Quality evaluation method and terminal for house steel structure project

Abstract

The invention provides a quality evaluation method and terminal for a house steel structure project, and the method comprises the steps: constructing a plurality of detection items of the house steel structure project, and determining the detection item weight of each detection item; acquiring detection data of each detection item in different construction stages of the house steel structure project; calculating a sub-quality evaluation value of the house steel structure project in each construction stage according to the detection data and the corresponding detection item weight; when each sub-quality evaluation value meets the requirement, determining a quality evaluation weight of each construction stage, and performing weighted summation on the sub-quality evaluation value of each construction stage and the corresponding quality evaluation weight to obtain a comprehensive quality evaluation value of the house steel structure project; and when the comprehensive quality evaluation value is greater than a preset threshold value, outputting an evaluation result that the quality of the house steel structure project is qualified so as to systematically and quantitatively evaluate the quality of the house steel structure project and ensure that the quality of the whole project reaches the standard in each construction stage.

Description

Technical Field

[0001] The present application relates to the technical field of quality assessment of steel structure projects, and in particular, to a quality assessment method and terminal for building steel structure projects. Background Art

[0002] Steel structure engineering is a structure made mainly of steel materials, mainly composed of steel beams, steel columns, steel trusses and other components made of steel and steel plates. The components or parts are usually connected by welding, bolts or rivets. It is one of the main types of building structures. Because of its light weight and simple construction, it is widely used in houses, large factories, venues and other fields.

[0003] The existing quality assessment method for housing steel structure projects generally adopts sampling inspection of steel structure components of housing steel structure projects after the entire housing steel structure project is completed, including material strength test, weld quality inspection, etc., to verify whether it meets the relevant standards and specifications. However, this quality assessment method does not take into account each construction stage of the housing steel structure project, and it is difficult to ensure that the quality of the entire project at each construction stage meets the preset standards, which easily leads to low quality assessment accuracy of housing steel structure projects.

[0004] In the technical solution with application number 202410713936.2, although it performs grayscale processing on the component view, and through the defect feature part marked at the grayscale processing, combined with the complete component view in different directions, it determines that the defect feature part is a convex defect feature or a concave defect feature, and then determines that the concave defect feature is a concave feature or a crack feature, thereby completing the surface quality of the steel component and the detection operation based on the image data to quickly find the defect feature. However, this technical solution does not take into account each construction stage of the house steel structure project, and it is difficult to ensure that the quality of the entire project at each construction stage meets the preset standards.

[0005] In the technical solution with application number 202410871298.7, although it uses the information determination model to determine the information of each welding point, the vibration video of each welding point, the information of multiple steel pipes connected to each welding point, and the vibration video of multiple steel pipes connected to each welding point, the graph structure is processed based on the graph neural network model to determine multiple abnormal welding points, and the unqualified welding points among the multiple abnormal welding points are determined based on the X-ray imaging of the multiple abnormal welding points. The X-ray processing model is used to determine the unqualified welding points in the multiple abnormal welding points, so as to quickly and accurately perform quality inspection on the steel structure. However, this technical solution only performs quality inspection on the welding points of the steel structure, and the quality assessment is not comprehensive enough. At the same time, it also does not take into account each construction stage of the house steel structure project, and it is difficult to ensure that the quality of the entire project at each construction stage meets the preset standards. Summary of the invention

[0006] The main purpose of this application is to provide a quality assessment method and terminal for housing steel structure projects, so as to systematically and quantitatively evaluate the quality of housing steel structure projects and ensure that the quality of the entire project at each construction stage meets the preset standards.

[0007] In order to achieve the above-mentioned invention object, the present application provides a quality assessment method for a steel structure project of a house, comprising:

[0008] Construct multiple inspection items for housing steel structure projects and determine the inspection item weight for each inspection item;

[0009] Obtaining the inspection data of each inspection item of the housing steel structure project at different construction stages;

[0010] According to the inspection data of each inspection item in different construction stages and the corresponding inspection item weight, the sub-quality assessment value of the housing steel structure project in each construction stage is calculated;

[0011] When the sub-quality assessment values ​​of each construction stage meet the requirements, the quality assessment weight of each construction stage is determined, and the sub-quality assessment value of each construction stage is weighted and summed with the corresponding quality assessment weight to obtain the comprehensive quality assessment value of the housing steel structure project;

[0012] When the comprehensive quality assessment value is greater than a preset threshold, an assessment result indicating that the quality of the housing steel structure project is qualified is output.

[0013] Preferably, determining the detection item weight of each detection item includes:

[0014] Obtain historical project data for each test project;

[0015] After data preprocessing of the historical project data of each detection project, the target historical project data of each detection project is obtained;

[0016] According to the target historical project data of each inspection project, the influence of each inspection project on the engineering quality of the housing steel structure project is evaluated respectively;

[0017] The corresponding detection item weight is determined according to the influence of each detection item, and the detection item weight is positively correlated with the influence.

[0018] Preferably, after performing data preprocessing on the historical project data of each detection project, target historical project data of each detection project is obtained, including:

[0019] The historical project data of each detection project are processed in sequence for missing values, outliers and data standardization to obtain target historical project data for each detection project.

[0020] Preferably, determining the corresponding detection item weight according to the influence of each detection item includes:

[0021] Set base weights;

[0022] The influence of each detection item is multiplied by the basic weight to obtain the detection item weight corresponding to each detection item.

[0023] In one embodiment, determining the quality assessment weight of each construction stage includes:

[0024] Identify the completed works items in each construction phase;

[0025] Calculate the proportion of the completed project in each construction stage to the total construction volume of the steel structure project, and obtain the proportion of the construction volume in each construction stage;

[0026] Conduct risk assessments on completed projects at each construction stage and determine the risk factor for each construction stage;

[0027] The quality assessment weight of each construction stage is obtained by multiplying the proportion of the engineering volume in each construction stage by the corresponding risk coefficient.

[0028] In one embodiment, the sub-quality assessment value of the steel structure project at each construction stage is calculated based on the inspection data of each inspection item at different construction stages and the corresponding inspection item weight, including:

[0029] For each construction stage, respectively extracting welding images of each inspection item, the inspection data including welding images of the housing steel structure project, and the inspection items including items for inspecting welding quality of the housing steel structure project;

[0030] Performing image preprocessing on the welding image to obtain a target welding image;

[0031] Removing connected regions and spots whose image area in the target welding image is lower than a preset value, so as to extract the center line of the weld in the target welding image;

[0032] Performing linear fitting on the center line of the weld to obtain the position of the characteristic point of the weld;

[0033] Performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features, wherein the welding defect features include cracks, pores or lack of fusion;

[0034] The welding defect characteristics are fused with the pre-processed environmental data to form comprehensive welding data for each construction stage, wherein the environmental data refers to data of various environmental factors that affect welding quality and welding process during the welding process of the steel structure project of the house;

[0035] Evaluate the comprehensive welding data at each construction stage to generate a welding quality evaluation value at each construction stage;

[0036] After multiplying the welding quality assessment value of each construction stage with the corresponding inspection item weight, the first sub-quality assessment value of the house steel structure project at each construction stage is obtained, and the first sub-quality assessment value is used to evaluate the welding quality of the house steel structure project.

[0037] In one embodiment, the performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features includes:

[0038] Based on the characteristic point positions of the weld, local maximum value detection is performed on the target welding image to determine detection points of multiple potential welding defect areas;

[0039] According to the plurality of detection points and the watershed algorithm, different image regions in the target welding image are segmented and screened to obtain a plurality of segmented regions, each of which corresponds to a potential welding defect;

[0040] Welding defect detection is performed on each of the segmented areas to obtain welding defect features.

[0041] Preferably, the performing image preprocessing on the welding image to obtain a target welding image comprises:

[0042] Performing median filtering on the welding image to obtain a first welding image;

[0043] Performing gradient detection on the first welding image to obtain a second welding image;

[0044] The second welding image is subjected to grayscale binarization processing to obtain a target welding image.

[0045] In one embodiment, before performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain the welding defect feature, the method further includes:

[0046] Identify the edge of the weld in the target welding image according to an edge detection algorithm;

[0047] The edge of the weld in the target welding image is removed.

[0048] The present application also provides a terminal, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0049] The present application provides a quality assessment method and terminal for a steel structure project of a house, which determine key inspection items that affect the quality of the steel structure project of the house, and assign weights to each item to reflect its relative importance in the overall quality assessment; collect data for each inspection item at different construction stages, and use the collected inspection data and the corresponding inspection item weights to calculate the sub-quality assessment value of each construction stage to assess the quality level of each construction stage; when the sub-quality assessment values ​​of all construction stages meet the requirements, determine the quality assessment weight of each construction stage, and perform weighted summation of the sub-quality assessment value and the corresponding weight to obtain a comprehensive quality assessment value of the entire project, so as to systematically and quantitatively assess the quality of the steel structure project of the house, and combine each construction stage of the steel structure project for comprehensive assessment, thereby ensuring that the quality of the entire project at each construction stage meets the preset standards, and improving the accuracy and reliability of the comprehensive quality assessment of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a quality assessment method for a steel structure project of a house according to an embodiment of the present application;

[0051] Figure 2 A flow chart of a quality assessment method for a steel structure project of a house according to another embodiment of the present application;

[0052] Figure 3 A flow chart of a quality assessment method for a steel structure project of a house according to another embodiment of the present application;

[0053] Figure 4 This is a schematic structural diagram of a quality assessment device for a steel structure project of a house according to an embodiment of the present application;

[0054] Figure 5 This is a schematic block diagram of the structure of a terminal according to an embodiment of the present application.

[0055] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The present application proposes a quality assessment method for a steel structure project of a house, wherein the execution subject is a terminal, which can be a stationary computing device such as a desktop computer or a PC, or a mobile or stationary server.

[0058] refer to Figure 1 In one embodiment, the present application provides a quality assessment method for a steel structure project of a house, the method comprising:

[0059] S11. Construct multiple inspection items for the housing steel structure project and determine the inspection item weight for each inspection item;

[0060] S12, obtaining the inspection data of each inspection item of the housing steel structure project at different construction stages;

[0061] S13, calculating the sub-quality assessment value of the steel structure project at each construction stage according to the inspection data of each inspection item in different construction stages and the corresponding inspection item weight;

[0062] S14. When the sub-quality assessment values ​​at each construction stage meet the requirements, determine the quality assessment weight of each construction stage, and perform weighted summation of the sub-quality assessment values ​​at each construction stage and the corresponding quality assessment weight to obtain a comprehensive quality assessment value of the housing steel structure project;

[0063] S15. When the comprehensive quality assessment value is greater than a preset threshold, output an assessment result indicating that the quality of the steel structure project of the house is qualified.

[0064] This embodiment can determine the key inspection items of the housing steel structure project, such as material strength, weld quality, dimensional accuracy, etc., according to the characteristics and requirements of the housing steel structure project. At the same time, a weight is assigned to each inspection item, which reflects the importance of the inspection item in the overall quality assessment of the housing steel structure project.

[0065] At each stage of construction (such as the foundation construction stage, the main structure construction stage, the enclosure structure construction stage, etc.), the test data of each test item is collected, and the sub-quality assessment value of the housing steel structure project at each construction stage is calculated based on the test data of each test item in different construction stages and the corresponding test item weight. For example, the weighted average method can be used to combine the test data and weights to calculate the sub-quality assessment value of each construction stage to evaluate the quality of the housing steel structure project at each construction stage.

[0066] Among them, the test data may include steel performance test data, welding material test data, bolt connection material test data, weld non-destructive testing data, welding process assessment test data, size and deformation test data, etc., and may also include a score value for each test item. For example, after analyzing and evaluating the steel performance test data, welding material test data and bolt connection material test data, a score value for material strength is obtained.

[0067] Steel performance test data: including indicators such as yield strength, tensile strength, elongation and impact toughness, which reflect the basic mechanical properties of steel.

[0068] Welding material testing data: involves chemical composition analysis and mechanical property testing of welding materials to ensure welding quality.

[0069] Bolt connection material testing data: including torque coefficient or pre-tension test of high-strength bolts to ensure the reliability of the connection.

[0070] Weld nondestructive testing data: Use ultrasonic testing, radiographic testing, magnetic particle testing and penetrant testing to detect defects inside and on the surface of welds.

[0071] Welding procedure qualification test data: evaluate the suitability of welding procedures and weld quality.

[0072] If the sub-quality assessment values ​​of all construction stages meet the requirements, for example, the sub-quality assessment values ​​of each construction stage are greater than the corresponding, preset reference quality assessment value, the quality assessment weight is determined according to the importance of each construction stage, and the sub-quality assessment value of each construction stage is weighted and summed with the corresponding quality assessment weight to calculate the comprehensive quality assessment value, which combines the quality assessment of each construction stage and is used to reflect the overall construction quality of the housing steel structure project. If the comprehensive quality assessment value exceeds the preset qualified threshold, the project quality is considered qualified.

[0073] For example, suppose a house steel structure project has the following inspection items and weights:

[0074] Material strength: 30%;

[0075] Weld quality: 40%;

[0076] Dimensional accuracy: 30%.

[0077] During the three stages of construction (foundation construction stage, main structure construction stage, and enclosure structure construction stage), the test data collected are as follows:

[0078] Foundation construction stage: material strength 90 points, weld quality 85 points, dimensional accuracy 90 points;

[0079] Main structure construction stage: material strength 95 points, weld quality 90 points, dimensional accuracy 80 points;

[0080] During the construction phase of the retaining structure: material strength 90 points, weld quality 90 points, and dimensional accuracy 80 points.

[0081] Based on the above data, the sub-quality assessment value for each construction stage is calculated as follows:

[0082] Foundation construction stage: 0.3*90+0.4*85+0.3*90=88 points;

[0083] Main structure construction stage: 0.3*95+0.4*90+0.3*80=88.5 points;

[0084] Retaining structure construction phase: 0.3*90+0.4*90+0.3*80=87 points.

[0085] Assuming that the quality assessment weight of each construction stage is the same, which is 1 / 3, the calculated comprehensive quality assessment value is:

[0086] S=(88+88.5+87)*1 / 3=87.83 points.

[0087] If the preset threshold is 80 points, it is determined that the quality of the house steel structure project is qualified.

[0088] The present application provides a quality assessment method for a steel structure project for a house, which determines key inspection items that affect the quality of the steel structure project for a house, and assigns a weight to each item to reflect its relative importance in the overall quality assessment; collects data for each inspection item at different construction stages, and uses the collected inspection data and the corresponding inspection item weights to calculate a sub-quality assessment value for each construction stage to assess the quality level of each construction stage; when the sub-quality assessment values ​​of all construction stages meet the requirements, determines the quality assessment weight for each construction stage, and performs a weighted summation of the sub-quality assessment value and the corresponding weight to obtain a comprehensive quality assessment value for the entire project, so as to systematically and quantitatively assess the quality of the steel structure project for a house, and combines each construction stage of the steel structure project for a comprehensive assessment, thereby ensuring that the quality of the entire project at each construction stage meets the preset standards, and improving the accuracy and reliability of the comprehensive quality assessment of the project.

[0089] In one embodiment, reference Figure 2 In step S11, determining the detection item weight of each detection item may specifically include:

[0090] S111, obtaining historical project data of each test project;

[0091] S112, after performing data preprocessing on the historical project data of each detection project, obtaining the target historical project data of each detection project;

[0092] S113, evaluating the influence of each inspection item on the engineering quality of the housing steel structure project according to the target historical project data of each inspection item;

[0093] S114. Determine a corresponding detection item weight according to the influence of each detection item, wherein the detection item weight is positively correlated with the influence.

[0094] This embodiment collects data of various inspection items in previous house steel structure projects to form historical project data, which may include material strength test results, weld quality inspection results, dimensional accuracy measurement results, etc.

[0095] Then, the historical project data of each test project is cleaned, including removing outliers, filling missing values, data standardization, etc., to obtain the target historical project data of each test project to ensure the quality and consistency of the data, and analyze the relationship between the target historical project data of each test project and the project quality to determine the degree of influence of each test project on the overall quality. The influence can be obtained through data analysis, such as determining the degree of influence of each test project on the project quality through regression analysis, correlation analysis and other methods, which will not be repeated here.

[0096] According to the size of the impact, a corresponding weight is assigned to each detection item, and the detection item with a greater impact is assigned a higher weight.

[0097] This embodiment can evaluate the impact of inspection items on project quality through quantitative methods, accurately set the inspection item weight of each inspection item to improve the accuracy and reliability of quality assessment, and can also promptly discover inspection items that may cause quality problems and take measures to prevent risks in advance.

[0098] For example, suppose there are four key inspection items in a house steel structure project: A (material strength), B (weld quality), C (dimensional accuracy), and D (painting quality). Based on historical project data, weld quality issues (item B) have the greatest impact on project quality, followed by material strength (item A), then dimensional accuracy (item C), and coating quality (item D) has the least impact. At this point, historical project data of these four inspection items for the past 10 similar projects can be collected, the historical project data can be cleaned, outliers can be removed, missing values ​​can be filled, and the data can be standardized to form target historical project data. Through statistical analysis, it is found that the target historical project data of inspection item B has the highest correlation with engineering quality accidents, followed by inspection item A, and inspection items C and D are lower. According to the impact assessment results, the weights are assigned as B = 40%, A = 30%, C = 20%, and D = 10%. In the new project, the sub-quality assessment value of each construction stage is calculated based on the assigned weights and inspection data, and the comprehensive quality assessment value is further calculated. In this way, the inspection item weight of each inspection item can be accurately set, and project managers can also clearly understand the impact of each inspection item on project quality and make scientific and reasonable management decisions based on it.

[0099] In one embodiment, the data preprocessing of the historical project data of each detection project to obtain the target historical project data of each detection project may specifically include:

[0100] The historical project data of each detection project are processed in sequence for missing values, outliers and data standardization to obtain target historical project data for each detection project.

[0101] In this embodiment, missing value processing can ensure the integrity of historical project data and avoid bias caused by missing values ​​during analysis. For example, forward filling (filling with the previous data), backward filling (filling with the next data) or Lagrange interpolation method can be used to fill the missing values ​​of historical project data.

[0102] Outlier processing can identify and process outliers in historical project data to reduce the impact on the overall data analysis results. The outlier processing methods include descriptive statistics (such as obviously erroneous data with negative age), three sigma method (outlier identification based on normal distribution), etc.

[0103] Data standardization can convert historical project data of different dimensions and magnitudes into comparable formats, eliminate unit effects, and facilitate subsequent analysis. The data standardization methods include minimum and maximum normalization (scaling data to the [0,1] interval), Z-Score standardization (standardization based on mean and standard deviation), etc.

[0104] This embodiment can improve the accuracy and reliability of data by processing missing values ​​and outliers in historical project data. At the same time, by standardizing the historical project data, data from different projects and different stages in the historical project data can be directly compared, reducing bias in analysis results caused by data quality issues and providing a more objective quality assessment.

[0105] In one embodiment, determining the corresponding detection item weight according to the influence of each detection item may specifically include:

[0106] Set base weights;

[0107] The influence of each detection item is multiplied by the basic weight to obtain the detection item weight corresponding to each detection item.

[0108] In this embodiment, a basic weight is first set for each detection item. The basic weight reflects a preliminary judgment on the importance of each detection item without any specific data support. For example, the basic weight can be determined by historical data analysis or industry standards.

[0109] Then, the impact degree of each inspection item (i.e., the specific impact degree of the inspection item on the project quality) is multiplied by its basic weight to obtain a more accurate inspection item weight.

[0110] This embodiment can make the weight distribution more scientific and reasonable by combining the basic weight and the influence, and can dynamically adjust the weight according to the specific circumstances of the actual project to improve the flexibility and adaptability of the evaluation.

[0111] For example, suppose there are three inspection items in a house steel structure project: A (material strength), B (weld quality), and C (dimensional accuracy). First, set the basic weights for these three inspection items, then analyze the influence of each inspection item based on historical data, and calculate the final inspection item weights. For example, set the basic weight to 0.8, and through historical data analysis, it is found that the influence of weld quality B is the highest, which is 1.2; the influence of material strength A is 1.0; and the influence of dimensional accuracy C is 0.8. Then the inspection item weights corresponding to each inspection item are:

[0112] Final weight of A: 0.8*1.0=80%;

[0113] Final weight of B: 0.8*1.2=96%;

[0114] Final weight of C: 0.8*0.8=64%.

[0115] Therefore, through the above technical solution, it can be ensured that the weight of each inspection item in the quality assessment is more accurate, so as to more effectively control and manage the quality of the housing steel structure project.

[0116] In one embodiment, reference Figure 3 In step S14, determining the quality assessment weight of each construction stage may specifically include:

[0117] S141. Determine the completed projects in each construction phase;

[0118] S142, respectively calculating the proportion of the engineering project completed in each construction stage to the engineering quantity of the entire house steel structure engineering, to obtain the proportion of the engineering quantity in each construction stage;

[0119] S143. Conduct risk assessment on completed projects at each construction stage and determine the risk factor for each construction stage;

[0120] S144. Multiply the engineering quantity proportion of each construction stage by the corresponding risk coefficient to obtain the quality assessment weight of each construction stage.

[0121] In the steel structure project of a house, according to the construction progress, the specific engineering projects that have been completed in each construction stage are clarified, such as foundation construction, main structure construction, enclosure structure construction, etc. By comparing the workload completed in each construction stage with the total workload of the entire project, the proportion of the workload in each construction stage is calculated. For example, it can be calculated through a bill of quantities or a quota of workload.

[0122] According to the construction safety risk assessment guidelines, the risks that may be faced at each construction stage are identified and classified, and the possibility and severity of the risks are assessed to determine the risk factor. Combining the proportion of engineering quantities and the risk factor, the proportion of engineering quantities at each construction stage is multiplied by the corresponding risk factor to calculate the quality assessment weight of each construction stage.

[0123] This embodiment comprehensively considers the two dimensions of engineering quantity and risk, making the calculation of quality assessment weights more accurate and comprehensive; at the same time, the allocation of quality weights based on data and risk assessment also makes quality assessment more scientific and objective.

[0124] For example, suppose a house steel structure project is divided into three projects at different construction stages: foundation construction, main structure construction, and enclosure construction. The following is an example of the proportion of project volume and risk factor for each project:

[0125] 1. Foundation construction:

[0126] Proportion of engineering work: 30%;

[0127] Risk factor: 1.2 (taking into account the importance and potential risks of foundation construction to the entire project);

[0128] 2. Main structure construction:

[0129] Project quantity proportion: 50%;

[0130] Risk factor: 1.5 (the construction risk of the main structure is relatively high);

[0131] 3. Construction of enclosure structure:

[0132] Project volume proportion: 20%;

[0133] Risk factor: 0.8 (relatively low risk).

[0134] Based on the above data, the quality assessment weight of each construction stage is calculated as:

[0135] Weight of foundation construction quality assessment: 30%*1.2=36%;

[0136] Weight of main structure construction quality assessment: 50%*1.5=75%;

[0137] Weight of enclosure structure construction quality assessment: 20%*0.8=16%.

[0138] In one embodiment, the sub-quality assessment value of the steel structure project at each construction stage is calculated based on the inspection data of each inspection item at different construction stages and the corresponding inspection item weight, which may specifically include:

[0139] For each construction stage, respectively extracting welding images of each inspection item, the inspection data including welding images of the housing steel structure project, and the inspection items including items for inspecting welding quality of the housing steel structure project;

[0140] Performing image preprocessing on the welding image to obtain a target welding image;

[0141] Removing connected regions and spots whose image area in the target welding image is lower than a preset value, so as to extract the center line of the weld in the target welding image;

[0142] Performing linear fitting on the center line of the weld to obtain the position of the characteristic point of the weld;

[0143] Performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features, wherein the welding defect features include cracks, pores or lack of fusion;

[0144] The welding defect characteristics are fused with the pre-processed environmental data to form comprehensive welding data for each construction stage, wherein the environmental data refers to data of various environmental factors that affect welding quality and welding process during the welding process of the steel structure project of the house;

[0145] Evaluate the comprehensive welding data at each construction stage to generate a welding quality evaluation value at each construction stage;

[0146] After multiplying the welding quality assessment value of each construction stage with the corresponding inspection item weight, the first sub-quality assessment value of the house steel structure project at each construction stage is obtained, and the first sub-quality assessment value is used to evaluate the welding quality of the house steel structure project.

[0147] In this embodiment, at each construction stage, the welded parts of the house steel structure project are inspected and corresponding welding images are extracted from the inspection data, which are the basic data for subsequent welding quality inspection.

[0148] The extracted welding images are subjected to image preprocessing, and the image preprocessing methods include denoising, contrast enhancement, binarization processing, etc., to facilitate subsequent feature extraction and analysis.

[0149] Then, a preset morphological processing method (such as corrosion, expansion, opening operation, closing operation, etc.) can be used to remove connected areas and spots in the target welding image whose area is less than a preset value, that is, to remove smaller connected areas and spots in the target welding image to extract the center line of the weld.

[0150] In one embodiment, when removing connected regions and spots whose image area is less than a preset value in the target welding image, a plurality of structural elements of different scales and shapes may be defined for the target welding image, and the structural elements determine the influence range and shape of the morphological operation. The structural elements may be in various shapes, such as a circle, a square, or a rectangle. The size of the structural element may affect the effect of the opening operation. A larger structural element may remove larger noise, but may affect the shape of larger objects in the image.

[0151] A unique structural element is assigned to each image region of the target welding image, and based on the assigned unique structural element, an erosion operation is performed on each image region corresponding to the target welding image. The erosion operation reduces the white area in the target welding image and eliminates small white spots and fine extensions. This embodiment can simultaneously process noise and details of different sizes by using structural elements of different scales for the erosion operation, retain important features of the image, and remove noise of different sizes. In addition, by using structural elements of different shapes, features of different directions in the target welding image can be better adapted. For example, circular, square, and diamond structural elements can be used to detect image regions of horizontal, vertical, and diagonal edges in the target welding image.

[0152] After the erosion operation, the expansion operation is performed on each image region corresponding to the target welding image based on the assigned unique structural element. The expansion operation increases the white area in the target welding image, which helps to restore the boundaries of the larger objects removed during the erosion process. By combining the erosion and then expansion, the image boundaries can be smoothed while removing small noise points, thereby removing small objects or details while maintaining the shape of larger objects. Finally, the bwareaopen function or the remove_small_objects function can be used to remove the connected areas with an area smaller than the preset value in the target welding image after the expansion operation, thereby combining structural elements of different scales and shapes to remove small connected areas and spots in the target welding image to accurately extract the centerline of the weld.

[0153] Next, this embodiment can perform straight line fitting on the extracted weld center line based on the Hough transform method to obtain the characteristic point position of the weld. The Hough transform method is a feature extraction technology used to identify geometric shapes such as straight lines and circles in an image. At the same time, welding defect detection is performed on the target welding image based on the characteristic point position of the weld to identify welding defect features such as cracks, pores or lack of fusion.

[0154] Multimodal data fusion is performed on welding defect characteristics and pre-processed environmental data (such as temperature, humidity, wind speed and other environmental factors that affect welding quality and process) to form comprehensive welding data for each construction stage. This is to optimize the image processing algorithm and improve anti-interference ability, detection efficiency and accuracy in response to strong radiation, arc light, smoke, spatter and other interferences during the welding process.

[0155] Among them, in the steel structure welding quality assessment, environmental data refers to the data of various environmental factors that affect the welding quality and welding process during the welding process. This environmental data is crucial to ensure the welding quality because they can affect the selection of welding parameters and the stability of the welding process. This environmental data includes:

[0156] temperature:

[0157] Temperature in the welding area: affects the heat-affected zone of the material and the microstructure of the weld joint.

[0158] Ambient temperature: affects the storage and handling of welding materials, as well as the thermal expansion of materials during welding.

[0159] humidity:

[0160] Ambient humidity: May affect the surface condition of the welded materials, increasing the risk of oxidation and corrosion.

[0161] Wind speed and direction:

[0162] Affecting the airflow in the welding area may affect the stability of the welding process, such as the flow of shielding gas.

[0163] Air Pressure:

[0164] In some welding processes, such as gas shielded welding, changes in gas pressure can affect the flow of shielding gas and weld quality.

[0165] By monitoring and recording this environmental data, the welding process can be better controlled, welding parameters can be optimized, and welding quality can be improved. In the automated welding quality assessment process, this environmental data can be analyzed together with the welding image data to provide a more comprehensive welding quality assessment.

[0166] Finally, the comprehensive welding data of each construction stage is evaluated to generate the welding quality assessment value of each construction stage. The welding quality assessment value of each construction stage is multiplied by the corresponding inspection item weight to obtain the first sub-quality assessment value of the house steel structure project in each construction stage, which is used to evaluate the welding quality of the house steel structure project.

[0167] This embodiment can improve the accuracy of welding defect detection through image preprocessing and feature extraction, and at the same time provide a more comprehensive welding quality assessment by combining multimodal data fusion of welding images and environmental data. In addition, through the quantified welding quality assessment value, a reliable guarantee is provided for the engineering quality.

[0168] For example, suppose a steel structure project of a house is divided into foundation welding, main body welding and capping welding in different construction stages. In each construction stage, 100 welding images of the steel structure project of the house are extracted, and each welding image is denoised and binarized to obtain the target welding image. The connected areas and spots with an area less than 100 pixels in the target welding image are removed, and the weld centerline of the target welding image is extracted. The weld centerline is linearly fitted to obtain the feature point position of the target welding image, and 10 cracks, 5 pores and 2 unfused areas are identified. The welding defect features are fused with environmental data (such as temperature 25°C, humidity 60%, wind speed 5m / s) to form comprehensive welding data. The comprehensive welding data is evaluated, and the welding quality evaluation values ​​of each construction stage are 85, 88 and 90. Assuming that the weights of the detection items are 30%, 40%, and 30% respectively, the calculated sub-quality evaluation values ​​are: 85*30%=25.5, 88*40%=35.2, and 90*30%=27 respectively.

[0169] In one embodiment, the performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features includes:

[0170] Based on the characteristic point positions of the weld, local maximum value detection is performed on the target welding image to determine detection points of multiple potential welding defect areas;

[0171] According to the plurality of detection points and the watershed algorithm, different image regions in the target welding image are segmented and screened to obtain a plurality of segmented regions, each of which corresponds to a potential welding defect;

[0172] Welding defect detection is performed on each of the segmented areas to obtain welding defect features.

[0173] This embodiment can use the characteristic point positions of the weld to perform local maximum detection on the target welding image to determine the detection points of potential welding defect areas. The local maximum detection is an image analysis technique used to identify bright or dark areas in an image that may be indicative of welding defects.

[0174] Based on the detection points of multiple potential welding defect areas, the watershed algorithm is applied to segment and screen different image areas in the target welding image. The watershed algorithm is a segmentation method based on image morphology, which can separate different objects in the image, and each segmented area corresponds to a potential welding defect.

[0175] Detailed weld defect inspection is performed on each segmented area to identify weld defect characteristics such as cracks, pores or lack of fusion to accurately identify and classify defects.

[0176] This embodiment can more accurately locate and identify welding defects through local maximum detection and watershed algorithm, and can identify and classify various welding defects to provide a basis for subsequent maintenance and improvement.

[0177] For example, suppose that the weld quality of a steel structure project is being inspected. The project contains multiple welding points, and each welding point needs to be evaluated for quality. Through image processing technology, feature points are extracted from the welding image. These points may be the center line of the weld or other significant geometric features. Based on these feature points, the local maximum value detection is performed on the welding image, and the detection points of 5 potential welding defect areas are found. Based on the detection points of multiple potential welding defect areas, the watershed algorithm is used to segment the target welding image into multiple areas, each area corresponds to a potential welding defect, and a total of 5 segmented areas are obtained. A detailed analysis of these 5 segmented areas identifies that 3 areas have cracks, 1 area has pores, and 1 area has no obvious defects. According to the recognition results, the severity of the defects in each area is scored, and combined with the preset inspection item weights, the welding quality evaluation value of each construction stage is calculated, which is used to evaluate the welding quality of the steel structure project at each construction stage, so as to systematically evaluate the quality of each welding point in the steel structure project, timely discover and repair potential welding defects, and ensure the stability and safety of the entire structure.

[0178] In one embodiment, performing image preprocessing on the welding image to obtain a target welding image includes:

[0179] Performing median filtering on the welding image to obtain a first welding image;

[0180] Performing gradient detection on the first welding image to obtain a second welding image;

[0181] The second welding image is subjected to grayscale binarization processing to obtain a target welding image.

[0182] In this embodiment, the welding image may be first subjected to median filtering to obtain a first welding image. The median filtering method replaces the value of each pixel in the image with the median of its neighboring pixel values ​​to remove noise, especially salt and pepper noise, in the welding image while maintaining the edge characteristics of the image and improving the image quality.

[0183] Gradient detection can enhance the edge information in the image and prepare for subsequent image segmentation and feature extraction. Gradient detection can use Sobel or Canny operators to calculate image information such as the gradient amplitude and direction of the image. This image information can be used to highlight the edges in the image and facilitate subsequent image analysis.

[0184] Finally, the welding image is subjected to grayscale binarization to obtain the target welding image. The grayscale binarization process can convert the grayscale image into a binary image so as to more clearly distinguish the foreground and background. Among them, the grayscale binarization process divides the pixels in the image into foreground (above the threshold) and background (below the threshold) by selecting a threshold. The binarization process simplifies the image and makes the image processing algorithm more efficient.

[0185] In one embodiment, before performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain the welding defect feature, the method further includes:

[0186] Identify the edge of the weld in the target welding image according to an edge detection algorithm;

[0187] The edge of the weld in the target welding image is removed.

[0188] In this embodiment, an edge detection algorithm, such as the Canny operator, can be used to identify the edge of the weld in the target welding image. The edge detection algorithm can identify the image area where the pixel intensity changes dramatically in the image, which is usually the boundary of the object contour. The Canny operator identifies the edge of the image through steps such as Gaussian filtering, gradient calculation, non-maximum suppression and double threshold detection.

[0189] After identifying the weld edge of the image, the weld edge of the image can be removed by a morphological corrosion method so as to focus more on the features inside the weld, such as welding defects.

[0190] This embodiment can reduce false alarms and improve the accuracy of welding defect detection by removing edge noise of the target welding image; after removing the edge, the internal features of the weld, such as cracks, pores, etc., can be more accurately analyzed, thereby enhancing the reliability of image analysis, and can also simplify subsequent image processing and analysis processes and improve image processing efficiency.

[0191] Reference Figure 4 In an embodiment of the present application, a quality assessment device for a steel structure project of a house is also provided, the device comprising:

[0192] A construction module 11 is used to construct multiple inspection items of the housing steel structure project and determine the inspection item weight of each inspection item;

[0193] An acquisition module 12 is used to acquire the test data of each test item of the house steel structure project in different construction stages;

[0194] A calculation module 13 is used to calculate the sub-quality assessment value of the housing steel structure project at each construction stage according to the detection data of each detection item in different construction stages and the corresponding detection item weight;

[0195] The determination module 14 is used to determine the quality assessment weight of each construction stage when the sub-quality assessment values ​​of each construction stage meet the requirements, and obtain the comprehensive quality assessment value of the steel structure project of the house after weighted summing the sub-quality assessment values ​​of each construction stage and the corresponding quality assessment weight;

[0196] The output module 15 is used to output an evaluation result indicating that the quality of the steel structure project of the house is qualified when the comprehensive quality evaluation value is greater than a preset threshold.

[0197] As described above, it can be understood that the various components of the quality assessment device for the house steel structure project proposed in this application can realize the functions of any of the quality assessment methods for the house steel structure project described above, and the specific structure will not be repeated.

[0198] Reference Figure 5 In the embodiment of the present application, a terminal is also provided, whose internal structure can be as follows Figure 5 As shown. The terminal includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the computer-designed processor is used to provide computing and control capabilities. The memory of the terminal includes a storage medium and an internal memory. The storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the storage medium. The database of the terminal is used to store relevant data of the quality assessment method of the housing steel structure project. The network interface of the terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a quality assessment method for a housing steel structure project is implemented.

[0199] In one embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a quality assessment method for a steel structure project of a house is implemented.

[0200] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synch link) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0201] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0202] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A quality assessment method for a steel structure project of a house, characterized in that: include: Construct multiple inspection items for housing steel structure projects and determine the inspection item weight for each inspection item; Obtaining the inspection data of each inspection item of the housing steel structure project at different construction stages; According to the inspection data of each inspection item in different construction stages and the corresponding inspection item weight, the sub-quality assessment value of the housing steel structure project in each construction stage is calculated; When the sub-quality assessment values ​​of each construction stage meet the requirements, the quality assessment weight of each construction stage is determined, and the sub-quality assessment value of each construction stage is weighted and summed with the corresponding quality assessment weight to obtain the comprehensive quality assessment value of the housing steel structure project; When the comprehensive quality assessment value is greater than a preset threshold, an assessment result indicating that the quality of the housing steel structure project is qualified is output.

2. The method according to claim 1, characterized in that Determining the test item weight of each test item includes: Obtain historical project data for each test project; After data preprocessing of the historical project data of each detection project, the target historical project data of each detection project is obtained; According to the target historical project data of each inspection project, the influence of each inspection project on the engineering quality of the housing steel structure project is evaluated respectively; The corresponding detection item weight is determined according to the influence of each detection item, and the detection item weight is positively correlated with the influence.

3. The method according to claim 2, characterized in that After the historical project data of each detection project is preprocessed, the target historical project data of each detection project is obtained, including: The historical project data of each detection project are processed in sequence for missing values, outliers and data standardization to obtain target historical project data for each detection project.

4. The method according to claim 2, characterized in that: Determining the corresponding detection item weight according to the influence of each detection item includes: Set base weights; The influence of each detection item is multiplied by the basic weight to obtain the detection item weight corresponding to each detection item.

5. The method according to claim 1, characterized in that The quality assessment weights for each construction stage are determined as follows: Identify the completed works items in each construction phase; Calculate the proportion of the completed project in each construction stage to the total construction volume of the steel structure project, and obtain the proportion of the construction volume in each construction stage; Conduct risk assessments on completed projects at each construction stage and determine the risk factor for each construction stage; The quality assessment weight of each construction stage is obtained by multiplying the proportion of the engineering volume in each construction stage by the corresponding risk coefficient.

6. The method according to claim 1, characterized in that The sub-quality assessment value of the steel structure project at each construction stage is calculated based on the inspection data of each inspection item in different construction stages and the corresponding inspection item weight, including: For each construction stage, respectively extracting welding images of each inspection item, the inspection data including welding images of the housing steel structure project, and the inspection items including items for inspecting welding quality of the housing steel structure project; Performing image preprocessing on the welding image to obtain a target welding image; Removing connected regions and spots whose image area in the target welding image is lower than a preset value, so as to extract the center line of the weld in the target welding image; Performing linear fitting on the center line of the weld to obtain the position of the characteristic point of the weld; Performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features, wherein the welding defect features include cracks, pores or lack of fusion; The welding defect characteristics are fused with the pre-processed environmental data to form comprehensive welding data for each construction stage, wherein the environmental data refers to data of various environmental factors that affect welding quality and welding process during the welding process of the steel structure project of the house; Evaluate the comprehensive welding data at each construction stage to generate a welding quality evaluation value at each construction stage; After multiplying the welding quality assessment value of each construction stage with the corresponding inspection item weight, the first sub-quality assessment value of the house steel structure project at each construction stage is obtained, and the first sub-quality assessment value is used to evaluate the welding quality of the house steel structure project.

7. The method according to claim 6, characterized in that The performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features includes: Based on the characteristic point positions of the weld, local maximum value detection is performed on the target welding image to determine detection points of multiple potential welding defect areas; According to the plurality of detection points and the watershed algorithm, different image regions in the target welding image are segmented and screened to obtain a plurality of segmented regions, each of which corresponds to a potential welding defect; Welding defect detection is performed on each of the segmented areas to obtain welding defect features.

8. The method according to claim 6, characterized in that The performing image preprocessing on the welding image to obtain a target welding image includes: Performing median filtering on the welding image to obtain a first welding image; Performing gradient detection on the first welding image to obtain a second welding image; The second welding image is subjected to grayscale binarization processing to obtain a target welding image.

9. The method according to claim 6, characterized in that Before performing welding defect detection on the target welding image based on the characteristic point position of the weld to obtain welding defect features, the method further includes: Identify the edge of the weld in the target welding image according to an edge detection algorithm; The edge of the weld in the target welding image is removed.

10. A terminal, characterized in that: include: processor; Memory; Wherein, the memory stores a computer program, and when the processor executes the computer program, it implements the quality assessment method for the building steel structure project as described in any one of claims 1 to 9.

Images