Building engineering door and window construction quality control method and system

Abstract

The invention relates to the technical field of constructional engineering, in particular to a constructional engineering door and window construction quality control method and system, and the method comprises the steps: obtaining door and window design data, determining each piece of representation information during door and window installation, and setting test parameters of doors and windows under each piece of representation information according to each piece of representation information during door and window installation; testing the door and window by using the test parameters to obtain basic calibration data and gap influence data; calibrating target quality data under the current test; according to the target quality data, obtaining characteristic attributes calibrated during door and window construction, constructing a characteristic association network by using the characteristic attributes, and calculating an association influence path of the characteristic association network under each characteristic attribute; determining a main influence range under door and window construction by using the associated influence path, and evaluating the current door and window construction quality according to data in the main influence range; and the overall construction quality and efficiency are realized.

Description

Technical Field

[0001] The invention relates to the technical field of building engineering, and in particular to a method and system for controlling the construction quality of doors and windows in a building engineering. Background Art

[0002] In construction projects, the quality of door and window construction directly affects the overall performance of the building, including but not limited to waterproofing, sound insulation, thermal insulation, and safety. However, in the actual construction process, due to the lack of precise quality control methods and effective monitoring means, deviations often occur in the installation of doors and windows, affecting the final use effect. Therefore, how to effectively evaluate and control the quality of door and window construction has become an important research topic.

[0003] For example, a Chinese patent application with publication number CN118070607A discloses a door and window risk prediction method, system and equipment based on stress tracking. In view of the existing problem that it is difficult to accurately predict the risk of door and window breakage, the following solution is proposed, which includes the following steps: Step 1: Obtain the structural properties of the door and window, wherein the structural properties of the door and window include at least environmental information and structural information; Step 2: Establish a finite element model of the door and window structure; The prior art describes that the dangerous situation during the construction of the door and window is determined by analyzing the door and window structure based on stress.

[0004] For example, a Chinese patent application with publication number CN111177837A discloses a data processing method, device and electronic equipment based on a three-dimensional building model. The method obtains a structured space plane model by processing the acquired three-dimensional building model, determines the spatial adjacency status between the spatial units of the structured space plane model and the spatial adjacency type of adjacent spatial units, and generates a business space connection relationship network to meet the needs of different businesses, thereby reducing the overall engineering cost of obtaining and managing building space relationship information.

[0005] The prior art describes the relative management conditions of doors and windows by measuring the stress of doors and windows and the relative spatial proximity of doors and windows. However, these conditions tend to view the basic properties of doors and windows, and cannot quickly view the current quality of doors and windows. Multiple indicators are needed to describe the actual conditions of the current doors and windows, which makes it impossible to fully identify the elements that are mainly affected by doors and windows when corresponding gaps and deformations occur in doors and windows, resulting in poor evaluation results for doors and windows. Summary of the invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for construction quality control of doors and windows in building projects, comprising: S1, obtaining door and window design data, determining various characterization information when doors and windows are installed, identifying the fit of doors and windows at various edge positions according to the various characterization information when doors and windows are installed, and setting test parameters for doors and windows under various characterization information.

[0007] S2, use the test parameters to test the doors and windows to obtain basic calibration data and gap impact data; obtain the edge integrity and edge fitting indicators of the doors and windows during construction through the basic calibration data.

[0008] S3, through the gap impact data, obtain the gap change size and gap change level during the construction of doors and windows, take the edge integrity, edge fitting index, gap change size and gap change level as input features, and calibrate the target quality data under the current test.

[0009] S4, according to the target quality data, obtain the characteristic attributes calibrated during the construction of doors and windows, and use the characteristic attributes to build a characteristic association network, and calculate the association influence path of the characteristic association network under each characteristic attribute.

[0010] S5, using the associated impact path, determines the main impact range under the door and window construction, and evaluates the current door and window construction quality according to the data within the main impact range.

[0011] The implementation method of representing the information in step S1 includes: extracting multiple construction nodes during the construction of the doors and windows according to the door and window design data, wherein the construction nodes represent various installation positions during the installation of the doors and windows.

[0012] According to the completion degree of each construction node, the representation information of the door and window installation is generated, and after the construction nodes are sorted in the order of completion of each construction node, each construction node is marked to obtain the representation information of the door and window installation.

[0013] The implementation of step S1 also includes: classifying each characterization information according to each characterization information when the doors and windows are installed, and determining a test parameter sequence corresponding to each characterization information.

[0014] According to the association relationship between each test parameter sequence, the corresponding content of each representation information is segmented and spaced to obtain a standardized sequence corresponding to the test parameter, thereby forming a test parameter under each representation information under multiple tests.

[0015] The implementation method of step S2 includes: S21, obtaining the basic coordinates of each component of the door and window from the basic calibration data, using the basic coordinates to compare with the coordinates of each component corresponding to the current door and window construction, and determining the coordinate deviation of each component in turn.

[0016] S22, checking the coordinate deviations of each component, and identifying the adjacency relationship between the coordinate deviations of each component on each adjacent component.

[0017] S23, in response to the adjacency relationship between the coordinate deviations of each component, determine whether each adjacent component is a window installation structure, whether it includes a door, a hole, a dividing line and a window, and set the edge integrity according to the description under the adjacency relationship.

[0018] S24, extracting the error of the sealing material on the doors and windows under the coordinate deviation of each component, and setting the edge fitting index according to the relative position of the coordinate deviation of each component and the sealing material.

[0019] The implementation method of step S3 includes: S31, taking edge integrity, edge fitting index, gap change size and gap change level as input features, setting a probability deviation sequence according to the occurrence probability of each input feature, judging the conditional probability of each input feature after combination in turn, and performing principal component analysis on the input features according to the values ​​of each conditional probability, and taking the data output by the principal component analysis as the target feature.

[0020] S32, performing association mapping on the target features, determining the degree of convergence of the target features, and sorting the target feature association mapping data according to the degree of convergence of the target features and outputting the data as target quality data.

[0021] The implementation method of step S32 also includes: processing the data of the association mapping of the target feature, identifying the numerical range that the target feature approaches, and setting the degree of approach for the target feature according to the upper limit, lower limit and average value of the numerical range that the target feature approaches.

[0022] The implementation of step S4 includes: S41, extracting characteristic attributes from the target quality data in sequence according to the working order of door and window installation, and determining the node type corresponding to each characteristic attribute.

[0023] S42, according to the node type corresponding to each feature attribute, each feature attribute is used as a node, the weight between the feature attributes under each node type is calculated, and a feature association network is constructed.

[0024] S43, calculating the path coefficient of each path in the characteristic association network, and selecting the shortest path with the maximum path coefficient value as the association influence path according to the path coefficient.

[0025] The implementation method of the feature association network also includes: obtaining the door and window structural relationship corresponding to each feature attribute, identifying the optimal connected subset corresponding to each feature attribute, and connecting each feature attribute according to the optimal connected subset to obtain the feature association network.

[0026] The implementation method of step S5 includes: randomly selecting a first sample point from the associated influence path, performing linear regression on the first sample point, determining a calculation result of the first sample point; and selecting a second sample point from the associated influence path according to the calculation result of the first sample point.

[0027] Determine the comprehensive weights of the first sample point and the second sample point under the associated influence path, perform information matching on the associated influence path according to the comprehensive weights, determine the weight distribution of the associated influence path after information matching, and take the area with the largest weight distribution as the main influence range under door and window construction.

[0028] The characteristic description of each node within the main impact range is compared with the preset database to determine the priority of the door and window construction assessment and obtain the assessment results of the door and window construction.

[0029] A construction quality control system for doors and windows of a building project includes: a data acquisition module for acquiring various original data related to the construction of doors and windows from the site, including but not limited to design drawings and construction records, and combining various original data into door and window design data.

[0030] The test analysis module is used to extract and execute specific test operations from the door and window design data, determine the test parameters to be executed and the test data corresponding to the test parameters.

[0031] The feature classification module is used to extract key features from the test data. The key features include edge integrity, edge fit index, gap change size and gap change level, and classify and manage the key features.

[0032] The association network construction module is used to construct a feature association network based on the extracted key features and calculate the association influence path between different key features.

[0033] The quality assessment module is used to comprehensively evaluate the construction quality of doors and windows based on the associated impact paths and provide users with specific improvement suggestions.

[0034] The beneficial effects of the present invention are as follows: 1. The present invention obtains relevant data during the installation of doors and windows, and uses these relevant data to select test parameters for door and window testing to achieve parametric modeling of construction quality. This can avoid subjectivity during manual inspection and tend to consider the fit and corresponding gap conditions of various positions during door and window construction to describe the specific conditions of the current door and window construction, thereby improving the controllability and observability of door and window quality construction.

[0035] 2. The present invention uses multiple indicators measured by test parameters and uses these indicators to construct a feature association network, which helps to identify the main factors affecting the construction quality of doors and windows and their interaction mechanisms; the door and window construction is described according to the association between multiple characteristic factors to further describe the actual content measured by the test parameters to achieve a quantitative analysis process; at the same time, according to the connection conditions under the feature association network, the relative weight in the network can be identified, which is convenient for the subsequent expression of the degree of influence of each construction node on the overall quality based on the main test content in the feature association network, thereby improving the efficiency of the overall construction quality test box and analysis.

[0036] 3. The present invention extracts the associated influence path from the feature association network to determine the main influencing range of door and window construction; finally, the current door and window construction quality is evaluated based on the data within the main influencing range; it describes the main influencing factors of door and window construction, and evaluates the overall door and window construction based on the factors to improve the overall construction quality and efficiency, which can reduce the impact between construction problems that occur during construction, and reduce the problem of reduced door and window construction quality caused by construction-affected data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0038] Figure 1 The invention is a flow chart of a method for controlling the construction quality of doors and windows in a building project.

[0039] Figure 2 The present invention is a flow chart of step S2 of a method for controlling the construction quality of doors and windows in a building project.

[0040] Figure 3 The present invention is a flow chart of step S3 of a method for controlling the construction quality of doors and windows in a building project.

[0041] Figure 4 The present invention is a flow chart of step S4 of a method for controlling the construction quality of doors and windows in a building project.

[0042] Figure 5 The present invention is a system diagram of a construction quality control system for doors and windows of a building project. DETAILED DESCRIPTION

[0043] The embodiments of the present invention are described in detail below. The embodiments described below are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. If no specific techniques or conditions are specified in the embodiments, the techniques or conditions described in the literature in the art or the product specifications are used.

[0044] See also Figure 1 A method for controlling the construction quality of doors and windows in a building project comprises: S1, obtaining design data of doors and windows, determining various characterization information when doors and windows are installed, identifying the fitting conditions of doors and windows at various edge positions according to the various characterization information when doors and windows are installed, and setting test parameters of doors and windows under various characterization information.

[0045] S2, use the test parameters to test the doors and windows to obtain basic calibration data and gap impact data; obtain the edge integrity and edge fitting indicators of the doors and windows during construction through the basic calibration data.

[0046] S3, through the gap impact data, obtain the gap change size and gap change level during the construction of doors and windows, take the edge integrity, edge fitting index, gap change size and gap change level as input features, and calibrate the target quality data under the current test.

[0047] S4, according to the target quality data, obtain the characteristic attributes calibrated during the construction of doors and windows, and use the characteristic attributes to build a characteristic association network, and calculate the association influence path of the characteristic association network under each characteristic attribute.

[0048] S5, using the associated impact path, determines the main impact range under the door and window construction, and evaluates the current door and window construction quality according to the data within the main impact range.

[0049] In one embodiment of the present invention, the implementation method of characterizing information in step S1 includes: extracting multiple construction nodes during door and window construction based on door and window design data, wherein the construction nodes represent various installation positions when doors and windows are installed, such as external window construction and external door bottom construction, and each position for door and window construction is regarded as a construction node.

[0050] According to the completion degree of each construction node, the representation information of the door and window installation is generated, and after the construction nodes are sorted in the order of completion of each construction node, each construction node is marked to obtain the representation information of the door and window installation.

[0051] The completion degree of the construction node indicates whether the work at the corresponding position during the construction of doors and windows is completed, and the construction nodes are marked according to the completion status. At the same time, the completed images or other forms of coordinate data can be collected to describe the corresponding characterization information.

[0052] The characterization information at this time will indicate the matching dimensions of the door and window frames and openings, horizontality and verticality, diagonal errors and other installation accuracy information, which is used to describe the relevant position coordinates and corresponding image information during the installation of doors and windows, as descriptive information for comparing the door and window installation conditions and the actual quality of the door and window installation.

[0053] At the same time, the characterization information can also represent multiple data information such as air tightness, water tightness, sealing strip status, wind pressure resistance and surface flatness that are pre-set for each position in the door and window design data; these parameters will be extracted as the main part of the door and window design data that mainly represents the current door and window performance, and then the doors and windows corresponding to these parameters will be tested, or some parameters will be selected as test parameters for subsequent use according to the actual fit of the doors and windows.

[0054] Airtightness: The amount of air permeability when doors and windows are closed, reflecting their heat insulation and energy-saving effects. Watertightness: The ability of doors and windows to resist rainwater leakage under simulated wind and rain conditions. Sealing strip status: Check whether the sealing strip is installed in place and has no aging or cracking. Wind pressure resistance: The deformation and bearing capacity of doors and windows under certain wind pressure. These four parameters can be used to judge their corresponding performance through the gaps of doors and windows during testing.

[0055] Surface flatness means that there should be no obvious scratches, dents or deformations on the surface of doors and windows. This part can be analyzed by collecting images of the installed doors and windows and building models to find out the completeness of the doors and windows installed in each part, so as to identify whether the overall installation meets the installation requirements.

[0056] When collecting and processing data on door and window installation, feeler gauges and vernier calipers can be used to detect the gaps between door and window sashes and frames, and between frames and walls, and compare the allowable deviation values.

[0057] Then use a laser level and a ruler to check the verticality and horizontality of the door and window frames to find out if there are deviations in these positions. At the same time, these data can be randomly sampled in the area after the construction is completed, and three-dimensional laser scanning, infrared thermal imaging and BIM model verification can be used to generate a three-dimensional point cloud model for the information of each door and window installed on site. The position deviation of these models at each actual construction position and the door and window design data can be calculated to find out if there are weak points in the installation of doors and windows, and the characterization information corresponding to these weak points will be used as the main content for subsequent processing and identification.

[0058] At the same time, you can also use a pressure box to perform pressure testing on doors and windows to check their leakage and deformation resistance. At this time, the doors and windows are mainly installed in various positions to conduct connectivity deviation checks to determine whether there are deviations in the current door and window construction. The deviations will be used as test parameters for subsequent use, and the overall edge integrity and deviation of the doors and windows will be tested.

[0059] When setting the test parameters of doors and windows under various characterization information, the main test parameters currently used will be determined mainly according to the data sampled on site, such as the deviation between the geometric dimensions, gaps, edge positions of the doors and windows installed and the doors and windows design data. The test parameters described at this time do not mean that the construction quality of the current doors and windows only uses the selected test parameters. Under normal door and window measurements, the conditions in multiple dimensions such as waterproofing, windproofing, heat insulation, and sound insulation will be measured for testing. At this time, the present invention focuses on dealing with the parts where obvious problems exist, and uses a visual network to display the associated impact paths, such as "sealant failure → rainwater leakage → wall mildew → circuit safety hazard", to describe the impact that the currently identified test parameters may have, so as to evaluate the construction quality of doors and windows.

[0060] Therefore, the implementation method of step S1 also includes: classifying each characterization information according to the characterization information when the doors and windows are installed, and determining the test parameter sequence corresponding to each characterization information. At this time, the classified test parameter sequence will represent the installation accuracy, that is, the parameters corresponding to the size and the parameters corresponding to the performance, and then a sequence representing multiple test parameters is obtained.

[0061] According to the correlation between each test parameter sequence, the corresponding content of each characterization information is segmented and spaced to obtain the standardized sequence corresponding to the test parameter, forming the test parameters under each characterization information under multiple tests. The correlation between each test parameter sequence is to couple each test parameter. For example, the hole size error can be associated with information that affects air tightness (excessive gaps lead to air leakage) and water tightness (rainwater infiltration), and the horizontality / verticality deviation is associated with reduced wind pressure resistance (uneven force and easy deformation). These contents will be used as the correlation between each test parameter sequence. At the same time, the correlation will be set in the database in advance to assist in the subsequent processing of each test parameter sequence combination.

[0062] The subsequent segmentation interval is to utilize the correlation between the test parameters to segment these correlated parameters, focusing on the test parameters that can cause the correlation, to segment the parameters in multiple test parameter sequences, to describe a standardized sequence with mutual influence. There are multiple test parameters in the standardized sequence, and then the test parameters in the standardized sequence are output to realize the main component analysis of the test parameters.

[0063] The test parameters will be different under different characterization information. For example, when each characterization information represents the size and coordinates of the current doors and windows, the width / height deviation, installation surface deviation, and window frame diagonal length difference can be set as the main identification test parameters.

[0064] For example, when identifying the matching size and geometric accuracy of the opening, the test parameters can be expressed as: opening size error: width / height deviation ≤±3mm (according to the "Architectural Construction Drawing Design" specification); horizontality / verticality: installation surface deviation ≤±2mm (measured using a laser theodolite); diagonal error: window frame diagonal length difference ≤5mm (reflecting the degree of rectangular deformation).

[0065] The test parameters described here are only some of the parameters extracted from the doors and windows under their construction conditions. The actual measured and selected parameters will be adjusted in other forms according to the measurement requirements and the actual design of the doors and windows.

[0066] The test parameters can also include the deviation between the actual coordinates and the design value, the width of the gap between the window frame and the wall, and the firmness test; installation position deviation: the deviation between the actual coordinates and the design value ≤±5mm (compared using the BIM model); gap control: the width of the gap between the window frame and the wall ≤3mm (filled with polyurethane foam); firmness test: the window frame is not loose when hammered (impact force ≥0.5kN).

[0067] In a certain project, the window frame tilted due to uneven walls. The thickness of the wooden spacers was adjusted in layers (each layer ≤ 2mm) and re-fixed to reduce the vertical deviation from 4mm to 1.5mm. The sealing was confirmed by feeler gauge testing.

[0068] When the test parameters are performance test parameters, other forms of parameters are mainly used for description, such as test parameters for air tightness and water tightness, wind pressure resistance and surface quality.

[0069] Air tightness level: air permeability per unit seam length (Q1-Q8, Q8 is the best); Water tightness level: simulated wind and rain pressure difference (ΔP1-ΔP6, ΔP6 corresponds to heavy rain level); Wind pressure resistance level: P3-P8 (P8 can withstand a level 12 typhoon); Surface flatness: 2m ruler detection gap ≤2mm (avoid scratches and deformation).

[0070] According to the values ​​represented by these parameters, the main test parameters used are extracted from the current test parameters to find out.

[0071] In one embodiment of the present invention, the basic calibration data reflects the performance benchmark values ​​of doors and windows under ideal installation conditions. These data will reflect the normal standard values ​​of the test parameters when the doors and windows are tested, and this data is used to compare the integrity of the doors and windows at the edges and the actual fit of the colloids, sealing strips, etc. at the edges, and verify the content of the gaps generated by the doors and windows in each case, so as to verify whether the edges can be shown to be complete, and use these calculated indicators as constraints for their use to complete the inspection of the construction quality of doors and windows.

[0072] Edge integrity indicates the degree of geometric matching between doors and windows and the edges of openings. The measurement parameters are mainly the minimum size deviation, diagonal error and surface flatness, which represent the error values ​​of door and window installation accuracy, to ensure that the window frame has no collision or deformation, and that the errors in the position of each component in the installation meet the construction specifications.

[0073] The edge fit index indicates the contact quality between the sealing material and the window frame / wall. The test parameters are mainly the compression of the sealing strip and the uniformity of the fit gap. These values ​​can be measured with a caliper at multiple points of the gap width and depth, and then judged whether the relative position error of the window meets the installation requirements after the sealing material is applied.

[0074] like Figure 2 As shown, the implementation method of step S2 includes: S21, obtaining the basic coordinates of each component of the door and window from the basic calibration data, using the basic coordinates to compare with the coordinates of each component corresponding to the current door and window construction, and determining the coordinate deviation of each component in turn.

[0075] S22, check the coordinate deviations of each component, and identify the adjacency relationship between the coordinate deviations of each component on each adjacent component. This indicates whether these deviations appear together on adjacent components when deviations of door and window components occur. If they appear together, it means that there are problems with both adjacent components, or that multiple deviations occur due to a problem with one component.

[0076] S23, in response to the adjacency relationship between the coordinate deviations of each component, determine whether each adjacent component is a window installation structure, whether it contains doors, holes, dividing lines and windows, and set the edge integrity according to the content described under the adjacency relationship. At this time, the edge integrity is based on the adjacency relationship. The existing coordinate error and other data are combined to describe whether the edge is complete. This indicator value will indicate the error situation at the corresponding position.

[0077] The described window sill installation structure can be a component with direct physical contact between door and window frames, walls, etc., and then the door, hole, dividing line and window are used to explain whether the current coordinate deviation of each component is located on the window, and according to the position, the edge integrity that appears at this time is explained. The edge integrity mainly describes the deviation generated.

[0078] S24, extracting the error of the sealing material fitting on the doors and windows under the coordinate deviation of each component, and setting the edge fitting index according to the relative position of the coordinate deviation of each component and the sealing material. The edge fitting index ultimately describes the error that occurs when fitting the sealing material on the corresponding component, and combines this error with the corresponding position on the doors and windows.

[0079] At this time, the coordinate errors generated on the doors and windows are processed, and these coordinate errors are explained according to the positions of the components and the relative contents of the sealing strips to indicate the corresponding positions when the coordinate errors occur. For the relevant errors of the sealing materials, image recognition can also be used to identify their relative coordinates, and basic calibration data can be used for comparison to obtain relevant errors.

[0080] In one embodiment of the present invention, the gap impact data describes the gaps generated during the performance test of the door and window construction quality. These gaps will affect the waterproof, windproof and other performance of the doors and windows under normal use. For example, if the gap set by the window frame changes due to wind test or heating test, then the size of the gap lock change and the interval represented by the level of change will indicate a decline in the performance of the current window itself and a reduction in the construction quality of the doors and windows.

[0081] Such as the minimum gap between doors and windows and the edge of openings, the gap in normal sliding grooves when doors and windows are installed, and other gaps. These gaps are measured to determine the overall stability of the current doors and windows under multiple simulated test environments. The gap change level will set multiple intervals according to the value of the gap change. For example, the gap width specified in the air tightness Q4 standard is used to describe the gap change level at this time. The intervals corresponding to the gap change levels will be pre-set in the database according to the data on the gap requirements for each level under the construction specifications, and describe the main conditions under the construction of the doors and windows.

[0082] The target quality data reflects the key indicators of the door and window installation quality, including the main parts of these test parameters, to find out the main problems that may exist in the current door and window construction, and use the data corresponding to these problems as the target quality data to conduct problem analysis on the door and window construction quality.

[0083] like Figure 3 As shown, the implementation method of step S3 includes: S31, taking edge integrity, edge fitting index, gap change size and gap change level as input features, setting a probability deviation sequence according to the occurrence probability of each input feature, judging the conditional probability of each input feature after combination in turn, and performing principal component analysis on the input features according to the values ​​of each conditional probability, and taking the data output by the principal component analysis as the target feature.

[0084] When using principal component analysis, the values ​​of edge integrity, edge fit index, gap change size and gap change level corresponding to the input features are first standardized and converted into a value range of 0-1, and then the probability of occurrence of each input feature is calculated, that is, the value is based on the distribution in historical data or experimental data, and then the relative weight of each input feature is obtained according to the sum of the probability of occurrence of each occurrence in the total data. The probability value is then converted into a deviation value. For example, the probability of occurrence of the input feature minus the average probability of occurrence is used to describe the deviation that each input feature can produce, and then the deviations of these probabilities are used to form a probability deviation sequence.

[0085] Then, the input features are combined in pairs to determine the conditional probability of satisfying multiple input features at the same time after the combination. When performing principal component analysis, after obtaining the covariance matrix of the input feature probability deviation, the weights of the corresponding two elements in the covariance matrix are set to the difference between the conditional probability of the two elements corresponding to the input features and the probability of occurrence of the input features corresponding to a single element. For example, there are two elements A and B in the covariance matrix. When considering the weights of A and B, the weight can be P(B|A)-P(B) to determine the relative weight of element B when element A occurs, to describe the adjustment of the content of the principal component analysis under the influence of conditional probability. Then, when performing eigenvalue decomposition, the existing technology will be used to implement the form of eigenvalue extraction. In this case, the eigenvalue extracted from the covariance matrix will be calculated, and when the cumulative variance contribution rate of the data output by the principal component reaches 0.95, the corresponding data will be used as the current target feature.

[0086] S32, performing association mapping on the target features, determining the degree of convergence of the target features, and sorting the target feature association mapping data according to the degree of convergence of the target features and outputting the data as target quality data.

[0087] The associative mapping of target features is to find out the data corresponding to the current target features, the positions and coordinates of these data on doors and windows, and the descriptive information recorded by these features. Then the degree of approach of the target features will indicate the numerical range that the corresponding input features approach, such as approaching the upper limit, lower limit and average value under normal circumstances. The data corresponding to the target features are represented by multiple numerical values ​​to describe the situation of approaching the numerical range. Then, according to the numerical range that the target features approach, multiple numerical values ​​are set for description, and then sorted to obtain three forms of target quality data.

[0088] Therefore, the implementation method of step S32 also includes: processing the data of the association mapping of the target feature, identifying the numerical range that the target feature approaches, and setting the degree of approach for the target feature according to the upper limit, lower limit and average value of the numerical range that the target feature approaches.

[0089] The TOPSIS method can be used to set the degree of trend of the target feature, that is, the absolute difference between the value and the negative ideal solution is divided by the sum of the absolute differences between the value and the negative ideal solution and the ideal solution. When setting the degree of trend, select the upper limit, lower limit and average value of the feature and the numerical range to calculate the maximum value of the trend, and then sort to obtain the target quality data.

[0090] In one embodiment of the present invention, in step S4, the features contained in the target quality data are used as feature attributes, and then the feature attributes are used as nodes, and the associations between the feature attributes are used as edges to form a feature association network; the Pearson correlation coefficient and the Spearman rank correlation coefficient can be used to calculate the feature attributes for the association relationships, and the main body of the calculation is based on the numerical values ​​corresponding to the feature attributes. It should be noted that the values ​​represented by the feature attributes are all normalized data, and the normalized data will also have a mapping relationship with the original data corresponding to the feature attributes, so as to facilitate the subsequent direct expression of the specific values ​​represented by each node under the feature association network.

[0091] like Figure 4 As shown, the implementation method of step S4 includes: S41, according to the working order of door and window installation, characteristic attributes are extracted from the target quality data in sequence, and the node type corresponding to each characteristic attribute is determined, and the node type includes input characteristic nodes corresponding to edge integrity, edge fitting index, gap change size and gap change level, intermediate variable node types describing test parameters, and target quality nodes corresponding to the target quality data when selected. These nodes will represent the contents represented by the test parameters mainly included in the target quality attributes.

[0092] S42, according to the node type corresponding to each feature attribute, each feature attribute is used as a node, the weights between the feature attributes under each node type are calculated, and a feature association network is constructed. As shown in Table 1, the extracted feature attributes are divided into the form of continuously associated nodes, and these nodes are combined to obtain a feature association network, which will represent the situation when the feature attributes are associated, and then these associations are combined with the problem to describe what should be represented when a related fault problem occurs.

[0093] Table 1. Schematic diagram of node types of feature attributes

[0094]

[0095] Table 1 shows the content that can be included in the description of feature attributes using node types, as well as the quantified values ​​of the corresponding nodes of feature attributes under various node types. For example, the input feature node represents the probability deviation relative to the ideal situation, and the intermediate variable node represents the probability of occurrence of the intermediate variable node under the condition of the input feature node, to describe the relationship between nodes at each level or type under the network connection. After that, the target quality node will use the same dimension as the input feature node, using probability distribution and discrete form to describe the relative situation of the target quality node. As shown in Table 2, the weights between various types of direct points in the feature association network can be described in the following way.

[0096] Table 2. Weight diagram

[0097]

[0098] Table 2 describes the associations that each type will adopt under these three types, that is, the weights between the input feature nodes will be implemented in the way that the corresponding data calculates the correlation coefficient, and the correlation coefficient can be expressed by the Pearson correlation coefficient; the input feature nodes and the target quality nodes will adopt the form of linear regression analysis, taking the input features as independent variables and the target quality as the dependent variable, and calculating the regression coefficient, and taking the regression coefficient as the weight between the input feature nodes and the target quality nodes. If the input feature node, the intermediate variable node, and the target quality node are connected, the corresponding path coefficient will be expressed by the product of the weights on this path; for the weight from the intermediate variable to the target variable, the linear regression analysis will also be adopted, taking the input features as independent variables and the target quality as the dependent variable, to obtain the corresponding regression coefficient, which is the weight from the intermediate variable to the target variable.

[0099] The paths under these weights are then connected to obtain an associated impact path related to the currently collected data.

[0100] The implementation method of the feature association network also includes: obtaining the door and window structural relationship corresponding to each feature attribute, identifying the optimal connected subset corresponding to each feature attribute, and connecting each feature attribute according to the optimal connected subset to obtain the feature association network.

[0101] At this point, we further describe whether the corresponding features on the doors and windows can be structurally connected. After connecting the nodes corresponding to the feature attributes, we use recursive feature elimination to find the optimal subset in the corresponding situation.

[0102] When extracting the optimal connected subset, extraction is performed according to the corresponding correlation coefficient of each feature attribute. Then, the input feature nodes with a correlation coefficient greater than 0.5 are selected, and when the regression coefficient between the input feature node and the target quality node, and between the intermediate variable node and the target quality node is greater than 0.6, the nodes that can be connected to the feature attributes at this time are taken as the optimal subset, and then the feature attributes are connected to obtain a feature association network.

[0103] S43, calculating the path coefficient of each path in the characteristic association network, and selecting the shortest path with the maximum path coefficient value as the association influence path according to the path coefficient.

[0104] At this time, after the feature attributes under different input features and corresponding node types are connected, the network mainly represents the relevant problems existing in the installation of doors and windows, and combines the features that may correspond to these problems, and finally obtains the correlation between different feature attributes, and further describes the errors in these feature attributes to judge the overall construction quality.

[0105] In one embodiment of the present invention, in step S5, the types of nodes included in the obtained associated impact path and how these nodes are connected are mainly used to find out the content that will be mainly affected by the current door and window construction, and this part of the affected content is marked as the main impact range. The characteristic information described by the main impact range is then used to describe the quality of the current door and window construction, so that subsequent engineering personnel can analyze the description of the corresponding door frame and judge whether the construction is completed normally.

[0106] Therefore, the implementation method of step S5 includes: randomly selecting a first sample point from the associated influence path, performing linear regression on the first sample point, and determining the calculation result of the first sample point; and selecting a second sample point from the associated influence path according to the calculation result of the first sample point. The first sample point represents any one of the input feature nodes, intermediate variable nodes, and target quality nodes, and then calculates the value of the node under the parameters calculated by each node described by the entire associated influence path, such as quantifying the change trend or relative association strength of the node, that is, obtaining the relative weight corresponding to the first sample point and other nodes, and then selecting the second sample point to represent the comprehensive weight of the two points under the associated influence path, and then selecting a group of the first sample point and the second sample point with the largest value according to the comprehensive weight to know the most obvious groups of parameters measured under the current door and window construction, and then clarifying that the current door and window construction may have this problem.

[0107] Determine the comprehensive weights of the first sample point and the second sample point under the associated influence path, perform information matching on the associated influence path according to the comprehensive weights, determine the weight distribution of the associated influence path after information matching, and take the area with the largest weight distribution as the main influence range under door and window construction.

[0108] The implementation method of information matching is to calculate the comprehensive weight of the corresponding data of the first sample point and the second sample point under the current associated path, and compare the values ​​corresponding to each group of the first sample point and the second sample point, and then determine the distribution and value of the comprehensive weight, and then select the area corresponding to the largest part of the value in the weight distribution sequence of the comprehensive weight combination, and identify the area as the main problem area under the current door and window construction quality test. The content and description of the corresponding node in this area will indicate the main problems in the door and window construction. For example, the edge integrity and gap change level are measured at the node. It is found that the gap change level has increased by 30% compared with the content measured under normal circumstances. This means that there are some small gaps in the door frame that are not handled properly during installation, or the door and window gaps of the corresponding materials of the door and window change significantly under wind, water and other tests. It is necessary to adjust the door and window materials used during construction to illustrate the main problems in the current door and window construction.

[0109] The characteristic description of each node within the main impact range is compared with the preset database to determine the priority of the door and window construction assessment and obtain the assessment results of the door and window construction.

[0110] Compare the content expressed by the data of each node within the main impact range with the preset database to explain what quality problems exist in the current door and window construction represented by the measured data at this time, and then determine the priority of the current problems in the door and window construction according to the position of these quality problems on the associated impact path. The priority can be expressed according to the relative weight of the node represented by this data and other nodes. Then, the node connection status, position and other content represented by these quality problems will be output. This output is the evaluation result, which is convenient for subsequent engineering personnel to check the construction problems existing at this time.

[0111] like Figure 5 As shown, the present invention also provides a construction quality control system for doors and windows of building projects, including: a data acquisition module, a test analysis module, a feature classification module, an association network construction module and a quality assessment module; wherein the output end of the data acquisition module is connected to the test analysis module, the output end of the test analysis module is connected to the feature classification module, the output end of the feature classification module is connected to the association network construction module, and the output end of the association network construction module is connected to the quality assessment module.

[0112] The data acquisition module is used to collect various original data related to door and window construction from the site, including but not limited to design drawings and construction records, and combine various original data into door and window design data.

[0113] The test analysis module is used to extract and execute specific test operations from the door and window design data, determine the test parameters to be executed and the test data corresponding to the test parameters.

[0114] The feature classification module is used to extract key features from the test data. The key features include edge integrity, edge fit index, gap change size and gap change level, and classify and manage the key features.

[0115] The association network construction module is used to construct a feature association network based on the extracted key features and calculate the association influence path between different key features.

[0116] The quality assessment module is used to comprehensively evaluate the construction quality of doors and windows based on the associated impact paths and provide users with specific improvement suggestions.

[0117] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention and they are still covered by the protection scope of the present invention.

Claims

1. A method for controlling the construction quality of doors and windows in a building project, characterized in that: include: S1, obtaining the design data of doors and windows, determining various characterization information when the doors and windows are installed, identifying the fitting conditions of the doors and windows at various edge positions according to the various characterization information when the doors and windows are installed, and setting the test parameters of the doors and windows under various characterization information; S2, test the doors and windows using the test parameters to obtain basic calibration data and gap impact data; obtain the edge integrity and edge fitting indicators of the doors and windows during construction through the basic calibration data; S3, through the gap impact data, obtain the gap change size and gap change level during the construction of doors and windows, take the edge integrity, edge fitting index, gap change size and gap change level as input features, and calibrate the target quality data under the current test; S4, according to the target quality data, obtain the characteristic attributes calibrated during the construction of doors and windows, and use the characteristic attributes to build a characteristic association network, and calculate the association influence path of the characteristic association network under each characteristic attribute; S5, using the associated impact path, determines the main impact range under the door and window construction, and evaluates the current door and window construction quality according to the data within the main impact range.

2. A construction quality control method for doors and windows of a building project according to claim 1, characterized in that: The implementation of the characterization information in step S1 includes: According to the design data of doors and windows, multiple construction nodes during the construction of doors and windows are extracted, wherein the construction nodes represent the installation positions of the doors and windows during installation; According to the completion degree of each construction node, the representation information of the door and window installation is generated, and after the construction nodes are sorted in the order of completion of each construction node, each construction node is marked to obtain the representation information of the door and window installation.

3. A construction quality control method for doors and windows of a building project according to claim 1, characterized in that: The implementation of step S1 also includes: According to the various characterization information during the installation of doors and windows, the various characterization information are classified, and the test parameter sequence corresponding to each characterization information is determined; According to the association relationship between each test parameter sequence, the corresponding content of each representation information is segmented and spaced to obtain a standardized sequence corresponding to the test parameter, thereby forming a test parameter under each representation information under multiple tests.

4. A construction quality control method for doors and windows of a building project according to claim 1, characterized in that: The implementation of step S2 includes: S21, obtaining the basic coordinates of each door and window component from the basic calibration data, comparing the basic coordinates with the coordinates of each component corresponding to the current door and window construction, and determining the coordinate deviations of each component in turn; S22, checking the coordinate deviations of each component, and identifying the adjacency relationship between the coordinate deviations of each component on each adjacent component; S23, in response to the adjacency relationship between the coordinate deviations of each component, determining whether each adjacent component is a window installation structure, whether it includes a door, a hole, a dividing line and a window, and setting the edge integrity according to the description under the adjacency relationship; S24, extracting the error of the sealing material on the doors and windows under the coordinate deviation of each component, and setting the edge fitting index according to the relative position of the coordinate deviation of each component and the sealing material.

5. A construction quality control method for doors and windows of a building project according to claim 1, characterized in that: The implementation of step S3 includes: S31, taking the edge integrity, edge fit index, gap change size and gap change level as input features, setting a probability deviation sequence according to the occurrence probability of each input feature, sequentially determining the conditional probability of each input feature after combination, and performing principal component analysis on the input features according to the value of each conditional probability, and taking the data output by the principal component analysis as the target feature; S32, performing association mapping on the target features, determining the degree of convergence of the target features, and sorting the target feature association mapping data according to the degree of convergence of the target features and outputting the data as target quality data.

6. A construction quality control method for doors and windows of a building project according to claim 5, characterized in that: The implementation of step S32 also includes: The data of the association mapping of the target feature is processed to identify the numerical range that the target feature approaches, and the degree of approach for the target feature is set according to the upper limit, lower limit and average value of the numerical range that the target feature approaches.

7. A construction quality control method for doors and windows of a building project according to claim 1, characterized in that: The implementation of step S4 includes: S41, extracting characteristic attributes from the target quality data in sequence according to the working order of door and window installation, and determining the node type corresponding to each characteristic attribute; S42, according to the node type corresponding to each feature attribute, each feature attribute is used as a node, the weight between the feature attributes under each node type is calculated, and a feature association network is constructed; S43, calculating the path coefficient of each path in the characteristic association network, and selecting the shortest path with the maximum path coefficient value as the association influence path according to the path coefficient.

8. A construction quality control method for doors and windows of a building project according to claim 7, characterized in that: The implementation method of the feature association network also includes: obtaining the door and window structural relationship corresponding to each feature attribute, identifying the optimal connected subset corresponding to each feature attribute, and connecting each feature attribute according to the optimal connected subset to obtain the feature association network.

9. A construction quality control method for doors and windows in a building project according to claim 1, characterized in that: The implementation of step S5 includes: Randomly select a first sample point from the associated influence path, perform linear regression on the first sample point, and determine a calculation result of the first sample point; and select a second sample point from the associated influence path according to the calculation result of the first sample point; Determine the comprehensive weights of the first sample point and the second sample point under the associated impact path, and match the associated impact path according to the comprehensive weights, determine the weight distribution of the associated impact path after information matching, and take the area with the largest weight distribution as the main impact range under the door and window construction; The characteristic description of each node within the main impact range is compared with the preset database to determine the priority of the door and window construction assessment and obtain the assessment results of the door and window construction.

10. A construction quality control system for doors and windows in a building project, characterized in that: include: The data collection module is used to collect various original data related to the door and window construction from the site, including but not limited to design drawings and construction records, and combine various original data into door and window design data; A test analysis module is used to extract and execute specific test operations from the door and window design data, determine the test parameters to be executed and the test data corresponding to the test parameters; The feature classification module is used to extract key features from the test data. The key features include edge integrity, edge fit index, gap change size and gap change level, and classify and manage the key features; The association network construction module is used to construct a feature association network based on the extracted key features and calculate the association influence path between different key features; The quality assessment module is used to comprehensively evaluate the construction quality of doors and windows based on the associated impact paths and provide users with specific improvement suggestions.

Images