speed). The inspection task plan ensured the effectiveness and targeting of drone inspections and avoided missing important inspection points.

[0146] Step 702: According to the flight path in the inspection task plan, control the UAV equipped with a high-resolution camera and lidar system to inspect the installation quality of the air conditioning equipment and obtain the original inspection data, which includes on-site images and three-dimensional point cloud data.

[0147] In this step, based on the generated inspection task plan, a drone equipped with a high-resolution camera and a LiDAR system is used to inspect the installation quality of the air conditioning equipment. The drone flies along a preset path, accurately collecting images and 3D point cloud data of the site to form raw inspection data. The high-resolution camera is used to capture high-definition images, while the LiDAR system is used to generate accurate 3D point cloud data, ensuring the integrity and accuracy of the data.

[0148] During the inspection of the office building project, the drone flew along a predetermined path, covering all key areas. It used high-resolution cameras to capture detailed images of each air vent, duct connection point, and other important structures, and generated three-dimensional point cloud data of the entire air conditioning system using a LiDAR system. This raw inspection data not only included visual information but also precise spatial coordinates, providing a solid foundation for subsequent data processing.

[0149] Step 703: Apply image recognition algorithms and 3D reconstruction technology to identify and model the original inspection data to generate a 3D model;

[0150] In this step, based on the original inspection data, image recognition algorithms and 3D reconstruction technology are applied to process the collected data. The image recognition algorithm is used to automatically identify and classify key features in the image (such as equipment components, connection points, etc.), while the 3D reconstruction technology converts the 3D point cloud data into a high-precision 3D model. This 3D model shows in detail the actual situation of the air conditioning equipment and its surrounding environment, providing an intuitive visualization tool for subsequent quality assessment.

[0151] In the data processing for the office building project's inspection, image recognition algorithms were first used to automatically mark all important equipment components and connection points. Then, 3D reconstruction technology was used to transform the point cloud data collected by LiDAR into a high-precision 3D model. This model not only shows the specific location and shape of the air conditioning equipment but also includes detailed internal structures and connection methods. For example, it clearly shows the location and size of each air vent, as well as the connection relationships between pipes, making any potential problems immediately apparent.

[0152] Step 704: Based on the three-dimensional model and the preset quality standards, conduct a comprehensive evaluation of the installation quality of the air conditioning equipment and generate an initial quality inspection report;

[0153] In this step, based on the 3D model generated in step 703 and combined with preset quality standards, a comprehensive evaluation of the installation quality of the air conditioning equipment is conducted. These quality standards include, but are not limited to, equipment position accuracy, connection firmness, and airflow distribution effect. Every detail in the 3D model is checked against these standards to detect any potential deviations or problems, ultimately generating an initial quality inspection report. This report records all inspection results in detail, providing a basis for subsequent improvements.

[0154] In the office building project, the 3D model was comprehensively evaluated according to the preset quality standards. For example, it was checked whether the location of each air vent met the design requirements, whether the pipe connections were secure, and whether the airflow distribution was uniform. The evaluation results showed that the locations of a few air vents were slightly off, and some pipe connection points were slightly loose. These problems were recorded in detail in the initial quality inspection report, with the specific location and degree of deviation marked, providing clear guidance for subsequent rectification.

[0155] Step 705: Optimize the initial quality inspection report using natural language processing technology to generate an optimal quality inspection report, wherein the quality inspection report includes marked problem areas and improvement suggestions;

[0156] In this step, based on the generated initial quality inspection report, it is optimized using Natural Language Processing (NLP) technology. NLP technology helps the system understand the textual descriptions in the report, automatically identify and mark potential problem areas; finally, the best quality inspection report is generated, which not only includes all the problems found, but also provides specific improvement suggestions to ensure the accuracy and usability of the report content.

[0157] During the final review phase of the office building project, NLP technology was used to analyze the textual descriptions in the initial quality inspection report, automatically identifying all marked problem areas. Based on historical project data and professional knowledge, detailed improvement suggestions were provided for each problem. For example, for the issue of air vent position deviation, it was recommended to adjust the mounting brackets to ensure precise alignment; for the issue of loose pipes, it was recommended to retighten the connections and add fixing points. The final optimal quality inspection report not only clearly marked all problem areas but also included detailed improvement suggestions, providing strong support for the successful acceptance of the project.

[0158] Figure 2 This invention provides a schematic diagram of a BIM-based air conditioning equipment installation system, as shown in the embodiment of the invention. Figure 2 As shown, the system includes:

[0159] Analysis module 21 is used to analyze the physical dimensions and performance parameters of the air conditioning equipment and the spatial structure data of the building. Based on the analysis results, it plans the installation path of the air conditioning equipment, generates multiple installation paths, and selects the optimal solution path from the multiple installation paths.

[0160] The identification module 22 is used to visualize the on-site construction guidance based on the optimal solution path, identify the on-site environmental features in the visualization results, generate virtual guidance content based on the identification results, and provide voice prompts for the virtual guidance content to obtain interactive help information;

[0161] Monitoring module 23 is used to monitor key parameters during the installation process of the air conditioning equipment based on the interactive help information, upload the monitoring results to the cloud building information modeling environment platform, and generate a monitoring data stream;

[0162] Module 24 is used to construct a thermodynamic prediction model based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment.

[0163] The control module 25 is used to control a drone equipped with a high-resolution camera and a lidar system to inspect the installation quality of the air conditioning equipment using the thermodynamic prediction model, and generate a three-dimensional model and a quality inspection report.

[0164] Figure 2 The aforementioned BIM-based air conditioning equipment installation system can perform... Figure 1 The implementation principle and technical effects of the BIM-based air conditioning equipment installation method described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit of the BIM-based air conditioning equipment installation system in the above embodiments perform operations have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0165] In one possible design, Figure 2 The BIM-based air conditioning equipment installation system of the illustrated embodiment can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0166] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0167] The processing component 32 is used to analyze the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building. Based on the analysis results, it plans the installation path of the air conditioning equipment, generates multiple installation paths, and selects the optimal solution path from among the multiple installation paths. Based on the optimal solution path, it performs visualization processing on the on-site construction guidance, identifies the on-site environmental features in the visualization results, generates virtual guidance content based on the identification results, and provides voice prompts for the virtual guidance content to obtain interactive help information. Based on the interactive help information, it monitors the key parameters in the installation process of the air conditioning equipment, uploads the monitoring results to the cloud building information modeling environment platform, and generates a monitoring data stream. Based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, it constructs a thermodynamic prediction model. Using the thermodynamic prediction model, it controls a drone equipped with a high-resolution camera and a lidar system to inspect the installation quality of the air conditioning equipment, and generates a three-dimensional model and a quality inspection report.

[0168] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0169] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0170] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0171] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0172] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0173] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0174] This invention also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The illustrated embodiment is a BIM-based air conditioning equipment installation method.

[0175] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0176] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0177] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A BIM-based air conditioning equipment installation method, characterized in that, include: Analyze the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building. Based on the analysis results, plan the installation path of the air conditioning equipment, generate multiple installation paths, and select the optimal solution path from among the multiple installation paths. Based on the optimal solution path, the on-site construction guidance is visualized, the on-site environmental features in the visualization results are identified, virtual guidance content is generated according to the identification results, and voice prompts are provided for the virtual guidance content to obtain interactive help information; Based on the interactive help information, key parameters during the installation of the air conditioning equipment are monitored, and the monitoring results are uploaded to the cloud-based building information modeling environment platform to generate a monitoring data stream. Based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, a thermodynamic prediction model is constructed. Using the aforementioned thermodynamic prediction model, a drone equipped with a high-resolution camera and lidar system is controlled to inspect the installation quality of the air conditioning equipment, generating a 3D model and a quality inspection report. This process includes: using the thermodynamic prediction model to plan the inspection task for the air conditioning equipment, identifying key areas and indicators for the inspection, and generating an inspection task plan; controlling the drone equipped with the high-resolution camera and lidar system to inspect the installation quality of the air conditioning equipment according to the flight path in the inspection task plan, obtaining raw inspection data, including on-site images and 3D point cloud data; applying image recognition algorithms and 3D reconstruction technology to identify and model the raw inspection data, generating a 3D model; comprehensively evaluating the installation quality of the air conditioning equipment based on the 3D model and preset quality standards, generating an initial quality inspection report; and optimizing the initial quality inspection report using natural language processing technology to generate an optimal quality inspection report, which includes marked problem areas and improvement suggestions.

2. The method according to claim 1, characterized in that, The physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building, are analyzed. Based on the analysis results, the installation path of the air conditioning equipment is planned, generating multiple installation paths. The optimal solution path is then selected from these multiple paths, including: Using a building information modeling environment, we collect and integrate data on the physical dimensions and performance parameters of air conditioning equipment and the spatial structure of buildings, and introduce environmental factors as auxiliary inputs to obtain a comprehensive dataset. Based on the comprehensive dataset, a virtual simulation scene is constructed in the building information modeling environment. The virtual simulation scene is used to analyze various environmental factors. Based on the analysis results, multiple installation paths are generated. The priority between each installation path is dynamically balanced through an adaptive weight adjustment mechanism to obtain the optimal set of installation paths. A multi-level evaluation is performed on the optimal installation path set to assess the length of each installation path, its impact on the existing structure, the expected airflow optimization results, and the possibility of encountering difficulties during construction, thereby generating a risk coefficient assessment report. Based on the set of optimal installation paths and the risk coefficient assessment report, a decision analysis is performed on each installation path, and the optimal solution path is selected based on the analysis results.

3. The method according to claim 2, characterized in that, Based on the comprehensive dataset, a virtual simulation scenario is constructed in a Building Information Modeling (BIM) environment. This virtual simulation scenario is used to analyze various environmental factors. Based on the analysis results, multiple installation paths are generated, and an adaptive weight adjustment mechanism dynamically balances the priorities among these paths to obtain an optimal set of installation paths, including: Based on the comprehensive dataset, a virtual simulation scene is constructed in the building information modeling environment. The installation process of air conditioning equipment is simulated using the virtual simulation scene. Based on the simulation results, the space limitations, installation difficulty, and airflow distribution effect of the air conditioning equipment during the installation process are calculated, and calculation results are generated. Based on the calculation results, an in-depth analysis of space limitations, installation difficulty, and airflow distribution effects is conducted, and multiple installation paths are generated based on the analysis results. Based on the multiple installation paths, an adaptive weight adjustment mechanism is introduced to dynamically balance the priorities among the installation paths, while adjusting the weight adjustment parameters of each installation path to generate a set of installation paths after weight adjustment. The optimized installation path set after weight adjustment is evaluated and selected using a multi-objective reinforcement learning framework. The preset path selection strategy is updated based on historical project data and real-time feedback. The optimal installation path set is generated based on the updated path selection strategy.

4. The method according to claim 1, characterized in that, Based on the optimal solution path, the on-site construction guidance is visualized, the on-site environmental features in the visualization results are identified, virtual guidance content is generated based on the identification results, and voice prompts are provided for the virtual guidance content to obtain interactive help information, including: The air conditioning equipment is installed according to the optimal solution path, and the installation process of the air conditioning equipment is visualized to generate a visual view. A convolutional neural network is used to identify the on-site environmental features in the visual view, and virtual guidance content is generated based on the identification results. Based on the virtual guidance content, a spatial positioning algorithm is applied in combination with real-time sensor data to locate and correct the installation position of the air conditioning equipment, and an installation position correction instruction is generated. Based on the virtual guidance content and installation location correction instructions, a dynamic interactive model is created. The dynamic interactive guidance model is used to generate voice prompts, which are then added to the virtual guidance content to generate interactive help information.

5. The method according to claim 4, characterized in that, Based on the virtual guidance content, a spatial positioning algorithm combined with real-time sensor data is applied to locate and correct the installation position of the air conditioning equipment, generating an installation position correction command, including: By applying spatial positioning algorithms and combining real-time sensor data, the installation location of the air conditioning equipment is determined, and spatial coordinates and attitude information are obtained. Based on the spatial coordinates and attitude information, machine learning algorithms are used to analyze historical installation data and current environmental conditions to predict installation locations outside the preset target, and potential problem warning information is generated based on the prediction results. Based on the potential problem warning information, simulation technology is applied to simulate the installation at different locations in a virtual simulation scenario, evaluate the feasibility and advantages and disadvantages of various simulation results, and generate installation plan suggestions based on the evaluation results; Based on the installation plan, it is recommended to output an installation position correction command.

6. The method according to claim 1, characterized in that, Based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment, a thermodynamic prediction model is constructed, including: An initial thermodynamic relationship model is constructed based on the monitoring data stream uploaded to the cloud-based building information modeling environment platform; The operating status of the air conditioning equipment under different working conditions and the interaction between the air conditioning equipment and the surrounding environment are simulated to generate simulation results under various working conditions. Based on the simulation results, a machine learning algorithm is applied to train the initial thermodynamic relationship model to obtain the trained thermodynamic relationship model.

7. A BIM-based air conditioning equipment installation system, applied to the BIM-based air conditioning equipment installation method according to any one of claims 1-6, characterized in that, include: The analysis module is used to analyze the physical dimensions and performance parameters of the air conditioning equipment, as well as the spatial structure data of the building. Based on the analysis results, the installation path of the air conditioning equipment is planned, multiple installation paths are generated, and the optimal solution path is selected from the multiple installation paths. The identification module is used to visualize the on-site construction guidance based on the optimal solution path, identify the on-site environmental features in the visualization results, generate virtual guidance content based on the identification results, and provide voice prompts for the virtual guidance content to obtain interactive help information; The monitoring module is used to monitor key parameters during the installation process of the air conditioning equipment based on the interactive help information, upload the monitoring results to the cloud building information modeling environment platform, and generate a monitoring data stream. The module is used to construct a thermodynamic prediction model based on the monitoring data stream and the thermodynamic relationship between the air conditioning equipment and the surrounding environment. The control module is used to control a drone equipped with a high-resolution camera and a lidar system to inspect the installation quality of the air conditioning equipment using the thermodynamic prediction model, and to generate a three-dimensional model and a quality inspection report.

8. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a BIM-based air conditioning equipment installation method as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a BIM-based air conditioning equipment installation method as described in any one of claims 1 to 6.

Images