A building engineering quality detection method and system based on big data

Abstract

The application discloses a building engineering quality detection method and system based on big data, relates to the technical field of building detection, obtains engineering information and real-time environment information of a building and constructs a three-dimensional model, configures different door and window information in the three-dimensional model to generate different door and window schemes, performs heat conduction simulation on the building under different door and window schemes to obtain an insulation effect diagram, obtains a plurality of simulation detection points and simulation insulation coefficients in the insulation effect diagram, obtains a heat conduction condition set of different buildings under different door and window schemes and constructs an insulation evaluation model, sets a plurality of actual detection points and obtains actual insulation coefficients, obtains theoretical insulation coefficients by using the insulation evaluation model, judges whether the building has an invalid door and window scheme, and generates a recommended door and window scheme; the method is favorable for obtaining the insulation effects of different doors and windows, reflecting the insulation capacity of different doors and windows, and improving the insulation quality of the building in a timely manner.

Description

Technical Field

[0001] This invention relates to the field of building inspection technology, specifically a building engineering quality inspection method and system based on big data. Background Technology

[0002] During the construction process of building projects, a large amount of relevant data is generated, including structural design data, material selection data, construction process data, etc. Using this data, we can comprehensively evaluate and optimize various performance aspects of building projects, realize real-time monitoring and early warning of building project quality, and provide strong support for the quality management of building projects.

[0003] For both completed and unfinished building projects, thermal insulation performance is always an important testing indicator. For the building itself, whether the thermal insulation of doors and windows can be properly tested and optimized will directly affect the thermal insulation performance of the entire building. In the existing technology, it is often impossible to intuitively and accurately reflect the thermal insulation capacity of doors and windows, nor can it achieve effective thermal insulation optimization, and it is impossible to detect the thermal insulation problems of doors and windows in the building in a timely manner, thus affecting the thermal insulation effect of the entire building. In view of the shortcomings of the existing technology, this invention provides a building engineering quality testing method and system based on big data. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for inspecting the quality of building engineering based on big data.

[0005] The objective of this invention can be achieved through the following technical solution: a construction engineering quality inspection system based on big data, comprising the following modules:

[0006] The data acquisition module is used to acquire the building's engineering information and real-time environmental information, and to build a corresponding 3D model. Different door and window information is configured in the 3D model to generate different door and window schemes.

[0007] The data simulation module is used to simulate the heat conduction of buildings under different door and window schemes to obtain the heat insulation effect diagram of the building under different door and window schemes. In the heat insulation effect diagram, several simulation test points and their simulated heat insulation coefficients under different door and window schemes are obtained.

[0008] The model building module is used to obtain the set of heat conduction conditions for different buildings under different door and window schemes, and to build a heat insulation evaluation model for doors and windows by combining the simulated heat insulation coefficient;

[0009] The quality inspection module is used to set up several actual inspection points on the building and obtain the corresponding actual thermal insulation coefficient. It uses the thermal insulation evaluation model to obtain the theoretical thermal insulation coefficient, and determines whether there are invalid door and window schemes in the building. For buildings with invalid door and window schemes, it generates recommended door and window schemes and provides feedback.

[0010] Furthermore, the process of acquiring the building's engineering information and real-time environmental information, constructing a corresponding 3D model, and configuring different door and window information in the 3D model to generate different door and window schemes includes:

[0011] The engineering information includes design drawings, material parameters, construction technology, and floor plan. The real-time environmental information includes indoor and outdoor temperature and humidity, indoor and outdoor light intensity, and indoor and outdoor air velocity. A three-dimensional model of the building is constructed using CAD software based on the acquired engineering information.

[0012] The door and window information includes door and window materials and door and window thickness. Using BIM technology, different door and window information is entered separately. The three-dimensional model of the building is imported into the building information model. Different door and window materials and door and window thicknesses are configured for the three-dimensional model in the building information model, and different door and window schemes are generated.

[0013] Furthermore, the process of conducting heat conduction simulations on buildings with different window and door schemes to obtain thermal insulation effect diagrams of buildings under different window and door schemes includes:

[0014] Based on the building information model, a corresponding digital twin model is constructed, and various real-time environmental information is synchronized to the digital twin model. Simulation software is used to simulate heat conduction in the digital twin model to obtain indoor and outdoor temperature difference data at the doors and windows of the building under a single door and window scheme. The indoor and outdoor temperature difference data refers to the temperature difference value between the inside and outside of each location at the doors and windows of the building.

[0015] The indoor and outdoor temperature difference data are divided into different numerical ranges according to their magnitude. A color corresponding to a wavelength is assigned to each numerical range. Each location is then rendered with the color corresponding to its indoor and outdoor temperature difference data to obtain the corresponding heat insulation effect diagram.

[0016] Furthermore, the process of obtaining several simulated test points and their simulated thermal insulation coefficients under different door and window schemes from the thermal insulation effect diagram includes:

[0017] In the thermal insulation effect diagram, the contact area between the building's doors and windows and the concrete exterior wall is taken as the edge area, and the other areas of the building's doors and windows other than the edge area are taken as the door and window area. The simulated detection points include edge detection points and center detection points.

[0018] Several locations are randomly selected within the edge region as edge detection points, and the indoor-outdoor temperature difference data W of each edge detection point at the same time is obtained. i Where i = 1, 2, ..., n, and n is the number of edge detection points, the edge temperature difference coefficient W at the same time is obtained. b ;

[0019]

[0020] The center of the door and window area is taken as the central detection point, and the indoor and outdoor temperature difference data W at the corresponding time point is obtained. z The simulated thermal insulation coefficient G is obtained by combining the edge temperature difference coefficient at the corresponding time. m ;

[0021]

[0022] The simulated thermal insulation coefficients of each door and window of a building under the same door and window scheme are obtained, and the simulated thermal insulation coefficients of each door and window of a building under different door and window schemes are obtained.

[0023] Furthermore, the process of obtaining the set of heat conduction conditions for different buildings under different door and window schemes, and constructing the corresponding heat insulation assessment model in combination with the simulated heat insulation coefficient, includes:

[0024] The set of heat conduction conditions includes the area of ​​doors and windows and the ambient temperature difference. The area of ​​doors and windows is the area of ​​a single door or window region, and the ambient temperature difference is the difference between the corresponding indoor ambient temperature and the outdoor ambient temperature.

[0025] The simulated thermal insulation coefficients of doors and windows in different buildings under different door and window schemes are obtained. The thermal insulation evaluation set is generated by combining the corresponding heat conduction condition set and the thermal insulation evaluation set is divided into training set and test set.

[0026] To construct a convolutional neural network, different door and window schemes and their heat conduction conditions in the training set are used as input data for the convolutional neural network, and the corresponding simulated heat insulation coefficients in the training set are used as output data for the convolutional neural network. The convolutional neural network is then trained to obtain an initial convolutional neural network.

[0027] The initial convolutional neural network is validated using a test set. The initial convolutional neural network whose output is less than or equal to the preset test error threshold is used as the thermal insulation evaluation model.

[0028] Furthermore, the process of setting up several actual testing points on the building, obtaining the corresponding actual insulation coefficients, using an insulation assessment model to obtain the theoretical insulation coefficients, and determining whether the building has ineffective door and window designs includes:

[0029] Obtain edge regions and door / window regions, along with their corresponding edge detection points and center detection points, at the doors and windows of the building to be inspected. The actual detection points include the edge detection points and center detection points of the building to be inspected.

[0030] Using the same method as for obtaining the simulated insulation coefficient, the actual insulation coefficient G at the doors and windows of the building under test was obtained. jThe system obtains the set of door and window schemes and heat conduction conditions for the doors and windows of the building to be tested, and inputs both into the thermal insulation evaluation model. The thermal insulation evaluation model then outputs the corresponding theoretical thermal insulation coefficient G0.

[0031] Compare the actual thermal insulation coefficient of the doors and windows of the building under test with its corresponding theoretical thermal insulation coefficient. If G j If G < 0, then mark it as an invalid door and window scheme; if 0 ≤ G j If G ≤ G0, then mark it as a valid door and window scheme; if G j If the value is greater than G0, then mark it as an invalid door and window scheme.

[0032] Furthermore, the process of generating and providing feedback on recommended door and window solutions for buildings with invalid door and window designs includes:

[0033] For windows and doors marked as invalid, obtain their current set of heat conduction conditions, input different window and door schemes into the heat insulation assessment model, use the heat insulation assessment model to output different theoretical heat insulation coefficients, select the window and door scheme corresponding to the smallest theoretical heat insulation coefficient as the recommended window and door scheme, and feed it back to the relevant personnel.

[0034] A big data-based method for inspecting the quality of construction projects includes the following steps:

[0035] Step S1: Obtain the building's engineering information and real-time environmental information, and construct the corresponding 3D model. Configure different door and window information in the 3D model to generate different door and window schemes.

[0036] Step S2: Perform heat conduction simulation on buildings under different door and window schemes to obtain heat insulation effect diagrams of buildings under different door and window schemes. Obtain several simulation test points and their simulated heat insulation coefficients under different door and window schemes from the heat insulation effect diagrams.

[0037] Step S3: Obtain the set of heat conduction conditions for different buildings under different door and window schemes, and construct the corresponding heat insulation evaluation model by combining the simulated heat insulation coefficient;

[0038] Step S4: Set up several actual detection points on the building and obtain the corresponding actual thermal insulation coefficients. Use the thermal insulation evaluation model to obtain the theoretical thermal insulation coefficients and determine whether there are invalid door and window schemes in the building. Generate recommended door and window schemes for buildings with invalid door and window schemes and provide feedback.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] This invention constructs a three-dimensional model of a building, introduces different door and window information on this basis, and then constructs a corresponding digital twin model. It can simulate the building insulation under different door and window schemes in the digital twin model, which is beneficial to obtain the insulation effect of different doors and windows. The simulated insulation coefficient is represented by the simulated insulation coefficient, which is obtained by analyzing the temperature difference between the edge and center of the door and window, and can reflect the insulation capacity of different doors and windows.

[0041] By acquiring the set of heat conduction conditions corresponding to different simulated insulation coefficients and constructing an insulation evaluation model in conjunction with corresponding door and window solutions, the current theoretical insulation coefficient can be directly obtained. By obtaining the actual insulation coefficient in the actual application scenario and comparing it with the theoretical insulation coefficient, it is helpful to determine whether the current doors and windows can meet the insulation requirements. For doors and windows that cannot meet the requirements, recommended door and window solutions can be generated in a timely manner, which is conducive to improving the insulation quality of buildings in a timely manner. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0043] like Figure 1 As shown, a construction engineering quality inspection system based on big data includes the following modules:

[0044] The data acquisition module is used to acquire the building's engineering information and real-time environmental information, and to build a corresponding 3D model. Different door and window information is configured in the 3D model to generate different door and window schemes.

[0045] The data simulation module is used to simulate the heat conduction of buildings under different door and window schemes to obtain the heat insulation effect diagram of the building under different door and window schemes. In the heat insulation effect diagram, several simulation test points and their simulated heat insulation coefficients under different door and window schemes are obtained.

[0046] The model building module is used to obtain the set of heat conduction conditions for different buildings under different door and window schemes, and to build a heat insulation evaluation model for doors and windows by combining the simulated heat insulation coefficient;

[0047] The quality inspection module is used to set up several actual inspection points on the building and obtain the corresponding actual thermal insulation coefficient. It uses the thermal insulation evaluation model to obtain the theoretical thermal insulation coefficient, and determines whether there are invalid door and window schemes in the building. For buildings with invalid door and window schemes, it generates recommended door and window schemes and provides feedback.

[0048] It should be further explained that, in the specific implementation process, the process of acquiring the building's engineering information and real-time environmental information, constructing the corresponding 3D model, and configuring different door and window information in the 3D model to generate different door and window schemes includes:

[0049] The engineering information refers to various data and attributes directly related to the building itself, including design drawings, material parameters, construction technology, floor plan, etc. The real-time environmental information refers to the environmental conditions around and inside the building, including indoor and outdoor temperature and humidity, indoor and outdoor light intensity, indoor and outdoor air velocity, etc.

[0050] Using computer-aided design (CAD) software, a three-dimensional model of the building is constructed based on the acquired engineering information. At this time, the constructed three-dimensional model only includes information such as the building's structure, dimensions, shape, and materials, but does not include subsequent door and window information.

[0051] The door and window information refers to the selection of materials and parameters for the doors and windows of the building, including door and window materials and thickness. Using Building Information Modeling (BIM) technology, door and window information with different materials and thicknesses is entered separately, and the three-dimensional model of the building is imported into the Building Information Model.

[0052] In Building Information Modeling (BIM), different door and window information with different materials and thicknesses are configured for the 3D model, and different door and window schemes are generated. At least one of the door and window materials and thicknesses is different for each scheme.

[0053] It should be further explained that, in the specific implementation process, the process of conducting heat conduction simulations on buildings with different door and window schemes to obtain thermal insulation effect diagrams of buildings under different door and window schemes includes:

[0054] A digital twin model of the building and its doors and windows is constructed based on the building information model. The digital twin model is used to describe the temperature distribution of the building's doors and windows during the heat conduction process, and various real-time environmental information is synchronized to the constructed digital twin model.

[0055] The heat conduction of a digital twin model under a single door and window scheme is simulated using simulation software to obtain indoor and outdoor temperature difference data at the doors and windows of the building under the single door and window scheme. The indoor and outdoor temperature difference data refers to the temperature difference value between the inside and outside of the doors and windows at various locations of the building.

[0056] The temperature difference value is equal to the indoor contact surface temperature at the corresponding location minus the outdoor contact surface temperature. The indoor and outdoor temperature difference data are divided into different numerical ranges according to their numerical values, and each numerical range is assigned a color corresponding to a wavelength. The larger the value, the larger the wavelength.

[0057] Each location is rendered with the color corresponding to its indoor and outdoor temperature difference data to obtain the corresponding heat insulation effect map. The heat insulation effect map can reflect the indoor and outdoor temperature difference at each location, obtain heat insulation effect maps under different door and window schemes, and bind the obtained heat insulation effect map with its door and window scheme.

[0058] It should be further explained that, in the specific implementation process, the process of obtaining several simulated test points and their simulated thermal insulation coefficients under different door and window schemes from the thermal insulation effect diagram includes:

[0059] Since the same building often contains different doors and windows, the same door and window scheme may also contain different thermal insulation effect diagrams. Take any thermal insulation effect diagram as an example.

[0060] In the thermal insulation effect diagram, the contact area between the building's doors and windows and the concrete exterior wall is taken as the edge area, and the other areas of the building's doors and windows other than the edge area are taken as the door and window area. The simulated detection points include edge detection points and center detection points.

[0061] Several locations are randomly selected within the edge region as edge detection points. The obtained edge detection points are numbered as i, i = 1, 2, ..., n, where n is the number of edge detection points.

[0062] The indoor and outdoor temperature difference data of each edge detection point at the same time is denoted as W. i Obtain the edge temperature difference coefficient at the same time, denoted as W. b ;

[0063]

[0064] The center of the door and window area is taken as the central detection point. The indoor and outdoor temperature difference data of the central detection point at the corresponding time is obtained and denoted as W. z The simulated thermal insulation coefficient at the doors and windows of the building is obtained by combining the edge temperature difference coefficient at the corresponding time, and is denoted as G. m ;

[0065]

[0066] The same method was used to obtain the simulated thermal insulation coefficients of each door and window of a building under the same door and window scheme, and the simulated thermal insulation coefficients of each door and window of a building under different door and window schemes were also obtained.

[0067] It should be further explained that, in the specific implementation process, the process of obtaining the set of heat conduction conditions for different buildings under different door and window schemes, and constructing the corresponding heat insulation assessment model in combination with the simulated heat insulation coefficient, includes:

[0068] The set of heat conduction conditions includes the area of ​​a single door and window area (i.e., the door and window area) and the difference between the corresponding indoor and outdoor ambient temperatures (i.e., the ambient temperature difference). The indoor and outdoor ambient temperatures refer to the ambient temperatures, not the contact surface temperatures at different locations on the doors and windows.

[0069] The simulated thermal insulation coefficients of doors and windows in different buildings under different door and window schemes are obtained, and a thermal insulation evaluation set is generated by combining the corresponding heat conduction condition set. The obtained thermal insulation evaluation set is divided into a training set and a test set.

[0070] Convolutional neural networks are constructed by using different door and window schemes and heat conduction conditions in the training set as input data and the corresponding simulated heat insulation coefficients in the training set as output data. The convolutional neural networks are then trained to obtain an initial convolutional neural network.

[0071] The initial convolutional neural network is validated using a test set. The initial convolutional neural network whose output is less than or equal to the preset test error threshold is used as the corresponding thermal insulation evaluation model.

[0072] It should be further explained that, in the specific implementation process, the process of setting up several actual testing points on the building, obtaining the corresponding actual insulation coefficients, using the insulation assessment model to obtain the theoretical insulation coefficients, and determining whether the building has ineffective door and window schemes includes:

[0073] In practical application scenarios, edge regions and door / window regions, along with their corresponding edge detection points and center detection points, are obtained at the doors and windows of the building to be inspected. The actual detection points include the edge detection points and center detection points at the doors and windows of the building to be inspected.

[0074] Using the same method as for obtaining the simulated insulation coefficient, the actual insulation coefficient G at the doors and windows of the building under test was obtained. j The system obtains the set of door and window schemes and heat conduction conditions for the doors and windows of the building to be tested, and inputs both into the thermal insulation evaluation model. The thermal insulation evaluation model then outputs the corresponding theoretical thermal insulation coefficient G0.

[0075] The actual thermal insulation coefficient G at the doors and windows of the building to be tested j Compare it with its corresponding theoretical insulation coefficient G0, if G j If G < 0, then mark it as an invalid door and window scheme; if 0 ≤ G j If G ≤ G0, then it is marked as a valid door and window scheme, and no other operations are performed on it; if G j If the value is greater than G0, then mark it as an invalid door and window scheme.

[0076] It should be further explained that, in the specific implementation process, the process of generating recommended door and window schemes for buildings with invalid door and window schemes and providing feedback includes:

[0077] For windows and doors marked as invalid, their current heat conduction conditions are obtained, and different window and door schemes are input into the heat insulation assessment model. The heat insulation assessment model outputs different theoretical heat insulation coefficients, and the window and door scheme corresponding to the smallest theoretical heat insulation coefficient is taken as the recommended window and door scheme. This is then fed back to relevant personnel, who are advised to select materials and carry out construction according to the recommended window and door scheme.

[0078] Embodiments of the present invention also include a method for inspecting the quality of building construction projects based on big data, comprising the following steps:

[0079] Step S1: Obtain the building's engineering information and real-time environmental information, and construct the corresponding 3D model. Configure different door and window information in the 3D model to generate different door and window schemes.

[0080] Step S2: Perform heat conduction simulation on buildings under different door and window schemes to obtain heat insulation effect diagrams of buildings under different door and window schemes. Obtain several simulation test points and their simulated heat insulation coefficients under different door and window schemes from the heat insulation effect diagrams.

[0081] Step S3: Obtain the set of heat conduction conditions for different buildings under different door and window schemes, and construct the corresponding heat insulation evaluation model by combining the simulated heat insulation coefficient;

[0082] Step S4: Set up several actual detection points on the building and obtain the corresponding actual thermal insulation coefficients. Use the thermal insulation evaluation model to obtain the theoretical thermal insulation coefficients and determine whether there are invalid door and window schemes in the building. Generate recommended door and window schemes for buildings with invalid door and window schemes and provide feedback.

[0083] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A construction engineering quality inspection system based on big data, characterized in that, Includes the following modules: The data acquisition module is used to acquire the building's engineering information and real-time environmental information, and to build a corresponding 3D model. Different door and window information is configured in the 3D model to generate different door and window schemes. The data simulation module is used to simulate the heat conduction of buildings under different door and window schemes to obtain the heat insulation effect diagram of the building under different door and window schemes. In the heat insulation effect diagram, several simulation test points and their simulated heat insulation coefficients under different door and window schemes are obtained. The model building module is used to obtain the set of heat conduction conditions for different buildings under different door and window schemes, and to build a heat insulation evaluation model for doors and windows by combining the simulated heat insulation coefficient; The quality inspection module is used to set up several actual inspection points on the building and obtain the corresponding actual thermal insulation coefficient. It uses the thermal insulation evaluation model to obtain the theoretical thermal insulation coefficient, and determines whether there are invalid door and window schemes in the building. It generates recommended door and window schemes for buildings with invalid door and window schemes and provides feedback. The process of simulating heat conduction in buildings with different door and window designs to obtain thermal insulation effect diagrams includes: Based on the building information model, a corresponding digital twin model is constructed, and various real-time environmental information is synchronized to the digital twin model. Simulation software is used to simulate heat conduction in the digital twin model to obtain indoor and outdoor temperature difference data at the doors and windows of the building under a single door and window scheme. The indoor and outdoor temperature difference data refers to the temperature difference value between the inside and outside of each location at the doors and windows of the building. The indoor and outdoor temperature difference data are divided into different numerical ranges according to their magnitude. A color corresponding to a wavelength is set for each numerical range. Each position is rendered with the color corresponding to its indoor and outdoor temperature difference data to obtain the corresponding heat insulation effect diagram. The process of obtaining several simulated test points and simulated insulation coefficients in the insulation effect diagram includes: In the thermal insulation effect diagram, the contact area between the building's doors and windows and the concrete exterior wall is taken as the edge area, and the other areas of the building's doors and windows other than the edge area are taken as the door and window area. The simulated detection points include edge detection points and center detection points. Several locations are randomly selected within the edge region as edge detection points, and the indoor-outdoor temperature difference data W of each edge detection point at the same time is obtained. i Where i = 1, 2, ..., n, and n is the number of edge detection points, the edge temperature difference coefficient W at the same time is obtained. b ; The center of the door and window area is taken as the central detection point, and the indoor and outdoor temperature difference data W at the corresponding time point is obtained. z The simulated thermal insulation coefficient G is obtained by combining the edge temperature difference coefficient at the corresponding time. m ; The simulated thermal insulation coefficients of each door and window of a building under the same door and window scheme are obtained, and the simulated thermal insulation coefficients of each door and window of a building under different door and window schemes are obtained. The process of obtaining the set of heat conduction conditions and constructing the corresponding insulation assessment model by combining the simulated insulation coefficient includes: The set of heat conduction conditions includes the area of ​​doors and windows and the ambient temperature difference. The area of ​​doors and windows is the area of ​​a single door or window region, and the ambient temperature difference is the difference between the corresponding indoor ambient temperature and the outdoor ambient temperature. The simulated thermal insulation coefficients of doors and windows in different buildings under different door and window schemes are obtained. The thermal insulation evaluation set is generated by combining the corresponding heat conduction condition set and the thermal insulation evaluation set is divided into training set and test set. To construct a convolutional neural network, different door and window schemes and their heat conduction conditions in the training set are used as input data for the convolutional neural network, and the corresponding simulated heat insulation coefficients in the training set are used as output data for the convolutional neural network. The convolutional neural network is then trained to obtain an initial convolutional neural network. The initial convolutional neural network is validated using a test set. The initial convolutional neural network whose output is less than or equal to the preset test error threshold is used as the thermal insulation evaluation model. The process of obtaining the actual and theoretical insulation coefficients and determining whether a building has ineffective door and window designs includes: Obtain edge regions and door / window regions, along with their corresponding edge detection points and center detection points, at the doors and windows of the building to be inspected. The actual detection points include the edge detection points and center detection points of the building to be inspected. Using the same method as for obtaining the simulated insulation coefficient, the actual insulation coefficient G at the doors and windows of the building under test was obtained. j The system obtains the set of door and window schemes and heat conduction conditions for the doors and windows of the building to be tested, and inputs both into the thermal insulation evaluation model. The thermal insulation evaluation model then outputs the corresponding theoretical thermal insulation coefficient G0. Compare the actual thermal insulation coefficient of the doors and windows of the building under test with its corresponding theoretical thermal insulation coefficient. If G j If G < 0, then mark it as an invalid door and window scheme; if 0 ≤ G j If G ≤ G0, then mark it as a valid door and window scheme; if G j If the value is greater than G0, then mark it as an invalid door and window scheme; The process of generating and providing feedback on recommended door and window schemes for buildings with invalid door and window schemes includes: For windows and doors marked as invalid, obtain their current set of heat conduction conditions, input different window and door schemes into the heat insulation assessment model, use the heat insulation assessment model to output different theoretical heat insulation coefficients, select the window and door scheme corresponding to the smallest theoretical heat insulation coefficient as the recommended window and door scheme, and feed it back to the relevant personnel.

2. The construction engineering quality inspection system based on big data according to claim 1, characterized in that, The process of building a 3D model of a building and generating different door and window designs includes: The engineering information includes design drawings, material parameters, construction technology, and floor plan. The real-time environmental information includes indoor and outdoor temperature and humidity, indoor and outdoor light intensity, and indoor and outdoor air velocity. A three-dimensional model of the building is constructed using CAD software based on the acquired engineering information. The door and window information includes door and window materials and door and window thickness. Using BIM technology, different door and window information is entered separately. The three-dimensional model of the building is imported into the building information model. Different door and window materials and door and window thicknesses are configured for the three-dimensional model in the building information model, and different door and window schemes are generated.

3. A method for inspecting the quality of building construction projects based on big data, implemented based on the big data-based building construction project quality inspection system as described in any one of claims 1-2, characterized in that, The method includes: Step S1: Obtain the building's engineering information and real-time environmental information, and construct the corresponding 3D model. Configure different door and window information in the 3D model to generate different door and window schemes. Step S2: Perform heat conduction simulation on buildings under different door and window schemes to obtain heat insulation effect diagrams of buildings under different door and window schemes. Obtain several simulation test points and their simulated heat insulation coefficients under different door and window schemes from the heat insulation effect diagrams. Step S3: Obtain the set of heat conduction conditions for different buildings under different door and window schemes, and construct the corresponding heat insulation evaluation model by combining the simulated heat insulation coefficient; Step S4: Set up several actual detection points on the building and obtain the corresponding actual thermal insulation coefficients. Use the thermal insulation evaluation model to obtain the theoretical thermal insulation coefficients and determine whether there are invalid door and window schemes in the building. Generate recommended door and window schemes for buildings with invalid door and window schemes and provide feedback.

Images