Construction engineering management quality control system and risk management method

Abstract

The invention discloses a construction engineering management quality control system and a risk management method, and relates to the technical field of construction engineering management, and the key point of the scheme is that the system comprises a risk analysis module, an engineering environment monitoring module, an engineering quality detection module and a structure specification examination module. According to the method, dynamic management of project quality and risks is realized by analyzing construction project data and monitoring a project site in real time, the risk level of the construction project is accurately quantified through multi-factor risk assessment, and compared with a traditional method, potential risks can be identified in the early stage of the project, prevention measures can be taken, and the risk level of the construction project can be accurately evaluated. The potential risk occurrence rate is remarkably reduced, the transparency of the construction process is improved through integrated analysis of real-time videos and sensor data, project managers can monitor quality control points in real time, construction strategies are adjusted in time through immediate recognition and analysis of concrete surface defects, the construction process is optimized, and the construction efficiency is improved. And the overall safety and success rate of project management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction project management, and in particular to a construction project management quality control system and a risk management method. Background Art

[0002] Construction project management involves many aspects such as project management, quality control, risk assessment and handling. Its purpose is to ensure that construction projects can be carried out effectively and efficiently from planning, design to construction and maintenance stages. Construction project management uses various management theories and practical methods, such as schedule management, cost management and contract management, to optimize the resource allocation and workflow of construction projects.

[0003] Among them, the construction project management quality control system is specially designed for quality control and risk management in construction project management. Its main purpose is to improve the efficiency and effectiveness of construction project management through automated methods. It can help project managers monitor project progress in real time, identify and predict potential risk points, and ensure that projects meet all quality standards and regulatory requirements. It provides a comprehensive management solution for construction projects, thereby reducing the risk of failure and increasing the success rate of engineering projects.

[0004] Existing technologies rely on static data processing and periodic quality inspections, lack adaptability to dynamic changes in construction sites, and are difficult to respond to sudden quality problems or safety risks during construction. They show obvious limitations in dealing with complex and changeable construction projects, especially in fast-paced and high-risk engineering environments. Traditional technologies focus on post-analysis and lack predictive and preventive measures, resulting in certain losses or delays once problems are identified. Existing technologies are deficient in integrating and analyzing multi-source data in real time, resulting in incomplete risk assessment and quality control, and failing to cover all relevant risk factors in an all-round way, affecting the management efficiency of engineering projects and increasing project costs and the risk of failure. Summary of the invention

[0005] The invention provides a construction engineering management quality control system and a risk management method.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme:

[0007] A construction project management quality control system, the system comprising:

[0008] The risk analysis module analyzes the project location, scale and construction period based on the construction project data, calculates the weights of multiple factors, obtains the project risk weight table, performs interval analysis based on the project risk weight table, and determines the risk level of the construction project by comparing it with known engineering accidents, thus obtaining the project risk classification index;

[0009] The engineering environment monitoring module identifies key factors in high-risk areas based on the project risk classification indicators, simultaneously collects sensor data at the engineering site, performs deviation analysis on the sensor data, evaluates the current engineering site risks, and obtains engineering environment assessment results;

[0010] The engineering quality detection module screens high-risk areas based on the engineering environment assessment results, collects real-time video data of the area, analyzes the color difference, holes and texture abnormalities of the concrete surface, compares the construction quality standards based on the analysis results, calculates the quality deviation range, and marks the feature points of the key deviation areas to obtain quality abnormality analysis information;

[0011] The structural specification review module analyzes the deviation area based on the quality anomaly analysis information, compares the drawing design information of the target area with the current geometric features, analyzes the integrity of the building structure, and identifies the design elements that do not comply with the building specifications to obtain the identification results of the non-compliance items.

[0012] The present invention is improved in that the steps of obtaining the project risk weight table are specifically as follows:

[0013] Based on construction project data, collect data on construction project location, scale and construction period, analyze the potential impact of factors on project risks, and screen key risk factors to obtain a preliminary risk factor set;

[0014] Performing weighted processing on the preliminary risk factor set, correcting the weight of each factor, and obtaining a weighted risk factor set;

[0015] The weighted risk factor set is normalized using the formula:

[0016]

[0017] Calculate the standardized weight of each risk factor to obtain the project risk weight table, where W i represents the standardized weight of the ith risk factor, a i represents the weight of the ith risk factor obtained from the weighted risk factor set, n is the total number of risk factors, and e is the base of the natural logarithm.

[0018] The present invention is improved in that the steps of obtaining the project risk classification index are specifically as follows:

[0019] Based on the project risk weight table, according to industry safety standards and known engineering accident cases, each risk factor is classified into a risk level, and the weight of each factor is compared with the industry standard to obtain preliminary risk level data;

[0020] The preliminary risk level data is aggregated to calculate the risk level of each construction project using the formula:

[0021]

[0022] Get the project risk classification index, where R is the risk level of the project, W i represents the standardized weight of the ith risk factor, L i represents the risk level score of the ith risk factor, and n is the total number of risk factors.

[0023] The present invention is improved in that the step of performing deviation analysis on the sensor data is specifically as follows:

[0024] Based on the project risk classification indicators, key factors in high-risk areas are identified, and sensor data at the project site, including noise, dust, vibration and temperature data, are collected simultaneously to obtain real-time monitoring data sets;

[0025] The real-time monitoring data set is preliminarily screened to remove noise and outliers, and the formula is used:

[0026]

[0027] Calculate the deviation between the multi-sensor data and the normal operation data to obtain the deviation analysis results, where ΔSv represents the deviation value, Sv i represents the current reading of the i-th sensor, represents the historical average reading of the ith sensor, n S Represents the total number of sensors.

[0028] The present invention is improved in that the steps of obtaining the engineering environmental assessment results are specifically as follows:

[0029] Based on the deviation analysis results, the current engineering site is evaluated, the deviation of each sensor is associated with known accident cases, the potential risk of each area is evaluated, and preliminary risk assessment information is obtained;

[0030] The preliminary risk assessment information is analyzed, and high-risk areas requiring emergency monitoring or prevention are determined based on the criticality and deviation size of each sensor to obtain an engineering environment assessment result.

[0031] The present invention is improved in that the analysis steps of the abnormal characteristics of the concrete surface are specifically as follows:

[0032] Based on the project environment assessment results, high-risk areas are screened, and real-time video data of key areas are collected using monitoring equipment to obtain project area video data;

[0033] Based on the video data of the engineering area, the color difference, holes and texture anomalies of the concrete surface are automatically identified and segmented to obtain an identified abnormal feature image;

[0034] The identified abnormal feature image is quantitatively analyzed using the formula:

[0035]

[0036] Calculate the degree of variation of each abnormal feature and obtain the abnormal feature analysis results, where CK is the square mean of the deviation, Obs i Represents the abnormal characteristic value of the i-th monitored, Std i represents the i-th standard value, n K is the total number of feature points analyzed.

[0037] The present invention is improved in that the step of obtaining the quality abnormality analysis information is specifically as follows:

[0038] Based on the analysis results, each abnormal feature is compared with the construction quality standard, the features exceeding the standard are identified, and a list of exceeding the standard features is obtained;

[0039] Based on the list of excessive features, assess their impact on the safety and functionality of the building structure, determine the potential risk level of each abnormal feature, and obtain risk rating information;

[0040] Based on the risk rating information, key areas that require attention are marked with features, and corresponding repair or reinforcement measures are formulated to obtain quality anomaly analysis information.

[0041] The present invention is improved in that the steps for obtaining the identification result of the non-conforming items are specifically as follows:

[0042] Based on the quality anomaly analysis information, the deviation area is analyzed, and the measured geometric features are compared with the original building design information to obtain a data comparison result;

[0043] Based on the data comparison results, a structural integrity analysis was performed using the formula:

[0044]

[0045] Calculate the stress value of each area, evaluate its impact on the structural integrity, and obtain the integrity assessment result, where FT i represents the design load of the ith region, AT i represents the load acting area, Tk is the safety factor, and Tδ represents the additional load factor obtained from the environmental data;

[0046] Based on the integrity assessment results, design elements that do not conform to building codes are identified to obtain code non-compliance identification results.

[0047] A construction project management risk management method comprises the following steps:

[0048] S1: Based on the construction project data, the project location, scale and construction period are analyzed, the weights of multiple factors are calculated, and interval analysis is performed. By comparing with known engineering accidents, the risk level of the construction project is determined and the project risk classification index is obtained;

[0049] S2: Based on the project risk classification indicators, identify key factors in high-risk areas, simultaneously collect sensor data at the engineering site, perform deviation analysis on the sensor data, evaluate the current engineering site risks, and obtain engineering environment assessment results;

[0050] S3: Based on the project environment assessment results, real-time video data of the area is collected to analyze the color difference, holes and abnormal texture characteristics of the concrete surface, and the construction quality standards are compared according to the analysis results to calculate the quality deviation range and obtain quality abnormality analysis information;

[0051] S4: Based on the quality anomaly analysis information, the drawing design information of the target area is compared with the current geometric features, the integrity of the building structure is analyzed, and the design elements that do not comply with the building specifications are identified to obtain the specification non-compliance identification results.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are:

[0053] In the present invention, by analyzing the construction project data and monitoring the construction site in real time, dynamic management of project quality and risk is achieved. Through multi-factor risk assessment, the risk level of the construction project is accurately quantified. Compared with traditional methods, potential risks can be identified and preventive measures can be taken in the early stages of the project, significantly reducing the potential risk incidence rate. The integrated analysis of real-time video and sensor data improves the transparency of the construction process, enabling project managers to monitor quality control points in real time and respond quickly to potential quality deviations. Through the instant identification and analysis of concrete surface defects, construction strategies are adjusted in time, the construction process is optimized, the building quality is improved, and it is ensured that the project meets all regulatory requirements, thereby improving the overall safety and success rate of project management. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. The drawings are only used to illustrate the implementation methods and are not to be considered as limitations of the present invention.

[0055] Figure 1 is a system module diagram in an embodiment of the present invention;

[0056] Figure 2 A flowchart of obtaining a project risk weight table in an embodiment of the present invention;

[0057] Figure 3 This is a flowchart for obtaining project risk classification indicators in an embodiment of the present invention;

[0058] Figure 4 This is a flow chart of performing deviation analysis on sensor data in an embodiment of the present invention;

[0059] Figure 5 is a flowchart for obtaining the engineering environment assessment results in an embodiment of the present invention;

[0060] Figure 6 is a flow chart for analyzing abnormal characteristics of a concrete surface in an embodiment of the present invention;

[0061] Figure 7 A flowchart of obtaining quality abnormality analysis information in an embodiment of the present invention;

[0062] Figure 8 The present invention is a flowchart for obtaining standardized incompatible item recognition results in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by technicians in the field of the present invention; the terms used in the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings, and are intended to cover non-exclusive inclusions.

[0065] In the description of the embodiments of the present invention, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present invention, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0066] In the description of the embodiments of the present invention, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0067] In the description of the embodiments of the present invention, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0068] In the description of the embodiments of the present invention, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the embodiments of the present invention.

[0069] In the description of the embodiments of the present invention, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to the specific circumstances.

[0070] Example

[0071] The embodiment of the present invention provides a construction project management quality control system, such as Figure 1 As shown, including:

[0072] The risk analysis module analyzes the project location, scale and construction period based on the construction project data, calculates the weights of multiple factors, obtains the project risk weight table, performs interval analysis based on the project risk weight table, and determines the risk level of the construction project by comparing it with known engineering accidents, thus obtaining the project risk classification index;

[0073] The engineering environment monitoring module identifies key factors in high-risk areas based on project risk classification indicators, simultaneously collects sensor data at the engineering site, and performs deviation analysis on the sensor data to assess the current engineering site risks and obtain engineering environment assessment results;

[0074] The project quality inspection module screens high-risk areas based on the project environment assessment results, collects real-time video data of the area, analyzes the color difference, holes and texture abnormalities of the concrete surface, compares the construction quality standards based on the analysis results, calculates the quality deviation range, and marks the feature points of the key deviation areas to obtain quality abnormality analysis information;

[0075] The structural specification review module analyzes the deviation area based on the quality anomaly analysis information, compares the drawing design information of the target area with the current geometric features, analyzes the integrity of the building structure, and identifies the design elements that do not comply with the building specifications to obtain the identification results of non-compliance items.

[0076] Project risk grading indicators include risk level determination, correlation factor weights, and risk interval division results. Engineering environmental assessment results include environmental deviation values, risk identification accuracy, and real-time monitoring data. Quality anomaly analysis information includes defect type, defect degree, and defect location. Specification non-compliance identification results include non-compliant design elements, structural integrity issues, and specification deviation analysis results.

[0077] like Figure 2 As shown in the figure, the specific steps for obtaining the project risk weight table are:

[0078] Based on construction project data, collect data on construction project location, scale and construction period, analyze the potential impact of factors on project risks, and screen key risk factors to obtain a preliminary risk factor set;

[0079] First, obtain the geographic information of the construction project site, including terrain conditions, meteorological environment, soil characteristics, etc. Use remote sensing measurement technology and geographic information systems to collect data from relevant public resources and field surveys. At the same time, analyze the project scale and extract key data such as building area, number of floors, and construction technical requirements through project planning documents. The construction period data is based on the project schedule, combined with historical construction cycle records, and quantified from the perspective of time arrangement and seasonal impact. After all data are initially collected, they need to go through data verification and cleaning processes to remove duplicate values ​​and outliers. Then, use normalization processing to uniformly quantify each data type to ensure that different types of data have consistent measurement standards and obtain a preliminary data set for subsequent analysis.

[0080] Perform weighted processing on the preliminary risk factor set, correct the weight of each factor, and obtain a weighted risk factor set;

[0081] When weighting the preliminary risk factor set, first determine the initial value of the weighted factor, calculate the influence of each factor by analyzing the frequency of occurrence of relevant factors in historical building projects and their impact on project accidents, and adjust their rationality based on historical risk assessment reports. Further correct the weight distribution of key factors, repeat the scoring multiple times and take the average value to improve accuracy. Then combine the corrected results with the historical calculated factor influence, and use the weighted formula to re-quantify the importance of each factor to generate a weighted risk factor set containing multiple key factor weights.

[0082] The weighted risk factor set is normalized using the formula:

[0083]

[0084] Calculate the standardized weight of each risk factor to obtain the project risk weight table, where W i represents the standardized weight of the ith risk factor, a i represents the weight of the ith risk factor obtained from the weighted risk factor set, n is the total number of risk factors, and e is the base of the natural logarithm;

[0085] There are three risk factors with weights of a1=0.5, a2=0.3 and a3=0.2. Substitute them into the formula for calculation:

[0086] e 0.5 ≈1.648;

[0087] e 0.3 ≈1.349;

[0088] e 0.2 ≈1.221;

[0089] The exponential sum of the factor weights is:

[0090] 1.648+1.349+1.221=4.218;

[0091] Therefore, the standardized weight of each risk factor is calculated as:

[0092]

[0093] The result shows that the first risk factor has the greatest impact on the overall risk of the project and has the highest standardized weight. This result is closely related to the step results, indicating that through standardized processing, the risk factors that have the greatest impact on the project can be effectively identified and emphasized, thereby guiding the formulation of project management and risk control measures.

[0094] like Figure 3 As shown in the figure, the specific steps for obtaining project risk classification indicators are as follows:

[0095] Based on the project risk weight table, industry safety standards and known engineering accident cases, each risk factor is classified into risk levels, and the weight of each factor is compared with the industry standard to obtain preliminary risk level data;

[0096] Collect a large amount of data on the location, scale and construction period of the construction project. The data is obtained through the construction project database and the historical accident record library. After the data is collected, the information is preliminarily screened and sorted to screen out the key risk factors related to safety standards. For example, for location data, factors such as geological stability and the frequency of historical disasters will be taken into account. Scale data includes building height, floor area, etc. The construction period needs to pay attention to information such as construction season and estimated construction duration. Then, according to industry safety standards and known engineering accident cases, the factors are deeply analyzed, and statistical tools such as SPSS or R language are used to calculate the risk coefficient of each factor. The coefficient will be compared with the industry standard to ensure the accuracy and practicality of the analysis results, and the weight of each risk factor will be obtained. The weight will directly affect the risk assessment of the project and form preliminary risk level data.

[0097] Aggregate the preliminary risk level data and calculate the risk level of each construction project to ensure that each risk level reflects its actual impact on the overall project safety, using the formula:

[0098]

[0099] Get the project risk classification index, where R is the risk level of the project, W i represents the standardized weight of the ith risk factor, L i represents the risk level score of the ith risk factor. The score is based on the potential impact of the risk factor and industry standards, including low risk (1 point), medium risk (2 points), high risk (3 points), etc. n is the total number of risk factors;

[0100] A project has three risk factors, where W1=0.4, W2=0.35, and W3=0.25. The corresponding risk level scores are L1=3, L2=2, and L3=1. Calculate the total risk level of the project:

[0101] R=(0.4×3)+(0.35×2)+(0.25×1);

[0102] R = 1.2 + 0.7 + 0.25 = 2.15;

[0103] The result shows that after comprehensively considering the weights of various factors and the potential risk impact, the project's risk level is 2.15, indicating that the project has an overall risk level of medium to high, which helps to determine the priority and intensity of risk mitigation measures that need to be taken.

[0104] like Figure 4 As shown in the figure, the steps for performing deviation analysis on sensor data are as follows:

[0105] Based on the project risk classification indicators, key factors in high-risk areas are identified, and sensor data at the project site, including noise, dust, vibration and temperature data, are collected simultaneously to obtain real-time monitoring data sets;

[0106] Key factors in high-risk areas are identified, including noise, dust, vibration and temperature data. By arranging different types of sensors in high-risk areas, noise data is collected by sound level meter sensors, recording decibel values ​​per minute, dust data is collected by light scattering particle sensors (such as PM2.5 and PM10 sensors), recording particle concentration values, vibration data is collected by accelerometer sensors, recording vibration frequency and amplitude parameters, temperature data is collected by thermistor sensors, recording real-time ambient temperature readings. Sensors automatically record data at intervals of 5 minutes and transmit them to the central data processing system via a wireless network. In the system, noise, dust, vibration and temperature data are formatted separately, including processing steps such as unit conversion, timestamp alignment and numerical accuracy correction. The cleaned data are stored in the corresponding data fields of noise, dust, vibration and temperature according to their types, ensuring real-time updating and unified management of all high-risk factor data.

[0107] The real-time monitoring data set is initially screened to remove noise and outliers, and the formula is used:

[0108]

[0109] Calculate the deviation between multi-sensor data and normal operation data to obtain the deviation analysis results, where ΔSv represents the deviation value, which is used to measure the difference between the current readings of all sensors and the historical average value, Sv i Represents the current reading of the i-th sensor, which is the data value collected in real time. represents the historical average reading of the ith sensor, based on the average value of long-term data collection, n S Represents the total number of sensors;

[0110] There are 5 sensors, the current reading Sv is measured i They are [100, 102, 98, 105, 103] respectively, the historical average readings They are [95, 100, 95, 100, 98] respectively, and the total number of sensors n S is 5, calculate the deviation of each sensor

[0111] 100-95=5;

[0112] 102-100=2;

[0113] 98-95=3;

[0114] 105-100=5;

[0115] 103-98=5;

[0116] Sum of deviations

[0117] 5+2+3+5+5=20;

[0118] Mean Deviation:

[0119]

[0120] The result shows that the average reading of each sensor is 4 higher than its historical average, reflecting that there are certain changes or deviations from the normal state in the engineering environment.

[0121] like Figure 5 As shown in the figure, the specific steps for obtaining the project environmental assessment results are:

[0122] Based on the deviation analysis results, the current engineering site is evaluated, the deviation of each sensor is associated with known accident cases, the potential risk of each area is evaluated, and preliminary risk assessment information is obtained;

[0123] Specific data in the deviation analysis report generated by the sensor is extracted, including the deviation values ​​of noise, dust, vibration and temperature in each area, and known accident case data is called from historical data. The sensor deviation value is compared with the deviation value under corresponding conditions in the historical case one by one to evaluate whether the deviation value exceeds the range of historical high-risk accidents. The deviation value is classified and marked by setting the partition threshold range, and then the potential risk of each area is quantitatively scored. According to the scoring results, a preliminary risk data set for each area is generated. This data set includes the risk level of each partition, the deviation factor weight and other related information, and finally the preliminary risk assessment information is obtained.

[0124] Analyze the preliminary risk assessment information, identify high-risk areas that require emergency monitoring or prevention based on the criticality and deviation size of each sensor, and obtain the engineering environment assessment results;

[0125] Analyze the preliminary risk assessment information, extract the risk level and sensor deviation factor weight data of each area, identify the key sensors in areas with higher deviation factor weights, associate high-weight areas with high deviation areas, and screen out high-risk areas that require key monitoring. Through comprehensive analysis of the historical deviation weights and current real-time deviation values ​​of each sensor, classify and identify areas that require emergency monitoring, mark regional priorities, and ultimately form a detailed list of high-risk areas as the main output of the engineering environmental assessment results.

[0126] like Figure 6As shown in the figure, the specific steps for analyzing the abnormal characteristics of the concrete surface are:

[0127] Based on the results of the project environment assessment, high-risk areas are screened, and real-time video data of key areas are collected using monitoring equipment to obtain video data of the project area;

[0128] The engineering area is divided into multiple sub-areas, and the areas are sorted according to the risk level. High-risk level areas are selected as key areas. Combined with the attribute information of the area and the data of historical risk events, an index library related to the high-risk area is established. By calling the index library, the locations where monitoring equipment needs to be deployed are associated, the specific installation location of the equipment and its monitoring range are clarified, and the relevant parameters of the monitoring equipment are set according to the characteristics of the high-risk area, including equipment resolution, shooting range and camera angle. A real-time data transmission protocol is set for each monitoring device, and the monitoring equipment is installed in a distributed manner. The real-time video data collected by the equipment is uploaded to the video processing center according to the transmission protocol. The data is divided into blocks in the video processing center, and the time window for segmented collection is set according to the video frame rate to ensure the integrity and continuity of the data, and finally obtain real-time engineering area video data covering the high-risk area.

[0129] Based on the video data of the engineering area, the color difference, holes and texture anomalies on the concrete surface are automatically identified and segmented to obtain the identified abnormal feature images;

[0130] First, the video data is subjected to frame extraction operation, and each frame of the image is grayed and the noise information in the image is removed at the same time to retain effective features. The significant edge features in the image are extracted by the edge detection algorithm, and the threshold range of the edge detection is set to filter out interference information. For the concrete surface area, the pixel difference analysis method is applied to identify the color difference area by comparing the brightness value difference of adjacent pixels in the image, and the pixels exceeding the set difference threshold are screened out. The pixels are grouped by the clustering algorithm to generate the contour of the color difference area. Subsequently, the hole detection algorithm based on contour tracking is used to identify the hole area in the segmented area, and the texture direction characteristics in the area are further analyzed. By statistically analyzing the distribution characteristics of the texture direction, the abnormal texture area is identified, and the feature extraction of the color difference, holes and texture anomalies on the concrete surface is completed, and finally the segmented and identified abnormal feature image is obtained;

[0131] The identified abnormal feature images are quantitatively analyzed using the formula:

[0132]

[0133] Calculate the variation degree of each abnormal feature and obtain the abnormal feature analysis results, where CK is the square mean of the deviation, which is used to quantify the quality deviation degree of the concrete surface, and Obsi represents the ith abnormal feature value monitored, which is obtained from the image processing algorithm in the video data and reflects the color difference, holes or texture abnormalities of the concrete surface actually monitored. i represents the i-th standard value, n K is the total number of feature points analyzed;

[0134] Five key feature points were identified in the analysis, and the observed abnormal feature values ​​Obs i They are [10, 12, 8, 15, 11] respectively, and the corresponding standard values ​​Std i They are [8, 8, 8, 8, 8] respectively, and the total number of feature points n K is 5, and the square difference of each feature point is calculated:

[0135] Obs1-Std1=(10-8) 2 =4;

[0136] Obs2-Std2=(12-8) 2 =16;

[0137] Obs3-Std3=(8-8) 2 =0;

[0138] Obs4-Std4=(15-8) 2 =49;

[0139] Obs5-Std5=(11-8) 2 =9;

[0140] Sum of squared differences:

[0141] 4+16+0+49+9=78;

[0142] Squared mean deviation:

[0143]

[0144] The results show that there is a significant difference between the observed value and the standard value of each feature point, indicating that there are many quality problems on the concrete surface and further quality control measures are needed.

[0145] like Figure 7 As shown, the steps for obtaining quality abnormality analysis information are as follows:

[0146] Based on the analysis results, each abnormal feature is compared with the construction quality standard, the features exceeding the standard are identified, and a list of features exceeding the standard is obtained;

[0147] Each abnormal feature is compared with the construction quality standard one by one, and the specific detection parameters and threshold information in the quality standard are extracted, including surface flatness, allowable range of color difference, hole area and texture distribution deviation, etc. Gradual calculation is performed according to the specific information extracted from the abnormal feature, and the relevant attribute data of each feature is input into the comparison program. It is determined whether it exceeds the standard range by setting rules. During the comparison process, the color difference feature is compared with the maximum difference value allowed in the standard pixel by pixel, the hole area is compared with the standard threshold range, and the texture deviation is calculated according to the regional distribution density and checked item by item with the standard deviation value. The features that exceed the quality standard are screened out through the judgment results of multiple features and recorded in a list. The list contains the type, location, corresponding exceeded attribute and specific numerical information of deviation from the standard of the abnormal feature, and a list of exceeded features is obtained.

[0148] Based on the list of exceeded features, evaluate their impact on the safety and functionality of the building structure, determine the potential risk level of each abnormal feature, and obtain risk rating information;

[0149] Combined with the construction design specifications and building structure performance parameters, the impact of each exceeding standard feature on the safety and functionality of the building structure is evaluated, and the basic information required for the impact assessment is extracted, including the location, area, degree of deviation and scope of influence of the abnormal features. The exceeding standard features are classified according to type and degree of influence, and the threat to the structural stability is judged by calculating the force influence value of the exceeding standard feature. The potential impact on the functional area is analyzed based on the location data of the feature, and the risk level of each abnormal feature is comprehensively calculated. The risk level is divided into low, medium and high levels according to preset classification rules to form risk rating information.

[0150] Based on the risk rating information, key areas that need attention are marked with features, and corresponding repair or reinforcement measures are formulated to obtain quality anomaly analysis information;

[0151] Mark the key areas that need attention as priority treatment objects. First, determine the scope of the area that needs to be reinforced or repaired based on the location data of high-risk level characteristics. Formulate repair or reinforcement measures based on the specific manifestations of risk characteristics. For abnormal color differences on the concrete surface, set surface treatment measure parameters, including cleaning range, type of repair material, and construction tool specifications. For excessive hole characteristics, formulate filling materials and operating procedures based on hole size and distribution. For abnormal texture characteristics, use re-coating or local polishing to repair. After the repair is completed, mark the reinforced area and record the treatment information. Organize the repair measures and treatment results of each key area into quality abnormality analysis information.

[0152] like Figure 8 As shown in the figure, the specific steps for obtaining the results of identifying items that do not conform to the standard are:

[0153] Based on the quality anomaly analysis information, the deviation area is analyzed, and the measured geometric features are compared with the original building design information to obtain the data comparison results;

[0154] Screen out areas with significant deviations, measure the geometric features of the areas using high-precision on-site measuring equipment, obtain the specific geometric parameters of each deviation area, including size, angle and position, compare the measured parameters with the original parameters in the architectural design drawings point by point, use difference calculation to identify the specific degree of deviation, mark the key differences in each area based on the comparison results, and organize the comparison results into a structured output file for subsequent analysis.

[0155] Based on the data comparison results, the structural integrity analysis is carried out using the formula:

[0156]

[0157] Calculate the stress value of each area, evaluate its impact on the structural integrity, and obtain the integrity assessment result, where FT i represents the design load of the ith area, which is the load value preset according to the building design specifications and expected use conditions. i It represents the load action area, that is, the specific area size of the design load action, Tk is the safety factor, and Tδ represents the additional load factor obtained from environmental data, including additional loads caused by geological factors;

[0158] If the design load FT of the i-th deviation area i is 5000N, load acting area AT i It is 20㎡, the safety factor Tk is 1.5, and the additional load factor Tδ is 200N / ㎡.

[0159] Calculate the design load stress part:

[0160]

[0161] Calculate the additional load part:

[0162] Tk·Tδ=1.5·200=300;

[0163] Total stress value:

[0164] Stress i =250+300=550;

[0165] The results show that the actual stress value of the ith area is 550 N / ㎡, which can be further evaluated for its safety when compared with the bearing capacity of building materials and specification requirements.

[0166] Based on the integrity assessment results, the design elements that do not comply with the building code are identified, and the results of the non-compliance with the code are obtained;

[0167] Based on the integrity assessment results, analyze whether each deviation area complies with the building code, compare the actual stress value of the deviation area with the bearing standard in the building code item by item, mark the exceedance of the code bearing threshold for each area, and calculate the potential risk of the exceeded area to the overall structure. Classify all identified non-conformities according to the code requirements, mark the key areas that need further processing, and form a comprehensive risk assessment list.

[0168] A construction project management risk management method comprises the following steps:

[0169] S1: Based on the construction project data, the project location, scale and construction period are analyzed, the weights of multiple factors are calculated, and interval analysis is performed. By comparing with known engineering accidents, the risk level of the construction project is determined and the project risk classification index is obtained;

[0170] S2: Based on the project risk classification indicators, identify the key factors of high-risk areas, simultaneously collect sensor data at the project site, and perform deviation analysis on the sensor data to assess the current project site risks and obtain the project environment assessment results;

[0171] S3: Based on the results of the project environment assessment, real-time video data of the area is collected to analyze the color difference, holes and abnormal texture characteristics of the concrete surface. Based on the analysis results, the construction quality standards are compared, the quality deviation range is calculated, and the quality abnormality analysis information is obtained;

[0172] S4: Based on the quality anomaly analysis information, the drawing design information of the target area is compared with the current geometric features to analyze the integrity of the building structure, and the design elements that do not comply with the building regulations are identified to obtain the identification results of non-compliance with regulations.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention. In particular, as long as there is no structural conflict, the various technical features mentioned in each embodiment can be combined in any way. The present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A construction project management quality control system, characterized in that: The system comprises: The risk analysis module analyzes the project location, scale and construction period based on the construction project data, calculates the weights of multiple factors, obtains the project risk weight table, performs interval analysis based on the project risk weight table, and determines the risk level of the construction project by comparing it with known engineering accidents, thus obtaining the project risk classification index; The engineering environment monitoring module identifies key factors in high-risk areas based on the project risk classification indicators, simultaneously collects sensor data at the engineering site, performs deviation analysis on the sensor data, evaluates the current engineering site risks, and obtains engineering environment assessment results; The engineering quality detection module screens high-risk areas based on the engineering environment assessment results, collects real-time video data of the area, analyzes the color difference, holes and texture abnormalities of the concrete surface, compares the construction quality standards based on the analysis results, calculates the quality deviation range, and marks the feature points of the key deviation areas to obtain quality abnormality analysis information; The structural specification review module analyzes the deviation area based on the quality anomaly analysis information, compares the drawing design information of the target area with the current geometric features, analyzes the integrity of the building structure, and identifies the design elements that do not comply with the building specifications to obtain the identification results of the non-compliance items.

2. The construction project management quality control system according to claim 1 is characterized in that: The specific steps for obtaining the project risk weight table are: Based on construction project data, collect data on construction project location, scale and construction period, analyze the potential impact of factors on project risks, and screen key risk factors to obtain a preliminary risk factor set; Performing weighted processing on the preliminary risk factor set, correcting the weight of each factor, and obtaining a weighted risk factor set; The weighted risk factor set is normalized using the formula: Calculate the standardized weight of each risk factor to obtain the project risk weight table, where W i represents the standardized weight of the ith risk factor, a i represents the weight of the ith risk factor obtained from the weighted risk factor set, n is the total number of risk factors, and e is the base of the natural logarithm.

3. The construction project management quality control system according to claim 1 is characterized in that: The specific steps for obtaining the project risk classification indicators are as follows: Based on the project risk weight table, according to industry safety standards and known engineering accident cases, each risk factor is classified into a risk level, and the weight of each factor is compared with the industry standard to obtain preliminary risk level data; The preliminary risk level data is aggregated to calculate the risk level of each construction project using the formula: Get the project risk classification index, where R is the risk level of the project, W i represents the standardized weight of the ith risk factor, L i represents the risk level score of the ith risk factor, and n is the total number of risk factors.

4. The construction project management quality control system according to claim 1, characterized in that: The steps of performing deviation analysis on sensor data are specifically as follows: Based on the project risk classification indicators, key factors in high-risk areas are identified, and sensor data at the project site, including noise, dust, vibration and temperature data, are collected simultaneously to obtain real-time monitoring data sets; The real-time monitoring data set is preliminarily screened to remove noise and outliers, and the formula is used: Calculate the deviation between the multi-sensor data and the normal operation data to obtain the deviation analysis results, where ΔSv represents the deviation value, Sv i represents the current reading of the i-th sensor, represents the historical average reading of the ith sensor, n S Represents the total number of sensors.

5. The construction project management quality control system according to claim 1, characterized in that: The specific steps for obtaining the project environmental assessment results are: Based on the deviation analysis results, the current engineering site is evaluated, the deviation of each sensor is associated with known accident cases, the potential risk of each area is evaluated, and preliminary risk assessment information is obtained; The preliminary risk assessment information is analyzed, and high-risk areas requiring emergency monitoring or prevention are determined based on the criticality and deviation size of each sensor to obtain an engineering environment assessment result.

6. The construction project management quality control system according to claim 1, characterized in that: The analysis steps of the abnormal characteristics of the concrete surface are specifically as follows: Based on the project environment assessment results, high-risk areas are screened, and real-time video data of key areas are collected using monitoring equipment to obtain project area video data; Based on the video data of the engineering area, the color difference, holes and texture anomalies of the concrete surface are automatically identified and segmented to obtain an identified abnormal feature image; The identified abnormal feature image is quantitatively analyzed using the formula: Calculate the degree of variation of each abnormal feature and obtain the abnormal feature analysis results, where CK is the square mean of the deviation, Obs i Represents the abnormal characteristic value of the i-th monitored, Std i represents the i-th standard value, n K is the total number of feature points analyzed.

7. The construction project management quality control system according to claim 1, characterized in that: The steps for obtaining the quality abnormality analysis information are specifically as follows: Based on the analysis results, each abnormal feature is compared with the construction quality standard, the features exceeding the standard are identified, and a list of exceeding the standard features is obtained; Based on the list of excessive features, assess their impact on the safety and functionality of the building structure, determine the potential risk level of each abnormal feature, and obtain risk rating information; Based on the risk rating information, key areas that require attention are marked with features, and corresponding repair or reinforcement measures are formulated to obtain quality anomaly analysis information.

8. The construction project management quality control system according to claim 1, characterized in that: The specific steps for obtaining the results of identifying items that do not conform to the specification are: Based on the quality anomaly analysis information, the deviation area is analyzed, and the measured geometric features are compared with the original building design information to obtain a data comparison result; Based on the data comparison results, a structural integrity analysis was performed using the formula: Calculate the stress value of each area, evaluate its impact on the structural integrity, and obtain the integrity assessment result, where FT i represents the design load of the ith region, AT i represents the load acting area, Tk is the safety factor, and Tδ represents the additional load factor obtained from the environmental data; Based on the integrity assessment results, design elements that do not conform to building codes are identified to obtain code non-compliance identification results.

9. A construction project management risk management method, characterized in that: The construction project management quality control system according to any one of claims 1 to 8 comprises the following steps: S1: Based on the construction project data, the project location, scale and construction period are analyzed, the weights of multiple factors are calculated, and interval analysis is performed. By comparing with known engineering accidents, the risk level of the construction project is determined and the project risk classification index is obtained; S2: Based on the project risk classification indicators, identify key factors in high-risk areas, simultaneously collect sensor data at the engineering site, perform deviation analysis on the sensor data, evaluate the current engineering site risks, and obtain engineering environment assessment results; S3: Based on the project environment assessment results, real-time video data of the area is collected, the color difference, holes and abnormal texture characteristics of the concrete surface are analyzed, the construction quality standards are compared according to the analysis results, the quality deviation range is calculated, and the quality abnormality analysis information is obtained; S4: Based on the quality anomaly analysis information, the drawing design information of the target area is compared with the current geometric features, the integrity of the building structure is analyzed, and the design elements that do not comply with the building specifications are identified to obtain the specification non-compliance identification results.

Images