Construction engineering quality monitoring information management method and system

Abstract

The invention relates to the technical field of constructional engineering quality monitoring, and discloses a constructional engineering quality monitoring information management method and system. The method comprises the steps of obtaining structural design parameters, real-time monitoring data and multi-source sensor data of constructional engineering; the method comprises the following steps: preprocessing multi-source sensor data, constructing a three-dimensional digital structure model, performing dynamic mechanical analysis to obtain an initial structure analysis model, and applying a load condition to obtain a comprehensive structure analysis model and dynamic coupling evaluation data; constructing and training a defect identification model to obtain initial defect parameters, and further obtaining defect evolution simulation information; constructing an optimization model to optimize monitoring equipment parameters; and adjusting the actual optimal monitoring parameters based on the risk assessment model to control the quality monitoring of the constructional engineering. According to the invention, data quality can be improved, building mechanical properties can be accurately simulated, defects can be accurately identified, monitoring equipment parameters can be optimized, and building engineering quality can be effectively monitored and controlled.

Description

Technical Field

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

[0002] As the construction industry continues to boom, the scale and complexity of construction projects are increasing, making quality monitoring increasingly important. Traditional methods of quality monitoring have numerous drawbacks and are no longer able to meet the stringent requirements of modern construction projects.

[0003] From a data acquisition perspective, the data obtained by traditional methods is often one-sided and simplistic. In the past, data collection relied heavily on manual on-site spot checks, relying on experience and simple tools. This method is inefficient and limited in scope, and it is unable to obtain comprehensive information about the building's overall structure. For example, in large and complex buildings, it is difficult for manual labor to conduct comprehensive inspections of hidden structures and high-altitude areas, and critical quality issues can be easily missed. Furthermore, the accuracy and timeliness of traditional monitoring data are also relatively poor. Manual measurements are easily influenced by subjective factors, and differences in the operating habits and skill levels of different surveyors can lead to data deviations. Furthermore, the data collection cycle is long, and the process from collection to feedback is cumbersome. As a result, the acquired data may lag behind the actual project situation during the transmission process, making it difficult to detect and address sudden quality issues in a timely manner.

[0004] Traditional methods also have significant shortcomings in model construction and analysis. Building models constructed in the past were mostly static and simple, unable to reflect the true mechanical properties of buildings subjected to multiple complex loads during actual use. For example, taking natural disasters such as earthquakes and strong winds, as well as dynamic loads during construction, traditional models struggle to simulate the impact of these loads on building structures and cannot accurately assess their stability and safety. Furthermore, traditional models lack the ability to integrate multi-source data and are unable to fully utilize the various sensor data in construction projects. This results in significant deviations between model analysis results and actual conditions, making them difficult to use as a basis for accurately judging building quality.

[0005] The limitations of traditional methods are even more pronounced when it comes to defect identification and risk assessment. Traditional defect identification relies primarily on manual visual inspection and simple non-destructive testing techniques, which are less capable of identifying hidden and minor internal defects. Problems such as corroded steel bars within building structures and cracks within concrete are difficult to detect manually, and simple non-destructive testing techniques may miss them due to insufficient precision. Regarding risk assessment, traditional methods are largely based on experience and simple indicators, lacking scientific quantitative analysis. This makes it difficult to accurately predict risks at different stages of a building's use, making it difficult to take effective preventative measures in advance.

[0006] Furthermore, traditional monitoring equipment parameter settings are often fixed and cannot be dynamically adjusted based on the actual conditions of the construction project. Under different construction phases and environmental conditions, fixed monitoring parameters may not meet monitoring needs, affecting the quality and effectiveness of monitoring data. This wastes resources and fails to achieve good monitoring results. In summary, traditional construction project quality monitoring methods have many problems in data acquisition, model building and analysis, defect identification, risk assessment, and monitoring equipment parameter optimization. There is an urgent need for a more advanced and efficient construction project quality monitoring information management method and system to ensure the quality and safety of construction projects. Summary of the Invention

[0007] The purpose of the present invention is to provide a construction project quality monitoring information management method and system to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: a method for managing construction project quality monitoring information, the method comprising:

[0009] Obtain structural design parameters and real-time monitoring data of construction projects;

[0010] Acquire and pre-process multi-source sensor data of the construction project to construct a 3D digital structural model. Perform dynamic mechanical analysis on the 3D digital structural model and combine it with structural design parameters to obtain an initial structural analysis model of the construction project.

[0011] Apply environmental load conditions and construction load conditions to the initial structural analysis model to obtain a comprehensive structural analysis model, and combine it with the structural design parameters to obtain dynamic coupling evaluation data;

[0012] Construct a defect recognition pre-training model and train it through dynamic coupling evaluation data to obtain a defect recognition model and then obtain the initial defect parameters;

[0013] Through the initial defect parameters, comprehensive structural analysis model and structural design parameters, defect evolution simulation information is obtained;

[0014] Based on the defect evolution simulation information and monitoring equipment parameters, an optimization model is constructed and the monitoring equipment parameters are optimized to obtain the optimal monitoring parameters of the monitoring equipment;

[0015] Based on the risk assessment model, the monitoring parameters of the current period are inferred to obtain the risk assessment prediction value of the current period. Based on the risk assessment prediction value of the current period, the optimal monitoring parameters of the current period and the monitoring parameters of the current period, the actual optimal monitoring parameters of the current period are adjusted to achieve control of the quality monitoring of the construction project.

[0016] Preferably, the dynamic coupling evaluation data includes at least the final displacement field, the final strain field and the high-risk area location set; the initial defect parameters include at least the initial defect position, the initial defect type and the initial defect morphology parameters; the defect evolution simulation information includes at least the defect expansion trend, the maximum displacement and the maximum strain.

[0017] Preferably, the method of acquiring multi-source sensor data of a construction project and preprocessing it, thereby constructing a three-dimensional digital structural model, performing dynamic mechanical analysis on the three-dimensional digital structural model and combining it with structural design parameters to obtain an initial structural analysis model of the construction project, comprises the following steps:

[0018] Scan the construction project from multiple angles to obtain multi-source sensor data sequences of different dimensions of the construction project;

[0019] Preprocessing the multi-source sensor data sequence to obtain a preprocessed multi-source sensor data sequence, wherein the preprocessing includes one or more of denoising, standardization, data fusion, outlier removal, data interpolation, and data smoothing;

[0020] Based on the pre-processed multi-source sensor data sequence and combined with 3D reconstruction technology, the corresponding 3D digital structure model is obtained;

[0021] A dynamic mechanical analysis is performed on the three-dimensional digital structural model to obtain an initial structural analysis model of the construction project, wherein the dynamic mechanical analysis includes at least meshing and parameter assignment, wherein different sub-areas are formed through meshing, and corresponding structural design parameters are assigned to different sub-areas.

[0022] Preferably, applying environmental load conditions and construction load conditions to the initial structural analysis model to obtain a comprehensive structural analysis model, and combining structural design parameters to obtain dynamic coupling evaluation data, comprises the following steps:

[0023] Applying environmental load conditions to the initial structural analysis model to achieve a constraint boundary, thereby obtaining a first structural analysis model;

[0024] Applying construction load conditions to the first structural analysis model to obtain a comprehensive structural analysis model, wherein the construction load conditions include static load conditions and dynamic load conditions;

[0025] Based on the comprehensive structural analysis model and structural design parameters, dynamic coupling evaluation data is obtained. The specific process includes:

[0026] Construct control equations, which include at least mechanical equilibrium equations, displacement coordination equations and material constitutive equations. Combined with the comprehensive structural analysis model, the control equations are solved through a discretization method to obtain the final displacement field, final strain field and a set of high-risk area positions.

[0027] Preferably, obtaining the high-risk area location set comprises the following steps:

[0028] Based on the final strain field, the maximum principal strain of each sub-region is obtained;

[0029] The sub-regions in the comprehensive structural analysis model where the maximum principal strain is not less than the strain threshold are identified, and the location set of high-risk areas is obtained.

[0030] Preferably, the construction of the defect recognition pre-training model and training through dynamic coupling evaluation data to obtain the defect recognition model and then obtain the initial defect parameters includes the following steps:

[0031] Construct a defect recognition pre-training model based on the spatial feature extraction model;

[0032] The defect recognition pre-training model is trained and verified through dynamic coupling evaluation data to obtain a defect recognition model;

[0033] Input the dynamic coupling assessment data to be assessed into the defect identification model to obtain a set of predicted high-risk area locations;

[0034] Based on the predicted high-risk area location set, initial defect parameters are obtained, wherein the initial defect parameters at least include initial defect location, initial defect type, and initial defect morphology parameters.

[0035] Preferably, obtaining the initial defect parameters based on the predicted high-risk area location set comprises the following steps:

[0036] Calculate the center position of the predicted high-risk area location set to obtain the initial defect location;

[0037] Fitting the initial defect morphology according to the spatial distribution of the predicted high-risk area location set to obtain initial defect morphology parameters, wherein the initial defect morphology parameters include initial defect shape and initial defect size;

[0038] The maximum principal strain direction of the predicted high-risk area position set is calculated to obtain an average value of the maximum principal strain directions, and the average value of the maximum principal strain directions is converted into a standard direction vector, which is the initial defect type.

[0039] Preferably, obtaining defect evolution simulation information by using initial defect parameters, a comprehensive structural analysis model and structural design parameters comprises the following steps:

[0040] The initial defect position is used as the reference point, and the initial defect morphological parameters are mapped to the comprehensive structural analysis model. The defect direction of the comprehensive structural analysis model is then adjusted to the initial defect type and the mesh of the defect area is refined to achieve the update of the comprehensive structural analysis model. The defect evolution conditions, defect evolution direction, and defect evolution increment are defined to obtain the defect evolution structural analysis model.

[0041] Based on the defect evolution structural analysis model, the control equations are dynamically analyzed through an iterative solution method. Based on the results of each iteration in the analysis process, defect evolution simulation information is obtained. The analysis process is the defect evolution simulation process, which specifically includes:

[0042] When the defect evolution conditions are met, the defect is expanded to obtain the current defect expansion trend, defect evolution increment, defect evolution direction, strain field and displacement field, and then update the defect evolution structure analysis model;

[0043] Based on the updated defect evolution structural analysis model, the control equations are re-solved until the termination condition is met, and then the defect evolution simulation process is terminated;

[0044] Based on the strain field and displacement field of each iteration, the maximum strain and maximum displacement are obtained;

[0045] The defect evolution condition includes performing defect expansion if the current defect energy accumulation value is not less than the energy accumulation threshold;

[0046] The defect evolution direction is determined based on the historical evolution direction and the current strain field direction;

[0047] The defect expansion trend and the defect evolution increment are determined based on material characteristic parameters and load variation parameters, respectively.

[0048] Preferably, the step of constructing an optimization model based on the defect evolution simulation information and the monitoring equipment parameters and optimizing the monitoring equipment parameters to obtain the optimal monitoring parameters of the monitoring equipment comprises the following steps:

[0049] Constructing an optimization model, wherein the optimization model includes at least an optimization variable model, an optimization target model, and a constraint condition model; constructing the optimization variable model based on monitoring equipment parameters; the monitoring equipment parameters, i.e., optimization variables, include at least sampling frequency, sensor sensitivity, monitoring point density, and data transmission rate; constructing the optimization target model based on a first risk assessment value and a monitoring cost value; the first risk assessment value is obtained based on defect evolution simulation information; the monitoring cost value includes at least equipment energy consumption cost value, maintenance cost value, and data processing cost value; the constraint condition model includes a monitoring equipment parameter constraint condition model and a monitoring accuracy constraint condition model; and constructing the monitoring accuracy constraint condition model based on data acquisition accuracy, data timeliness, and equipment stability;

[0050] The optimization model is preliminarily solved by the simulated annealing algorithm to obtain the preliminary optimized monitoring parameters;

[0051] The optimization model is globally solved by the ant colony algorithm, and the optimal path of the ant colony is the optimal monitoring parameter of the monitoring equipment.

[0052] Preferably, the present invention further includes a construction project quality monitoring information management system, the system comprising:

[0053] Data acquisition module, used to obtain structural design parameters, real-time monitoring data and multi-source sensor data of construction projects;

[0054] The model building and analysis module is used to pre-process multi-source sensor data, build a three-dimensional digital structural model, perform dynamic mechanical analysis on the three-dimensional digital structural model and combine it with structural design parameters to obtain an initial structural analysis model of the construction project. Environmental load conditions and construction load conditions are applied to the initial structural analysis model to obtain a comprehensive structural analysis model. Combined with the structural design parameters, dynamic coupling evaluation data is obtained;

[0055] The defect recognition module is used to build a defect recognition pre-training model and train it through dynamic coupling evaluation data to obtain the defect recognition model and then obtain the initial defect parameters;

[0056] The simulation analysis module is used to obtain defect evolution simulation information through initial defect parameters, comprehensive structural analysis model and structural design parameters;

[0057] Parameter optimization module, which is used to build an optimization model and optimize the monitoring equipment parameters based on the defect evolution simulation information and monitoring equipment parameters to obtain the optimal monitoring parameters of the monitoring equipment;

[0058] The risk assessment and control module is used to infer the monitoring parameters of the current period based on the risk assessment model to obtain the risk assessment prediction value of the current period. Based on the risk assessment prediction value of the current period, the optimal monitoring parameters of the current period and the monitoring parameters of the current period, the actual optimal monitoring parameters of the current period are adjusted to achieve control of the quality monitoring of the construction project.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] In terms of data acquisition and processing, this method and system significantly improves data quality and comprehensiveness by acquiring structural design parameters, real-time monitoring data, and multi-source sensor data from construction projects, and performing pre-processing such as denoising and standardization on the multi-source sensor data. The multi-dimensional multi-source sensor data sequences acquired through multi-angle scanning provide a precise and rich data foundation for subsequent model construction. This enables the monitoring system to fully grasp the actual status of construction projects, overcoming the one-sided and single-minded nature of traditional manual sampling data, ensuring that critical information is not missed and laying a solid data foundation for accurate building quality assessments.

[0061] During the model construction and analysis phase, a three-dimensional digital structural model is constructed and dynamic mechanical analysis is performed. Structural design parameters are combined to generate an initial structural analysis model, and environmental and construction load conditions are then applied to create a comprehensive structural analysis model. This approach accurately simulates the mechanical properties of the building during actual use and construction. By constructing governing equations to solve the final displacement field, final strain field, and the location of high-risk areas, compared to traditional static, simple models, this model can more realistically reflect the response of the building structure under complex loads, accurately identify potential high-risk areas, and inform quality management personnel of weaknesses in the building structure in advance, enabling timely reinforcement or improvement measures to effectively improve the safety and stability of the building structure.

[0062] For defect identification, a pre-trained defect identification model is constructed based on a spatial feature extraction model. This model is trained using dynamic coupling assessment data to obtain initial defect parameters. This process accurately determines the initial defect location, type, and morphological parameters, significantly improving the accuracy and efficiency of defect identification. Compared to traditional manual visual inspection and simple non-destructive testing techniques, this method can detect hidden and subtle defects within buildings, providing strong support for timely defect repair and preventing quality issues from worsening, thereby reducing subsequent maintenance costs and safety risks.

[0063] Defect evolution simulation information is derived from initial defect parameters, a comprehensive structural analysis model, and structural design parameters, simulating defect expansion trends, maximum displacement, and maximum strain. This capability enables quality management personnel to predict defect development in advance and develop targeted repair and reinforcement plans before defects seriously impact the building structure. This prevents serious consequences such as structural damage or even collapse caused by defect expansion, safeguarding the lives and property of building occupants.

[0064] For monitoring equipment parameter optimization, an optimization model was constructed based on defect evolution simulation information and monitoring equipment parameters. The optimal monitoring parameters were then determined using simulated annealing and ant colony algorithms. This optimization approach dynamically adjusts monitoring equipment parameters, such as sampling frequency and sensor sensitivity, based on the actual construction project conditions. This improves the quality and effectiveness of monitoring data while avoiding resource waste, achieving optimal monitoring results with minimal investment and enhancing the cost-effectiveness of the monitoring system.

[0065] The risk assessment and control module infers the monitoring parameters for the current period based on the risk assessment model, deriving risk assessment predictions and adjusting the optimal monitoring parameters accordingly. This enables real-time dynamic monitoring and control of construction project quality. Once potential risks are identified, timely measures can be taken to mitigate them, ensuring that the construction project remains safe and reliable throughout its lifecycle. This enhances the scientific nature and reliability of construction project quality monitoring and provides strong technical support for the sustainable development of the construction industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a working principle diagram of the construction engineering quality monitoring information management method of the present invention;

[0067] Figure 2 Flowchart for constructing an initial structural analysis model for acquiring multi-source sensor data;

[0068] Figure 3 Flowchart for obtaining dynamic coupling evaluation data for applied loading conditions;

[0069] Figure 4 A flow chart for determining the location of high-risk areas;

[0070] Figure 5 Flowchart for optimizing monitoring equipment parameters to obtain optimal monitoring parameters. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0072] See also Figure 1-Figure 5 The present invention relates to a construction engineering quality monitoring information management method, and the specific implementation steps are as follows:

[0073] Obtain structural design parameters and real-time monitoring data for construction projects. This data forms the basis for subsequent analysis. Structural design parameters include information such as building design specifications and material properties, while real-time monitoring data reflects the building's immediate status during actual construction or use.

[0074] Multi-source sensor data for construction projects is acquired and preprocessed to remove noise and fill missing values, making the data more accurate and reliable. The processed data is then used to construct a 3D digital structural model. Dynamic mechanical analysis is then performed on this model, combined with structural design parameters, to produce an initial structural analysis model for the construction project. This model provides a preliminary simulation of the mechanical properties of the building structure under normal conditions.

[0075] Environmental and construction load conditions are applied to the initial structural analysis model. Taking into account the environmental loads such as wind and earthquake forces that buildings are subject to in practice, as well as various loads during construction, a comprehensive structural analysis model is generated. Combined with the structural design parameters, dynamic coupled assessment data is generated. This data can more comprehensively reflect the state of the building structure under complex loads.

[0076] A defect recognition pre-training model is constructed and trained with dynamic coupling assessment data to obtain a defect recognition model, which in turn derives initial defect parameters. These parameters can be used to preliminarily determine the location, type, and form of possible building defects.

[0077] By using the initial defect parameters, comprehensive structural analysis model and structural design parameters, defect evolution simulation information is obtained to predict the possible development trend of the defect.

[0078] Based on the defect evolution simulation information and monitoring equipment parameters, an optimization model is constructed and the monitoring equipment parameters are optimized to obtain the optimal monitoring parameters of the monitoring equipment, so that the monitoring equipment can monitor the building status more accurately.

[0079] Based on the risk assessment model, the monitoring parameters of the current period are inferred to obtain the risk assessment prediction value of the current period. Then, combined with the optimal monitoring parameters of the current period and the monitoring parameters of the current period, the actual optimal monitoring parameters of the current period are adjusted to finally achieve control of the construction project quality monitoring.

[0080] The present invention will be further described below in conjunction with Examples 1 to 5:

[0081] Example 1:

[0082] Using specialized scanning equipment, we scan buildings from multiple angles, collecting data from various locations and angles to obtain multi-source sensor data sequences covering various dimensions of the building. These data sequences contain raw information about each part of the building, but may contain noise, outliers, and other issues.

[0083] The multi-source sensor data series is then preprocessed, using one or more methods from the following: denoising, standardization, data fusion, outlier removal, data interpolation, and data smoothing, depending on the data's characteristics. For example, if the data contains outliers that significantly deviate from the normal range, they are removed using a suitable algorithm. If the data contains noise interference, a denoising algorithm is used to remove the noise and improve data quality.

[0084] Based on the pre-processed multi-source sensor data sequence and combined with 3D reconstruction technology, the processed data is converted into a 3D model to obtain the corresponding 3D digital structural model. This model intuitively displays the structural form of the building.

[0085] Dynamic mechanical analysis is performed on the 3D digital structural model. During the analysis, meshing is performed to divide the entire model into different sub-regions, allowing for a more detailed analysis of the mechanical properties of each part. Furthermore, structural design parameters are assigned to each sub-region based on the building's design, such as the material's elastic modulus and density. Ultimately, an initial structural analysis model for the building project is obtained.

[0086] Consider the case of a high-rise office building under construction undergoing construction quality monitoring and information management. To acquire and preprocess multi-source sensor data for the building, a 3D digital structural model is constructed. Dynamic mechanical analysis is then performed on the 3D digital structural model, combined with structural design parameters to generate an initial structural analysis model. The building is then scanned from multiple angles using a drone equipped with multiple sensors and ground-based laser scanning equipment. The drone scans the building's overall appearance and partial structure from different heights and angles, capturing data such as the smoothness of the facade and the structural outlines of each floor. The ground-based laser scanning equipment performs detailed scans of the building's substructure, internal beams, and columns, capturing detailed dimensions and surface texture information. This results in a multi-source sensor data sequence covering various dimensions of the building.

[0087] The scanned data sequence contains some anomalies caused by equipment noise and external interference, as well as some missing data due to occlusion. To address these issues, a wavelet denoising algorithm is used to remove data noise. Standardization methods are used to unify data collected by different sensors into the same numerical range to improve data comparability. Data fusion technology is used to integrate overlapping area data collected by drones and ground laser scanning equipment to ensure data integrity. For outliers, a reasonable threshold is set based on the statistical characteristics of the data, and data points exceeding the threshold are identified as outliers and removed. For missing data, linear interpolation is used to interpolate the data to make it complete. Finally, the data is smoothed using a sliding average filter to obtain the preprocessed multi-source sensor data sequence.

[0088] Using 3D reconstruction software, we imported preprocessed multi-source sensor data sequences into the software. Using the software's built-in algorithms, we gradually constructed a 3D digital structural model of the office building based on the spatial coordinates, geometric shape, and other information contained in the data. The model clearly depicts the building's overall appearance, internal floor layout, and the location and shape of its beams and columns, providing an intuitive foundation for subsequent analysis.

[0089] Perform dynamic mechanical analysis on the constructed three-dimensional digital structural model. Using professional finite element analysis software, the model is first meshed, and the entire office building model is divided into many small sub-areas. For example, the floor slabs, walls, beams and columns of each floor are meshed separately to ensure that each structural component can be accurately analyzed. Then, according to the structural design drawings of the building, the corresponding structural design parameters are assigned to different sub-areas. For example, the frame columns of the office building are made of high-strength concrete, and the corresponding concrete elastic modulus, density and other parameters are assigned to them; the beams are made of a specific type of steel, and the yield strength, Poisson's ratio and other parameters of the steel are assigned to the sub-areas of the beams. Through this series of operations, the initial structural analysis model of the office building construction project is finally obtained. This model can preliminarily simulate the mechanical response of the building under actual stress conditions.

[0090] Example 2:

[0091] Environmental load conditions are applied to the initial structural analysis model to simulate the loads the building would experience in the real environment, such as wind and temperature fluctuations. By applying these loads, the constraint boundaries are established, resulting in the first structural analysis model. This model reflects the building's initial mechanical response to environmental loads.

[0092] Construction load conditions are applied to the first structural analysis model. These conditions include static and dynamic load conditions. Static loads include the deadweight of building materials, while dynamic loads include vibration loads generated by the operation of construction equipment. After applying these loads, a comprehensive structural analysis model is generated, which comprehensively considers various load effects from the environment and the construction process.

[0093] Based on the comprehensive structural analysis model and structural design parameters, dynamic coupling assessment data is generated. The governing equations are constructed. Although not specifically formulated, they encompass mechanical equilibrium equations, displacement coordination equations, and material constitutive equations. In conjunction with the comprehensive structural analysis model, these governing equations are solved using a discretization method. The resulting solution yields a final displacement field, reflecting the displacement of various building components under load. The final strain field, demonstrating the degree of deformation of building materials, is also obtained. High-risk locations are then identified, locating areas within the building prone to potential problems.

[0094] Taking a cross-sea bridge project under construction as an example, when applying environmental load conditions and construction load conditions to the initial structural analysis model to obtain a comprehensive structural analysis model, combined with structural design parameters, dynamic coupling evaluation data is obtained:

[0095] Apply environmental load conditions to the initial structural analysis model. The marine environment where the cross-sea bridge is located is complex, and factors such as sea breeze, waves, and seawater corrosion will have an impact on the bridge structure. When simulating sea breeze loads, the average wind speed and maximum wind speed in different seasons and time periods are determined based on the historical meteorological data of the sea area. For example, the average wind speed in this sea area in summer is 10 meters per second, and the maximum wind speed can reach 25 meters per second. Through professional structural analysis software, these wind speed data are converted into corresponding wind pressures and applied to the initial structural analysis model of the bridge to simulate the effect of sea breeze on the bridge, realize the constraint boundary, and thus obtain the first structural analysis model. This model reflects the initial mechanical response of various structural components such as piers, bridge towers, and main beams under the action of sea breeze loads alone, such as the horizontal thrust on the piers and the lateral displacement trend of the bridge towers.

[0096] Construction load conditions are applied to the first structural analysis model. During the construction of a cross-sea bridge, the lifting operation of construction equipment, the impact during concrete pouring, and the weight of construction workers and materials are all construction loads. Taking concrete pouring as an example, assuming that a large concrete pump truck is used for pouring, the pump truck will generate vibration loads when working, and the weight of concrete poured each time is large, which will generate static loads on the bridge structure. When simulating these loads, the size and distribution of the static load are determined according to the construction plan and the actual equipment parameters used. For example, the weight of concrete poured each time is 50 tons and is evenly distributed in a specific construction area. For vibration loads, the vibration frequency and amplitude of the pump truck are measured during operation, and converted into equivalent dynamic loads and applied to the model. After applying these construction load conditions, a comprehensive structural analysis model is obtained, which comprehensively considers the mechanical state of the bridge structure under the combined action of environmental loads (sea breeze loads) and construction loads.

[0097] Based on the comprehensive structural analysis model and structural design parameters, dynamic coupling assessment data is obtained. While the governing equations do not involve specific formulas, they include mechanical equilibrium equations, displacement coordination equations, and material constitutive equations. Combined with the comprehensive structural analysis model, the governing equations are solved using the finite element discretization method. This solution yields the final displacement field, which, for example, allows one to clearly determine the displacement of various locations on a bridge's main beam under various loads. Excessive displacement at a particular location may indicate insufficient structural strength or stiffness at that location. Simultaneously, the final strain field is obtained, revealing the degree of deformation of the bridge's structural materials under load. For example, the strain of the concrete in a bridge tower can be used to determine whether the concrete is in a safe stress state. This process also allows the identification of high-risk locations. By analyzing the final strain field, the maximum principal strain is calculated for each subregion (e.g., the different subregions defined by piers, towers, and main beams). Assuming the strain threshold is set to 0.003, when the maximum principal strain of a sub-region is not less than this threshold, the sub-region is identified as a high-risk area. These high-risk areas may be locations prone to problems such as cracks and excessive deformation. Therefore, the location set of high-risk areas is determined, providing an important basis for subsequent monitoring and maintenance.

[0098] Example 3:

[0099] The pre-trained defect recognition model is trained and validated using dynamic coupling evaluation data. During training, the model parameters are continuously adjusted to enable the model to better learn the features in the data. Through multiple training and validation cycles, a high-performance defect recognition model is obtained.

[0100] The dynamic coupling assessment data to be evaluated is input into the defect recognition model. The model analyzes and predicts based on the learned features to obtain a set of predicted high-risk area locations.

[0101] Based on the predicted high-risk area location set, the initial defect parameters are further obtained. The center position of the predicted high-risk area location set is calculated, and this center position is the initial defect location. The initial defect morphology is fitted according to the spatial distribution of the predicted high-risk area location set to determine the initial defect shape and initial defect size, and obtain the initial defect morphology parameters. The maximum principal strain direction of the predicted high-risk area location set is calculated, and its average value is calculated and converted into a standard direction vector. This vector is the initial defect type.

[0102] Taking a super high-rise residential building under construction as an example, during the construction process, when monitoring the quality of the super high-rise residential building, a defect recognition pre-training model is constructed and trained through dynamic coupling evaluation data to obtain a defect recognition model, and then the initial defect parameters are obtained.

[0103] First, a pre-trained defect recognition model was constructed based on the spatial feature extraction model. A convolutional neural network (CNN) was selected as the underlying architecture for the spatial feature extraction model. The convolutional layers in a CNN automatically extract spatial features from images. For building structural data, these features may include the shape and size relationships of different structural components, as well as stress and strain distribution characteristics. The pre-trained defect recognition model was constructed using a relevant deep learning framework, and initial model parameters were set, such as the size and number of convolution kernels and the number of network layers.

[0104] The defect recognition pre-training model is trained and verified using the dynamic coupling assessment data of the super high-rise residential building. The dynamic coupling assessment data covers information such as the displacement field, strain field, and location of high-risk areas of the building structure under various loads. For example, at different construction stages, the displacement change data of each floor of the building and the strain data of concrete components are recorded. These data are divided into training sets and validation sets according to a certain ratio. The training set is used to train the model so that the model can learn the relationship between the features in the data and potential defects; the validation set is used to evaluate the performance of the model and prevent the model from overfitting. During the training process, the cross entropy loss function is used to measure the difference between the model prediction results and the true label. The cross entropy loss function formula is: Where L represents the cross entropy loss value, n is the number of samples, y i represents the true label of the i-th sample (in defect identification, for example, whether it belongs to a high-risk area, 1 if yes, 0 if no), p i represents the probability that the model predicts that the i-th sample belongs to the positive class (high-risk area). The backpropagation algorithm continuously adjusts the model parameters, gradually reducing the cross-entropy loss and improving the model's accuracy. After multiple rounds of training and validation, a high-performance defect recognition model was obtained.

[0105] The dynamic coupling assessment data to be evaluated is fed into the defect identification model. For example, the displacement and strain field data collected after a construction phase is input. The model analyzes and predicts the learned features and outputs a set of predicted high-risk area locations.

[0106] Based on the predicted high-risk area location set, the initial defect parameters are further obtained. The center position of the predicted high-risk area location set is calculated. Assuming that the high-risk area location set consists of multiple coordinate points (x j ,y j ,z j )(j=1,2,…,m, m is the number of points in the high-risk area), and the formula Calculate center position This central position is the initial defect location. The initial defect morphology is fitted based on the spatial distribution of the predicted high-risk area location set. For example, if the high-risk area has an elliptical distribution, the initial defect shape obtained through fitting calculation is an ellipse with a major axis length of a and a minor axis length of b. These are the shape and size information in the initial defect morphology parameters. The maximum principal strain direction of the predicted high-risk area location set is calculated, and the maximum principal strain direction of each point is measured to obtain a series of direction vectors. The average of these vectors is calculated, and then the average of the maximum principal strain direction is converted into a standard direction vector. This standard direction vector is the initial defect type, which is used to determine the possible cause and development trend of the defect.

[0107] b, these are the shape and size information in the initial defect morphological parameters. Calculate the maximum principal strain direction for the predicted set of high-risk area locations. Measure the maximum principal strain direction at each point to obtain a series of direction vectors. Average these vectors and convert the average maximum principal strain direction into a standard direction vector. This standard direction vector is the initial defect type, which is used to determine the possible cause and development trend of the defect.

[0108] Example 4:

[0109] The initial defect location is used as a reference point, and the initial defect morphological parameters are mapped to the comprehensive structural analysis model. The defect direction of the comprehensive structural analysis model is adjusted according to the initial defect type, and the mesh of the defect area is refined. This allows for a more accurate analysis of the mechanical changes in the defect area. At the same time, the defect evolution conditions, defect evolution direction, and defect evolution increment are defined to obtain the defect evolution structural analysis model.

[0110] Based on the defect evolution structural analysis model, an iterative solution method is used to dynamically analyze the governing equations. When the defect evolution conditions are met (i.e., the current defect energy accumulation value is no less than the energy accumulation threshold), defect expansion is performed to obtain the current defect expansion trend, defect evolution increment, defect evolution direction, strain field, and displacement field, and then update the defect evolution structural analysis model.

[0111] Based on the updated defect evolution structural analysis model, the governing equations are resolved and this process is repeated until the termination criteria are met, terminating the defect evolution simulation. During each iteration, the strain and displacement fields are recorded, and the maximum strain and displacement are obtained. These data reflect the mechanical changes in the building structure during the defect evolution process.

[0112] Taking the construction project of a large gymnasium as an example, it is assumed that initial defect parameters have been obtained during the quality monitoring of the gymnasium. For example, through preliminary testing and analysis, an initial defect is found at a node in the steel structure of the gymnasium roof. The initial defect is located at a node in the middle of a span of the roof. The initial defect type is determined to be local stress concentration caused by welding defects. The initial defect morphological parameters show that the weld at the defect has an incomplete weld of about 5 mm, and the defect area is circular with a diameter of about 10 cm.

[0113] The initial defect position is used as the reference point, and the initial defect morphological parameters are mapped to the comprehensive structural analysis model. Using professional structural analysis software, the defect position is accurately located in the comprehensive structural analysis model of the gymnasium. According to the initial defect type, that is, the local stress concentration caused by the welding defect, the mechanical parameters of the area in the model are adjusted to simulate the influence of stress concentration. At the same time, the mesh of the defect area is encrypted and the originally larger mesh is refined. For example, the mesh size of the area is refined from the original 10 cm × 10 cm to 1 cm × 1 cm. This can more accurately capture the mechanical changes of the defect area when it is subjected to stress. Next, the defect evolution conditions, defect evolution direction and defect evolution increment are defined. The defect evolution condition is set to propagate when the accumulated energy in the defect region reaches 100 joules (a hypothetical value determined based on material properties, etc.). The defect evolution direction is determined based on a combination of the historical evolution direction (initially assumed to be along the weld) and the current strain field direction. The defect evolution increment is determined based on the characteristic parameters of the stadium's steel (such as elastic modulus and yield strength) and load variation parameters (such as the change in live load generated by spectator seating). Through these operations, a structural analysis model for defect evolution is obtained.

[0114] Based on the defect evolution structural analysis model, an iterative solution method was used to dynamically analyze the governing equations. During the stadium construction process, the loads on the structure continuously changed as construction progressed. Additional construction loads were added during roof installation. The model was analyzed at each construction stage. Assuming that at a certain point, the accumulated energy in the defect region reached 105 joules, satisfying the defect evolution conditions, the defect was then expanded. At this point, the current defect expansion trend was calculated based on material properties and load changes. For example, a defect was predicted to expand along the weld at a rate of 0.1 mm per day. The defect evolution increment was then calculated, such as a 5 MPa stress increase in the defect region. The defect evolution direction was then determined. If the current strain field direction had a small angle with the historical evolution direction, the defect was considered to be expanding along the weld. The strain and displacement field data at that point were also obtained. This data was used to update the defect evolution structural analysis model and adjust the parameters and shape of the defect region within the model.

[0115] Based on the updated defect evolution structural analysis model, the control equations are re-solved. This process is repeated until the termination condition is met. The termination condition can be set as the completion of the gymnasium construction and after a period of monitoring, the energy accumulation value in the defect area no longer increases or increases extremely slowly, and the various mechanical indicators are stable. During each iteration, the strain field and displacement field data are recorded. For example, after many iterations, it was found that at a certain moment the maximum strain of the gymnasium roof steel structure reached 0.0025 (close to the allowable strain value of the material), and the maximum displacement occurred in the area near the defect, with a displacement of 5 cm. These maximum strain and maximum displacement data can intuitively reflect the mechanical changes of the gymnasium structure during the defect evolution process, and provide a key basis for evaluating structural safety and formulating subsequent maintenance measures.

[0116] Example 5:

[0117] Construct an optimization model, which includes an optimization variable model, an optimization target model, and a constraint model. The optimization variable model is constructed based on monitoring equipment parameters, with monitoring equipment parameters such as sampling frequency, sensor sensitivity, monitoring point density, and data transmission rate serving as optimization variables. A first risk assessment value is obtained based on defect evolution simulation information, while a monitoring cost value is constructed by considering equipment energy consumption cost, maintenance cost, and data processing cost. The optimization target model is constructed using the first risk assessment value and monitoring cost value. The constraint model includes a monitoring equipment parameter constraint model and a monitoring accuracy constraint model. The monitoring accuracy constraint model is constructed based on data acquisition accuracy, data timeliness, and equipment stability.

[0118] The optimization model was initially solved using the simulated annealing algorithm, a heuristic search algorithm that can, to a certain extent, avoid falling into local optimal solutions and obtain preliminary optimized monitoring parameters. The optimization model was then globally solved using the ant colony algorithm, which simulates the behavior of ants searching for food. The ants leave pheromones along their paths for information exchange, ultimately determining the optimal path for the ant colony. The parameters corresponding to this optimal path are the optimal monitoring parameters for the monitoring equipment.

[0119] For example, a construction quality monitoring project for a large commercial complex has already deployed monitoring equipment, including displacement sensors and strain sensors located on different floors and in key structural areas, to obtain real-time data on the building's status. However, to more accurately and efficiently monitor building quality, it is necessary to construct an optimization model based on defect evolution simulation information and monitoring equipment parameters, and then optimize the monitoring equipment parameters to obtain the optimal monitoring parameters.

[0120] Build an optimization model. First, we create an optimization variable model based on the monitoring equipment parameters, which serve as optimization variables. For example, the displacement sensor sampling frequency is currently set to once per minute, the sensor sensitivity is 0.01 mm, the monitoring point density in the key load-bearing column area is one sensor for every two columns, and the data transmission rate is 10 KB per second. These parameters can be adjusted based on actual needs and optimization objectives.

[0121] Then, an optimization target model is constructed, and the first risk assessment value is obtained based on the defect evolution simulation information. Through the analysis of the early monitoring data of the commercial complex and the simulation of the structural model, it is predicted that under the current construction progress, if the monitoring is not in place, the probability that a certain area may cause safety risks due to structural deformation is 20% (hypothesis). This is the first risk assessment value. At the same time, the monitoring cost value is considered. The monitoring cost value includes the equipment energy consumption cost value, maintenance cost value and data processing cost value. Calculated on a monthly basis, the equipment energy consumption cost is 500 yuan, the maintenance cost (including equipment calibration, maintenance, etc.) is 800 yuan, and the data processing cost (such as the server resource cost required for storage and analysis of data) is 1,000 yuan. The total monitoring cost value is 2,300 yuan. The optimization target model is constructed by combining the first risk assessment value and the monitoring cost value. The goal is to control costs while reducing risks.

[0122] Then, a constraint model is constructed, including a monitoring equipment parameter constraint model and a monitoring accuracy constraint model. The monitoring accuracy constraint model is constructed based on data acquisition accuracy, data timeliness, and equipment stability. For example, it is stipulated that the measurement accuracy error of the displacement sensor cannot exceed ±0.05 mm, data must be transmitted to the monitoring center within 1 minute of acquisition to ensure timeliness, and the equipment must be able to operate stably in the complex electromagnetic environment within the commercial complex without data loss or errors.

[0123] The optimization model is initially solved using a simulated annealing algorithm. Starting with an initial solution, the simulated annealing algorithm randomly searches the solution space. For example, it might first try increasing the displacement sensor sampling frequency to 2 times per minute and the sensor sensitivity to 0.005 mm, while also adjusting the density of monitoring points and the data transmission rate. After each new solution attempt, the objective function value is calculated based on the optimization target model (taking into account both risk and cost). If the objective function value of the new solution is better than the current solution, the new solution is accepted; if it is worse, it is accepted with a certain probability, which gradually decreases with each algorithm iteration. After multiple iterative calculations, the initial optimized monitoring parameters are obtained, such as adjusting the sampling frequency to 1.5 times per minute, the sensor sensitivity to 0.008 mm, increasing the density of monitoring points in key areas to one sensor per pillar, and increasing the data transmission rate to 15 KB per second.

[0124] The optimization model is globally solved using an ant colony algorithm (ACA). The ACA simulates the behavior of ants searching for food. Ants leave pheromones along their paths, and paths with high pheromone concentrations are more attractive to other ants. In this project, different combinations of monitoring device parameters are considered paths along which ants search for food. At the beginning of the algorithm, ants randomly select paths (i.e., different parameter combinations). As iterations proceed, the pheromone concentration is updated based on the objective function value (combined risk and cost) corresponding to each path (parameter combination). For example, if a parameter combination performs well in reducing risk and controlling cost, the pheromone concentration on the corresponding path will increase, attracting more ants. After multiple rounds of iterations, the optimal path for the ant colony is ultimately determined, which in turn is the optimal monitoring parameters for the monitoring device. Assume that the optimal monitoring parameters are: a sampling frequency of twice per minute, a sensor sensitivity of 0.005 mm, a density of monitoring points differentiated by structural importance, with a sensor every 0.5 meters in critical structural areas and one every 1 meter in general areas, and a data transmission rate of 20 KB per second. By setting these optimal monitoring parameters, it is possible to minimize monitoring costs and safety risks of building structures while ensuring monitoring accuracy and timeliness, thereby achieving efficient monitoring of the construction quality of commercial complexes.

[0125] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0126] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A construction engineering quality monitoring information management method, characterized in that: The following steps are involved: Obtain structural design parameters and real-time monitoring data of construction projects; Acquire and pre-process multi-source sensor data of the construction project to construct a 3D digital structural model. Perform dynamic mechanical analysis on the 3D digital structural model and combine it with structural design parameters to obtain an initial structural analysis model of the construction project. Apply environmental load conditions and construction load conditions to the initial structural analysis model to obtain a comprehensive structural analysis model. Combined with the structural design parameters, dynamic coupling evaluation data is obtained. Construct a defect recognition pre-training model and train it through dynamic coupling evaluation data to obtain a defect recognition model and then obtain the initial defect parameters; Through the initial defect parameters, comprehensive structural analysis model and structural design parameters, defect evolution simulation information is obtained; Based on the defect evolution simulation information and monitoring equipment parameters, an optimization model is constructed and the monitoring equipment parameters are optimized to obtain the optimal monitoring parameters of the monitoring equipment; Based on the risk assessment model, the monitoring parameters of the current period are inferred to obtain the risk assessment prediction value of the current period. Based on the risk assessment prediction value of the current period, the optimal monitoring parameters of the current period and the monitoring parameters of the current period, the actual optimal monitoring parameters of the current period are adjusted to achieve control of the quality monitoring of the construction project.

2. The construction engineering quality monitoring information management method according to claim 1, characterized in that: The dynamic coupling assessment data at least includes the final displacement field, the final strain field and a set of high-risk area locations; The initial defect parameters include at least initial defect position, initial defect type and initial defect morphology parameters; The defect evolution simulation information includes at least defect expansion trend, maximum displacement and maximum strain.

3. The construction engineering quality monitoring information management method according to claim 1, characterized in that: The method of acquiring multi-source sensor data of a construction project and preprocessing it, thereby constructing a three-dimensional digital structural model, performing dynamic mechanical analysis on the three-dimensional digital structural model and combining it with structural design parameters to obtain an initial structural analysis model of the construction project, includes the following steps: Scan the construction project from multiple angles to obtain multi-source sensor data sequences of different dimensions of the construction project; Preprocessing the multi-source sensor data sequence to obtain a preprocessed multi-source sensor data sequence, wherein the preprocessing includes one or more of denoising, standardization, data fusion, outlier removal, data interpolation, and data smoothing; Based on the pre-processed multi-source sensor data sequence and combined with 3D reconstruction technology, the corresponding 3D digital structure model is obtained; A dynamic mechanical analysis is performed on the three-dimensional digital structural model to obtain an initial structural analysis model of the construction project, wherein the dynamic mechanical analysis includes at least meshing and parameter assignment, wherein different sub-areas are formed through meshing, and corresponding structural design parameters are assigned to different sub-areas.

4. The construction engineering quality monitoring information management method according to claim 1, characterized in that: Applying environmental load conditions and construction load conditions to the initial structural analysis model to obtain a comprehensive structural analysis model, and combining structural design parameters to obtain dynamic coupling evaluation data, includes the following steps: Applying environmental load conditions to the initial structural analysis model to achieve a constraint boundary, thereby obtaining a first structural analysis model; Applying construction load conditions to the first structural analysis model to obtain a comprehensive structural analysis model, wherein the construction load conditions include static load conditions and dynamic load conditions; Based on the comprehensive structural analysis model and structural design parameters, dynamic coupling evaluation data is obtained. The specific process includes: Construct control equations, which include at least mechanical equilibrium equations, displacement coordination equations and material constitutive equations. Combined with the comprehensive structural analysis model, the control equations are solved through a discretization method to obtain the final displacement field, final strain field and a set of high-risk area positions.

5. The construction engineering quality monitoring information management method according to claim 4, characterized in that: Obtaining the high-risk area location set includes the following steps: Based on the final strain field, the maximum principal strain of each sub-region is obtained; The sub-regions in the comprehensive structural analysis model where the maximum principal strain is not less than the strain threshold are identified, and the location set of high-risk areas is obtained.

6. The construction engineering quality monitoring information management method according to claim 1, characterized in that: The method of constructing a defect recognition pre-training model and training it through dynamic coupling evaluation data to obtain a defect recognition model and then obtain initial defect parameters includes the following steps: Construct a defect recognition pre-training model based on the spatial feature extraction model; The defect recognition pre-training model is trained and verified through dynamic coupling evaluation data to obtain a defect recognition model; Input the dynamic coupling assessment data to be assessed into the defect identification model to obtain a set of predicted high-risk area locations; Based on the predicted high-risk area location set, initial defect parameters are obtained, wherein the initial defect parameters at least include initial defect location, initial defect type, and initial defect morphology parameters.

7. The construction engineering quality monitoring information management method according to claim 6, characterized in that: The method of obtaining initial defect parameters based on the predicted high-risk area location set includes the following steps: Calculate the center position of the predicted high-risk area location set to obtain the initial defect location; Fitting the initial defect morphology according to the spatial distribution of the predicted high-risk area location set to obtain initial defect morphology parameters, wherein the initial defect morphology parameters include initial defect shape and initial defect size; The maximum principal strain direction of the predicted high-risk area position set is calculated to obtain an average value of the maximum principal strain directions, and the average value of the maximum principal strain directions is converted into a standard direction vector, which is the initial defect type.

8. The construction engineering quality monitoring information management method according to claim 1, characterized in that: The defect evolution simulation information is obtained by using the initial defect parameters, the comprehensive structural analysis model and the structural design parameters, including the following steps: The initial defect position is used as the reference point, and the initial defect morphological parameters are mapped to the comprehensive structural analysis model. The defect direction of the comprehensive structural analysis model is then adjusted to the initial defect type and the mesh of the defect area is refined to achieve the update of the comprehensive structural analysis model. The defect evolution conditions, defect evolution direction, and defect evolution increment are defined to obtain the defect evolution structural analysis model. Based on the defect evolution structural analysis model, the control equations are dynamically analyzed through an iterative solution method. Based on the results of each iteration in the analysis process, defect evolution simulation information is obtained. The analysis process is the defect evolution simulation process, which specifically includes: When the defect evolution conditions are met, the defect is expanded to obtain the current defect expansion trend, defect evolution increment, defect evolution direction, strain field and displacement field, and then update the defect evolution structure analysis model; Based on the updated defect evolution structural analysis model, the control equations are re-solved until the termination condition is met, and then the defect evolution simulation process is terminated; Based on the strain field and displacement field of each iteration, the maximum strain and maximum displacement are obtained; The defect evolution condition includes performing defect expansion if the current defect energy accumulation value is not less than the energy accumulation threshold; The defect evolution direction is determined based on the historical evolution direction and the current strain field direction; The defect expansion trend and the defect evolution increment are determined based on material characteristic parameters and load variation parameters, respectively.

9. The construction engineering quality monitoring information management method according to claim 1, characterized in that: The method of constructing an optimization model based on the defect evolution simulation information and the monitoring equipment parameters and optimizing the monitoring equipment parameters to obtain the optimal monitoring parameters of the monitoring equipment includes the following steps: Constructing an optimization model, wherein the optimization model includes at least an optimization variable model, an optimization target model, and a constraint condition model; constructing the optimization variable model based on monitoring equipment parameters; the monitoring equipment parameters, i.e., optimization variables, include at least sampling frequency, sensor sensitivity, monitoring point density, and data transmission rate; constructing the optimization target model based on a first risk assessment value and a monitoring cost value; the first risk assessment value is obtained based on defect evolution simulation information; the monitoring cost value includes at least equipment energy consumption cost value, maintenance cost value, and data processing cost value; the constraint condition model includes a monitoring equipment parameter constraint condition model and a monitoring accuracy constraint condition model; and constructing the monitoring accuracy constraint condition model based on data acquisition accuracy, data timeliness, and equipment stability; The optimization model is preliminarily solved by the simulated annealing algorithm to obtain the preliminary optimized monitoring parameters; The optimization model is globally solved by the ant colony algorithm, and the optimal path of the ant colony is the optimal monitoring parameter of the monitoring equipment.

10. A construction engineering quality monitoring information management system, characterized in that: include: Data acquisition module, used to obtain structural design parameters, real-time monitoring data and multi-source sensor data of construction projects; The model building and analysis module is used to pre-process multi-source sensor data, build a three-dimensional digital structural model, perform dynamic mechanical analysis on the three-dimensional digital structural model and combine it with structural design parameters to obtain an initial structural analysis model of the construction project. Environmental load conditions and construction load conditions are applied to the initial structural analysis model to obtain a comprehensive structural analysis model. Combined with the structural design parameters, dynamic coupling evaluation data is obtained; The defect recognition module is used to build a defect recognition pre-training model and train it through dynamic coupling evaluation data to obtain the defect recognition model and then obtain the initial defect parameters; The simulation analysis module is used to obtain defect evolution simulation information through initial defect parameters, comprehensive structural analysis model and structural design parameters; Parameter optimization module, which is used to build an optimization model and optimize the monitoring equipment parameters based on the defect evolution simulation information and monitoring equipment parameters to obtain the optimal monitoring parameters of the monitoring equipment; The risk assessment and control module is used to infer the monitoring parameters of the current period based on the risk assessment model to obtain the risk assessment prediction value of the current period. Based on the risk assessment prediction value of the current period, the optimal monitoring parameters of the current period and the monitoring parameters of the current period, the actual optimal monitoring parameters of the current period are adjusted to achieve control of the quality monitoring of the construction project.

Images