Concrete crack resistance simulation monitoring method, device, equipment and storage medium

Abstract

The present invention relates to the technical field of concrete performance simulation, and in particular to a method, device, equipment and storage medium for simulation monitoring of concrete anti-cracking performance. The method comprises the following steps: obtaining multiple groups of internal microstructure images; segmenting multiple groups of internal microstructure images into different component regions, and performing quantitative analysis of mechanism structure to generate mechanism structure parameters of different regions; performing real-time environmental parameter monitoring of the monitored concrete based on multiple sensor nodes to obtain concrete environmental perception parameters; performing environmental stress load mining on concrete environmental perception parameters to generate concrete environmental stress load characteristics; performing multi-frequency filtering and noise reduction on internal three-dimensional microstructure images based on mechanism structure parameters of different regions, and performing regional structure three-dimensional point cloud modeling to construct a concrete three-dimensional point cloud model. The present invention realizes high-precision and high-efficiency simulation of concrete anti-cracking performance.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete performance simulation, and in particular to a method, device, equipment and storage medium for simulation monitoring of concrete anti-cracking performance. Background Art

[0002] As the quality requirements of construction projects continue to increase, concrete, as a common building material, has an extremely important crack resistance in engineering practice. Concrete is affected by many factors during use, such as temperature changes, load effects, material properties, etc. These factors lead to the generation and expansion of concrete cracks, which in turn affect the structural integrity and service life of the building. Traditional concrete crack resistance monitoring methods mainly rely on manual detection and field tests, which have the problems of low detection accuracy and low efficiency. Therefore, in order to meet the precise needs of today's construction projects for concrete crack resistance monitoring, an intelligent simulation monitoring method is urgently needed to improve monitoring accuracy and efficiency. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a method, device, equipment and storage medium for simulating and monitoring the anti-cracking performance of concrete, so as to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for simulating and monitoring the anti-cracking performance of concrete, comprising the following steps:

[0005] Step S1: acquiring multiple sets of internal microstructure images; segmenting the multiple sets of internal microstructure images into different component regions, and performing mechanism structure quantitative analysis to generate mechanism structure parameters of different regions;

[0006] Step S2: Based on the multi-sensor nodes, real-time environmental parameter monitoring is performed on the concrete to be monitored to obtain concrete environmental perception parameters; environmental stress load mining is performed on the concrete environmental perception parameters to generate concrete environmental stress load characteristics;

[0007] Step S3: performing multi-frequency filtering and noise reduction on the internal three-dimensional microstructure image based on the mechanism structural parameters of different regions, and performing regional structure three-dimensional point cloud modeling to construct a three-dimensional point cloud model of concrete;

[0008] Step S4: dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics to construct a dynamic twin evolution model; identify potential structural defects in the dynamic twin evolution model to extract concrete structural defect data;

[0009] Step S5: performing defect coupling evolution analysis on the concrete structure defect data, and reconstructing multiple time series trends to construct a defect evolution prediction trend curve;

[0010] Step S6: Analyze the change trend of the crack resistance performance of the defect evolution prediction trend curve, and perform maintenance decision analysis to build a concrete performance maintenance decision strategy.

[0011] The present invention also provides a concrete anti-cracking performance simulation monitoring device, comprising:

[0012] The mechanism structure module is used to obtain multiple sets of internal microstructure images; segment the multiple sets of internal microstructure images into different component regions, and perform mechanism structure quantitative analysis to generate mechanism structure parameters of different regions;

[0013] The stress load module is used to monitor the environmental parameters of the concrete to be monitored in real time based on multiple sensor nodes to obtain the concrete environmental perception parameters; the environmental stress load mining of the concrete environmental perception parameters is carried out to generate the concrete environmental stress load characteristics;

[0014] The 3D point cloud modeling module is used to perform multi-frequency filtering and noise reduction on the internal 3D microstructure image based on the mechanism structural parameters of different regions, and to perform regional structure 3D point cloud modeling to construct a 3D point cloud model of concrete;

[0015] The dynamic simulation evolution module is used to dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics, and to construct a dynamic twin evolution model; to identify potential structural defects in the dynamic twin evolution model and to extract concrete structural defect data;

[0016] Defect prediction module, used to analyze the defect coupling evolution of concrete structure defect data, reconstruct multiple time series trends, and construct defect evolution prediction trend curve;

[0017] The comprehensive performance evaluation module is used to analyze the change trend of the anti-crack performance of the defect evolution prediction trend curve, conduct maintenance decision analysis, and build a concrete performance maintenance decision strategy.

[0018] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above-mentioned methods for simulating and monitoring the anti-cracking performance of concrete when executing the computer program.

[0019] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for simulating and monitoring the anti-cracking performance of concrete are implemented.

[0020] The specific beneficial effects of the present invention are as follows: by segmenting the internal microstructure image into different component regions and performing quantitative analysis of the mechanism structure, the structural characteristics and mechanisms inside the concrete can be deeply understood; the generation of mechanism structure parameters in different regions is helpful to provide basic data for subsequent 3D point cloud modeling and dynamic simulation; real-time monitoring of the environmental parameters of the concrete can help capture the environmental stress load conditions on the concrete, and provide real environmental data for subsequent simulation evolution; the generated concrete environmental stress load characteristics are helpful to evaluate the performance changes of the concrete under different environmental conditions; noise reduction processing and 3D point cloud modeling are helpful to accurately reconstruct the internal structure of the concrete, and provide accurate initial data for subsequent simulation evolution models; the constructed 3D point cloud model of the concrete is helpful for subsequent dynamic Simulation provides the basic structure. The dynamic simulation evolution model can simulate the behavior of concrete under different stress loads and help discover potential structural defects. The extracted concrete structure defect data provides important information for subsequent evolution prediction and performance evaluation. Through evolution analysis and trend reconstruction, the development law of concrete structure defects can be explored to provide a basis for performance evaluation and maintenance decisions. The constructed defect evolution prediction trend curve helps to predict the future state of the concrete structure. Through crack resistance evaluation and performance life calculation, the performance of concrete in different periods can be quantified to provide a basis for maintenance decisions. The generated comprehensive concrete performance evaluation value and maintenance decision-making strategy help to formulate an effective concrete structure maintenance plan, extend the structure life, and ensure structural safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of the steps of a method for simulating and monitoring the anti-cracking performance of concrete according to the present invention;

[0022] Figure 2 Detailed implementation flow chart of step S2;

[0023] Figure 3 is a schematic diagram of a detailed implementation process of step S3;

[0024] Figure 4 It is a schematic diagram of the detailed implementation steps of step S4. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0026] The present application example provides a method, device, equipment and storage medium for simulation monitoring of concrete crack resistance. The execution subjects of the method, device, equipment and storage medium for simulation monitoring of concrete crack resistance include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0027] See also Figures 1 to 4 The present invention provides a simulation monitoring method for concrete crack resistance, the method comprising the following steps:

[0028] Step S1: acquiring multiple sets of internal microstructure images; segmenting the multiple sets of internal microstructure images into different component regions, and performing mechanism structure quantitative analysis to generate mechanism structure parameters of different regions;

[0029] Step S2: Based on the multi-sensor nodes, real-time environmental parameter monitoring is performed on the concrete to be monitored to obtain concrete environmental perception parameters; environmental stress load mining is performed on the concrete environmental perception parameters to generate concrete environmental stress load characteristics;

[0030] Step S3: performing multi-frequency filtering and noise reduction on the internal three-dimensional microstructure image based on the mechanism structural parameters of different regions, and performing regional structure three-dimensional point cloud modeling to construct a three-dimensional point cloud model of concrete;

[0031] Step S4: dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics to construct a dynamic twin evolution model; identify potential structural defects in the dynamic twin evolution model to extract concrete structural defect data;

[0032] Step S5: performing defect coupling evolution analysis on the concrete structure defect data, and reconstructing multiple time series trends to construct a defect evolution prediction trend curve;

[0033] Step S6: Analyze the change trend of the crack resistance performance of the defect evolution prediction trend curve, and perform maintenance decision analysis to build a concrete performance maintenance decision strategy.

[0034] By segmenting the internal microstructure images into different component regions and quantitatively analyzing the mechanism structure, we can gain an in-depth understanding of the structural characteristics and mechanisms inside the concrete. Generating the mechanism structure parameters of different regions can help provide basic data for subsequent 3D point cloud modeling and dynamic simulation. Real-time monitoring of the environmental parameters of concrete can help capture the environmental stress load conditions of concrete and provide real environmental data for subsequent simulation evolution. The generated concrete environmental stress load characteristics can help evaluate the performance changes of concrete under different environmental conditions. Noise reduction processing and 3D point cloud modeling can help accurately reconstruct the internal structure of concrete and provide accurate initial data for subsequent simulation evolution models. The constructed 3D point cloud model of concrete provides a basic The dynamic simulation evolution model can simulate the behavior of concrete under different stress loads and help discover potential structural defects. The extracted concrete structure defect data provides important information for subsequent evolution prediction and performance evaluation. Through evolution analysis and trend reconstruction, the development law of concrete structure defects can be explored to provide a basis for performance evaluation and maintenance decisions. The constructed defect evolution prediction trend curve is helpful to predict the future state of the concrete structure. Through crack resistance evaluation and performance life calculation, the performance of concrete in different periods can be quantified to provide a basis for maintenance decisions. The generated comprehensive concrete performance evaluation value and maintenance decision-making strategy are helpful to formulate an effective concrete structure maintenance plan, extend the structure life, and ensure structural safety.

[0035] In the embodiment of the present invention, refer to Figure 1 , is a schematic diagram of the steps of a simulation monitoring method for concrete crack resistance of the present invention. In this example, the steps of the simulation monitoring method for concrete crack resistance include:

[0036] Step S1: acquiring multiple sets of internal microstructure images; segmenting the multiple sets of internal microstructure images into different component regions, and performing mechanism structure quantitative analysis to generate mechanism structure parameters of different regions;

[0037] In this embodiment, a high-resolution microscope (such as a scanning electron microscope SEM or a transmission electron microscope TEM) is used to capture images of the internal microstructure of concrete, and multiple sets of images are collected to cover different concrete samples and regions for comprehensive analysis. The acquired images are preprocessed, including denoising, contrast enhancement, and brightness adjustment, to improve the accuracy of subsequent analysis. Image processing software (such as ImageJ or MATLAB) is used to process the images to ensure good image quality. A suitable segmentation algorithm is selected according to image features, such as threshold segmentation, region growing method, or segmentation method based on machine learning (such as U-Net). The preprocessed microstructure images are input into the selected The segmentation algorithm automatically segments the component areas to ensure that the segmentation results are clear and can accurately distinguish different component areas (such as cement, aggregate, voids, etc.). The features of the segmented different component areas are extracted, including area, perimeter, shape factor, porosity, etc. Image processing tools are used to extract these geometric features and record the statistical data of each area. Based on the extracted features, the mechanism and structure parameters of concrete, such as the ratio of cement to aggregate, void distribution, crack characteristics, etc., are calculated. Physical models or statistical models are used to analyze the relationship between these mechanism and structure parameters and concrete performance. The mechanism and structure parameters of different areas are summarized to form a structured data set for subsequent analysis and application.

[0038] Step S2: Based on the multi-sensor nodes, real-time environmental parameter monitoring is performed on the concrete to be monitored to obtain concrete environmental perception parameters; environmental stress load mining is performed on the concrete environmental perception parameters to generate concrete environmental stress load characteristics;

[0039] In this embodiment, multiple sensor nodes are arranged on the concrete structure to be monitored, and the sensor types include temperature sensors, humidity sensors, strain sensors and pressure sensors. Ensure that the sensors cover the key areas of the concrete to obtain comprehensive environmental data. Configure the sampling frequency of the sensor to ensure that the environmental parameters can be obtained in real time (for example, sampling once every minute or every second). Ensure that the data acquisition system can operate stably and can monitor the status of the sensor in real time (such as battery power, connection status, etc.). The collected data is transmitted to the central data processing system in real time through a wireless network or a wired network. The data should be stored in a database for subsequent access and analysis. According to the material properties and environmental parameters of the concrete, a stress load calculation model (such as a linear elastic model or a nonlinear model) is established. The environmental parameters that need to be considered include the effects of temperature, humidity and pressure on the stress state of the concrete. The environmental stress load of the concrete is calculated using an existing physical model or numerical simulation method (such as finite element analysis). Combine the environmental parameters with the stress load model to calculate the stress state of the concrete under different environmental conditions. Extract the concrete environmental stress load characteristics from the calculation results, including the maximum stress, the minimum stress, the stress concentration area, etc. Record the changes in the stress load characteristics at different time points for subsequent analysis.

[0040] Step S3: performing multi-frequency filtering and noise reduction on the internal three-dimensional microstructure image based on the mechanism structural parameters of different regions, and performing regional structure three-dimensional point cloud modeling to construct a three-dimensional point cloud model of concrete;

[0041] In this embodiment, a suitable multi-frequency filter is selected, such as a wavelet transform or a Gaussian filter. Filter) to remove noise from the image, perform multi-frequency filtering on the three-dimensional image to remove high-frequency noise and retain important structural information, adjust filtering parameters (such as filter window size and frequency range) to ensure the best noise reduction effect, view the filtering results through visualization tools to ensure that the noise reduction process does not lose important details, divide the denoised three-dimensional image into regions according to the mechanism structure parameters (such as porosity, material distribution, etc.) to ensure that the features of each region are independent, use a three-dimensional reconstruction algorithm (such as voxelization method or surface reconstruction method) to convert the denoised image into point cloud data, each voxel or pixel generates a corresponding three-dimensional coordinate point according to its grayscale value or eigenvalue to form a point cloud, process the generated point cloud, including removing noise points and outliers to ensure the quality of the point cloud, apply filtering technology (such as statistical outlier removal) to further clean the point cloud data, extract features from the processed point cloud, calculate the geometric features of the point cloud, such as curvature, normal vector, etc., record the feature information of different regions for subsequent analysis, and save the final three-dimensional point cloud model in a standard format (such as PLY, OBJ or LAS) for subsequent visualization and analysis.

[0042] Step S4: dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics to construct a dynamic twin evolution model; identify potential structural defects in the dynamic twin evolution model to extract concrete structural defect data;

[0043] In this embodiment, based on the extracted concrete environmental stress load characteristics, load conditions are defined, including temperature, humidity, pressure, etc., to ensure that the load data matches the time series and spatial distribution of the point cloud model, a dynamic simulation model is created using finite element analysis (FEA) software (such as ANSYS, COMSOL), the three-dimensional point cloud model and environmental load characteristics are input, material properties (such as elastic modulus, Poisson's ratio, etc.) are defined to accurately reflect the physical properties of concrete, dynamic simulation is run, the stress and deformation response of concrete under different environmental conditions is observed, the simulation results, including stress distribution, displacement changes and any potential structural response, are recorded, and a suitable defect recognition algorithm is selected, such as a machine learning-based classifier (such as a support vector machine, a convolutional neural network) or a rule-based detector. The measurement method uses the dynamic simulation results as input data, including stress concentration, displacement anomaly, strain distribution and other characteristics, integrates historical defect data (such as cracks, voids, etc.) to improve the accuracy of the model, runs the defect recognition algorithm, analyzes the dynamic simulation model, identifies potential structural defects, records the identified defect type, location and impact degree, extracts the concrete structure defect data from the recognition results, including the geometric characteristics of the defects, location coordinates and their relationship with the environmental stress load, forms a structural defect data set for subsequent analysis and decision support, generates a detailed defect recognition report, records the identified defects and their characteristics, saves them in document or database format, combines the recognition results with the dynamic simulation model, forms a complete analysis report, and facilitates subsequent evaluation and decision-making.

[0044] Step S5: performing defect coupling evolution analysis on the concrete structure defect data, and reconstructing multiple time series trends to construct a defect evolution prediction trend curve;

[0045] In this embodiment, a suitable coupling analysis model (such as a multivariate regression model or a coupled dynamics model) is selected to analyze the mutual influence between different defects, determine the influencing factors that need to be considered, including environmental stress, material properties and defect attributes, run the coupling model, analyze the coupling effects between different defects, identify how the defects affect each other's expansion and evolution, record the change trend and coupling relationship of each defect under different conditions, organize the coupling evolution analysis results into a report, record the coupling influence of each defect and its consequences, and provide basic data for subsequent analysis. A suitable time series analysis method (such as ARIMA, seasonal decomposition, moving average, etc.) is selected to analyze the historical trend of defect data, organize the defect data obtained by the coupling evolution analysis into a time series data set, ensure that the data format is suitable for time series analysis, apply the selected time series analysis method, reconstruct the defect data trend, identify long-term and short-term trends and periodic changes, generate defect evolution prediction data, including the expected defect expansion rate and future defect status, plot the reconstructed defect evolution prediction data into a trend curve, and display the evolution of defects over time. Use visualization tools (such as Matplotlib or Tableau) to generate clear charts for easy understanding and analysis.

[0046] In this embodiment, step S6: performing crack resistance performance change analysis on the defect evolution prediction trend curve, and performing maintenance decision analysis to construct a concrete performance maintenance decision strategy.

[0047] In this embodiment, a suitable anti-cracking performance evaluation model (such as a stress-strain model or an empirical formula based on material properties) is selected, model input parameters are determined, including defect status, environmental conditions and material properties, defect evolution prediction trends are combined with anti-cracking performance models, future anti-cracking performance changes are calculated, anti-cracking performance evaluation values ​​at different time points are analyzed, an upward or downward trend in anti-cracking performance is identified, and the results of anti-cracking performance changes are compiled into a report to record performance change trends and their impacts. Based on the anti-cracking performance change trend, the maintenance needs of concrete are evaluated, areas that require maintenance or reinforcement are identified, key time nodes are determined, and when to perform maintenance to maximize the life of the structure is evaluated. A maintenance decision model is established, and multiple factors such as maintenance cost, construction difficulty, material selection and environmental impact are considered. The advantages and disadvantages of different maintenance strategies (such as reinforcement, repair or regular inspection) are determined. Different maintenance strategies are simulated to evaluate their impact on concrete performance. The cost-effectiveness ratio of different strategies at different time points is calculated to ensure the economy and effectiveness of the decision. According to the simulation results and the decision model, a final maintenance decision strategy is generated, the maintenance time, method and material are specified, and a detailed implementation plan is formulated to ensure the effective execution of maintenance work.

[0048] In this embodiment, the specific steps of step S1 are:

[0049] Step S11: Perform multi-directional CT scanning imaging on the concrete to be monitored to obtain multiple sets of internal microstructure images;

[0050] Step S12: reconstructing the multiple sets of internal microstructure images by multi-directional projection to construct an internal three-dimensional microstructure image;

[0051] Step S13: Perform component visual semantic recognition on the internal three-dimensional microstructure image to generate concrete component data;

[0052] Step S14: segmenting the internal three-dimensional microstructure image into different component regions based on the concrete composition data to generate a plurality of concrete region images;

[0053] Step S15: performing mechanism structure quantitative analysis on multiple concrete region images to generate mechanism structure parameters of different regions;

[0054] Wherein, step S15 is specifically as follows:

[0055] Performing brightness and darkness distribution analysis on multiple concrete area images to obtain internal three-dimensional brightness and darkness distribution information;

[0056] Quantitative structural analysis of multiple concrete area images is performed based on internal three-dimensional brightness distribution information to generate concrete cement ratio characteristics;

[0057] Performing morphological feature analysis on multiple concrete region images to generate component morphological feature data;

[0058] The concrete cement ratio characteristics and component morphology characteristics data are used to conduct quantitative analysis of the concrete mechanism structure to generate the mechanism structure parameters of different regions.

[0059] In this embodiment, a computed tomography (CT) device is used to ensure that it can perform high-resolution multi-directional scanning. The concrete sample to be monitored is placed in the CT scanner to ensure its stability. The concrete sample is CT scanned at different angles (such as 0°, 45°, 90°, etc.) to obtain multiple sets of internal microstructure images. The imaging parameters (such as scanning time and energy level) of each scan are ensured to be consistent to improve the comparability of the data. A suitable CT reconstruction algorithm (such as filtered back projection or iterative reconstruction method) is selected for image reconstruction. The multiple sets of internal microstructure images are used as input data for processing. The image data obtained by the multi-directional scanning is converted into a three-dimensional model through a projection reconstruction algorithm. Image denoising and enhancement technology is used to improve the quality and readability of the reconstructed image. The generated three-dimensional microstructure image is preprocessed (such as normalization, resizing, etc.). A suitable image segmentation and recognition algorithm (such as convolutional neural network CNN) is selected for component recognition. Features are extracted from the three-dimensional image to identify the main components of the concrete (such as cement, Aggregate, water, etc.), classify the extracted features, generate concrete component data, identify the proportion and distribution of each component, select a suitable image segmentation algorithm (such as K-means clustering or threshold segmentation) to perform regional segmentation on the three-dimensional image, and identify and segment the internal three-dimensional microstructure image according to the concrete component data. The results of the segmentation operation are converted into multiple concrete region images, the characteristics of each region are identified, and the mechanism structure parameters that need to be analyzed (such as porosity, particle distribution, hierarchical structure, etc.) are determined. The appropriate quantitative analysis algorithm (such as statistical analysis or morphological analysis) is selected to analyze each region, calculate the mechanism structure parameters of each concrete region image, extract relevant quantitative information, and generate mechanism structure parameter data for different regions, including the characteristic value and statistical information of each region.

[0060] The specific implementation steps of step S15 are:

[0061] The color image is converted into a grayscale image to simplify the brightness analysis. The brightness distribution histogram is generated by counting the grayscale value of each pixel, and the brightness mean and standard deviation of the image are calculated. The brightness information of each area is converted into a three-dimensional distribution model. A grid (such as a voxel grid) is usually used to represent the brightness of each point. Based on the obtained three-dimensional brightness distribution information, the cement and aggregate areas in the concrete are identified and extracted, and the proportion of the volume of the cement area to the total concrete volume is calculated as the cement ratio feature. The average brightness, distribution range and other statistical features of the cement area are calculated. The concrete image is processed using morphological algorithms (such as corrosion and expansion) to enhance the component features. The edge detection algorithm (such as Canny edge detection) is applied to extract the edge features of the concrete components. The shape features of the region (such as area, perimeter, roundness, etc.) are calculated. The concrete cement ratio features are combined with the component morphological feature data to form a comprehensive feature set. Based on the comprehensive features, a mechanism structure model of concrete is established, its internal structure and component distribution are analyzed, and the mechanism structure parameters of different regions, such as aggregate distribution uniformity and porosity, are calculated.

[0062] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0063] Step S21: Real-time environmental parameter monitoring of the concrete to be monitored is performed based on multiple sensor nodes to obtain concrete environmental perception parameters;

[0064] Step S22: performing temperature fluctuation analysis on concrete environment perception parameters to generate concrete temperature fluctuation data;

[0065] Step S23: performing regional temperature difference trend fitting on the concrete temperature fluctuation data to obtain a regional temperature difference trend curve;

[0066] Step S24: identifying the time-series humidity change of concrete environment perception parameters and extracting the time-series humidity change data of concrete;

[0067] Step S25: Perform environmental stress load mining on the temperature difference trend curve between regions and the concrete time series humidity change data to generate concrete environmental stress load characteristics.

[0068] In this embodiment, multiple sensor nodes are installed in the concrete area to be monitored, including temperature sensors, humidity sensors and pressure sensors, ensuring that the sensors are evenly distributed so as to comprehensively monitor the environmental changes of the concrete, configure sensors for real-time data collection, set the sampling frequency (such as every minute or every second), record the readings of each sensor, obtain the concrete environmental perception parameters (temperature, humidity, pressure, etc.), transmit the collected data to the central server or cloud platform in real time through wireless network or wired communication, extract temperature data from the database, perform preliminary cleaning, remove abnormal values ​​and noise (such as abnormal readings caused by equipment failure or external interference), calculate basic statistical indicators of temperature, including mean, standard deviation and maximum / minimum values, analyze the temperature change trend over time, identify the temperature fluctuation pattern (such as daytime / nighttime fluctuation), generate a concrete temperature fluctuation data report, including the fluctuation range, frequency and trend chart, for subsequent analysis, and classify the temperature data into different Region, ensure that the data of each region is independent, use curve fitting technology (such as polynomial fitting, spline interpolation) to analyze the temperature data of each region, generate the temperature difference trend curve between regions, through fitting, the temperature difference change trend between different regions can be identified, the fitted temperature difference trend curve is stored for visualization and further analysis, and the humidity data is extracted from the environmental perception parameters. Similarly, data cleaning is performed to process outliers, and time series analysis methods (such as sliding average or Fourier transform) are used to identify humidity changes, extract key features (such as peak values, cycles, etc.), and generate a concrete time series humidity change data report, including the trend and periodic characteristics of humidity changes. Use physical models or machine learning methods to analyze the impact of temperature difference and humidity changes on concrete stress. By establishing mathematical models (such as linear regression or finite element analysis), the environmental stress load characteristics of different regions are calculated, and concrete environmental stress load characteristic data is generated. The stress load parameters of each region are recorded and saved as a report.

[0069] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0070] Step S31: performing multi-frequency filtering and noise reduction on the internal three-dimensional microstructure image to obtain a filtered and noise-reduced microstructure image;

[0071] Step S32: performing texture detail feature analysis on the filtered denoised microstructure image based on the internal three-dimensional brightness distribution information to extract image texture detail features;

[0072] Step S33: performing cluster analysis on the image texture detail features to generate concrete texture cluster data, wherein the concrete texture cluster data includes concrete fissures, voids and cracks;

[0073] Step S34: Based on the mechanism structural parameters of different regions, regional structural three-dimensional point cloud modeling is performed on concrete fissures, voids and cracks to construct a concrete three-dimensional point cloud model.

[0074] In this embodiment, a suitable multi-frequency filter, such as a wavelet transform filter or a Gaussian filter, is selected according to the characteristics of the image, and the multi-frequency filtering technology is applied to reduce the noise of the image to remove high-frequency noise and retain important structural information. The filtering parameters (such as the frequency range) are adjusted as needed to optimize the noise reduction effect. Based on the microstructure image after filtering and noise reduction, the brightness distribution information of each pixel is calculated, and the texture detail features of the image are extracted using a texture analysis algorithm (such as a gray level co-occurrence matrix, a local binary pattern). Feature indicators such as contrast, entropy, uniformity, etc. are calculated to obtain a quantitative description of the texture. According to the data characteristics, a suitable clustering algorithm is selected, such as K-means clustering, hierarchical clustering or DBSCAN, and the obtained texture detail features are organized into a format suitable for clustering (usually feature Matrix), run the clustering algorithm, analyze the texture detail features of concrete, identify different texture types, generate concrete texture clustering data, including the clustering results of concrete cracks, voids and cracks, partition the concrete according to the mechanism structural parameters of different areas, ensure that the features of each area are independent, use a 3D reconstruction algorithm (such as structured light scanning or laser scanning) to perform 3D point cloud modeling of cracks, voids and cracks, map the features in the clustering results (such as crack position and shape) to 3D space, generate corresponding point cloud data, use point cloud processing software (such as PCL or MeshLab) to process the generated point cloud, construct a 3D point cloud model of concrete, and perform smoothing, simplification and meshing of the point cloud to obtain a clearer 3D model.

[0075] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S4. In this embodiment, the detailed implementation steps of step S4 include:

[0076] Step S41: performing time series load dynamics analysis on concrete environmental stress load characteristics, thereby obtaining stress load dynamics evolution law;

[0077] Step S42: dynamically simulate and evolve the concrete three-dimensional point cloud model according to the dynamic evolution law of stress load, and construct a dynamic twin evolution model;

[0078] Step S43: defining multiple time windows, and performing time series evolution simulation calculation on the dynamic twin evolution model based on the multiple time windows to obtain concrete time series evolution simulation data;

[0079] Step S44: identifying potential structural defects of the concrete time-series evolution simulation data and extracting concrete structural defect data.

[0080] In this embodiment, a suitable dynamic model (such as a linear elastic model or a nonlinear model) is selected to describe the stress-strain relationship of concrete, and a finite element analysis (FEA) method is applied to simulate the response of concrete under different loads. Through time series analysis, the stress load changes at different time points are calculated, and its dynamic evolution law (such as periodic fluctuations, mutations, etc.) is identified. A chart or curve is used to display the change trend of stress load over time, and a stress load dynamic evolution law report is generated. According to the obtained stress load dynamic evolution law, a dynamic twin evolution model is designed, and the input parameters (such as time, load, material properties) and output response (such as displacement, strain) of the model are determined. A dynamic simulation is performed using simulation software (such as ANSYS, COMSOL, etc.), load data is input, the model is run, the dynamic response of concrete under different load conditions is observed, and its evolution process is recorded. According to the service life of concrete and the characteristics of load changes, multiple time windows (such as short-term, medium-term, Long-term), each time window should consider different external conditions and environmental influences, and perform time-series evolution simulation calculations on the dynamic twin evolution model. In each time window, different load conditions are applied to simulate the dynamic response of concrete, and the simulation results of each time window are collected to generate concrete time-series evolution simulation data, including displacement, strain, stress distribution and other information. Key features (such as stress concentration and displacement anomaly) are extracted from the obtained time-series evolution simulation data, and statistical analysis is performed using data processing and analysis tools (such as MATLAB, Python, etc.) to identify potential structural defects. Machine learning or deep learning algorithms (such as support vector machines and convolutional neural networks) are used to train and classify time-series data to automatically identify structural defects. Combined with previous clustering analysis results, defect types (such as cracks, voids, etc.) are further confirmed and classified to generate a concrete structure defect data report, recording the identified defect type, location and severity, and saving it for subsequent processing.

[0081] In this embodiment, the specific steps of step S5 are:

[0082] Step S51: diagnose the defect type of the concrete structure defect data to obtain the structural defect type;

[0083] Step S52: performing defect location analysis on the concrete structure defect data, thereby generating structural defect location points;

[0084] Step S53: performing defect expansion analysis on each type of structural defect one by one, and generating defect expansion evolution characteristics of all types;

[0085] Step S54: performing defect location marking on the dynamic twin evolution model based on the structural defect location point, thereby obtaining a defect location evolution model;

[0086] Step S55: performing defect coupling evolution analysis on the defect location evolution model according to the extended evolution characteristics of all types of defects, thereby obtaining defect coupling evolution effects;

[0087] Step S56: performing multi-period defect damage evolution prediction on the concrete structure defect data based on the defect coupling evolution effect, and generating defect evolution prediction trends in multiple time periods;

[0088] Step S57: reconstruct the defect evolution prediction trends in multiple time periods into multiple time series trends to construct a defect evolution prediction trend curve.

[0089] In this embodiment, a suitable defect diagnosis model (such as a decision tree, random forest or neural network) is selected for classification, and the diagnosis model is trained using a labeled defect data set to improve classification accuracy. The trained model is used to analyze the newly acquired defect data, identify the defect type (such as cracks, gaps, peeling, etc.), save the type of each defect, form a structural defect type data set, select a suitable positioning algorithm (such as geometric positioning, image processing algorithm or machine learning-based method), use defect features (such as coordinates, shape) to locate and analyze each defect, combine image processing technology to extract the location information of the defect, record the exact location of each defect, generate structural defect positioning point data, and save the positioning point data for subsequent analysis and model marking. For each defect type, analyze its expansion characteristics under different conditions (such as environmental impact, load change), analyze each defect type one by one, simulate its expansion process, record the expansion range and speed, use finite element analysis or other numerical simulation methods to evaluate the expansion impact of the defect, generate expansion evolution feature data of all types of defects, form a feature report, and mark the dynamic twin model based on the generated defect positioning points. Record the location and type of defects to ensure clear visualization effects, generate a defect location evolution model, save the marked dynamic model, construct a defect coupling evolution model based on the obtained defect expansion evolution characteristics, analyze the mutual influence between different defects and their comprehensive influence on the performance of concrete structures, apply numerical simulation technology to evaluate the impact of defect coupling on the overall structure, generate a defect coupling evolution effect data report, record the coupling influence between each defect, select a suitable time series prediction model (such as ARIMA, LSTM) to predict the evolution of defect damage, input relevant data for multi-period prediction based on the defect coupling evolution effect, calculate the defect damage evolution trend in different time periods, generate defect evolution prediction results, save defect evolution prediction trend data for multiple time periods, select a suitable trend reconstruction method (such as spline interpolation, smooth curve fitting) to reconstruct the prediction results for multiple time periods, organize and process the defect evolution prediction results for each time period to ensure data consistency, generate a defect evolution prediction trend curve, depict the overall trend of defect development and change, and use visualization tools (such as Matplotlib or Tableau) to display the defect evolution prediction trend curve for easy understanding and analysis.

[0090] In this embodiment, the specific steps of step S6 are:

[0091] Step S61: performing multi-point sampling on the defect evolution prediction trend curve to obtain multiple defect evolution prediction points;

[0092] Step S62: extracting timestamps of multiple defect evolution prediction points, performing time series interval calculation on the timestamps, and generating prediction point time series intervals;

[0093] Step S63: evaluating the current concrete anti-cracking performance at multiple defect evolution prediction points to obtain anti-cracking performance evaluation values ​​of multiple sampling points;

[0094] Step S64: performing an anti-crack performance change trend analysis on the anti-crack performance evaluation values ​​of multiple sampling points based on the prediction point time series interval, thereby generating anti-crack performance trend data of the concrete to be monitored;

[0095] Step S65: performing comprehensive performance life calculation on the anti-cracking performance status data of the concrete to be monitored to generate a comprehensive performance evaluation value of the concrete to be monitored;

[0096] Step S66: Perform maintenance decision analysis based on the comprehensive performance evaluation value of the concrete to be monitored, and construct a concrete performance maintenance decision strategy.

[0097] In this embodiment, the number and interval of sampling points are determined (such as uniform sampling or sampling by key points), multiple defect evolution prediction points are extracted from the trend curve according to the set strategy, the prediction value of each point and the corresponding timestamp are recorded, the multiple defect evolution prediction point data obtained by sampling are saved to form a data set, the time interval between adjacent prediction points is calculated, and recorded as time series interval data, a simple time difference formula (such as timestamp2 - timestamp1) is used for calculation, a suitable anti-cracking performance evaluation model (such as a stress-strain model or an empirical formula) is selected, and the defect evolution prediction point data sampled in step S61 is used as input to evaluate the anti-cracking performance, and the anti-cracking performance evaluation value of each sampling point is calculated, including indicators such as safety factor and stress state, the evaluation results of all sampling points are summarized, and the anti-cracking performance evaluation values ​​of multiple sampling points are saved as a data set, and a statistical analysis method (such as linear regression or moving average) is used to analyze the change trend of the anti-cracking performance evaluation value over time, identify the rising or falling trend of the anti-cracking performance, and calculate the change rate, so as to form the anti-cracking performance situation data of the concrete to be monitored, and record the change of the anti-cracking performance situation, select a suitable comprehensive performance life calculation model (such as a model based on fatigue analysis), use the obtained anti-cracking performance status data as input, perform performance life calculation, use the model to calculate the comprehensive performance evaluation value of the concrete to be monitored, consider the impact of different defects on the structural life, save the generated comprehensive performance evaluation value of the concrete to be monitored, and establish a maintenance decision analysis model (such as a model based on cost-benefit analysis) based on the comprehensive performance evaluation value of the concrete to be monitored. Integrate the comprehensive performance evaluation value with historical data, environmental conditions and maintenance plans, evaluate the effects of different maintenance strategies, propose maintenance decision strategies, including recommended maintenance time, methods and materials, etc., and optimize based on the comprehensive performance evaluation value.

[0098] The present invention also provides a concrete anti-cracking performance simulation monitoring device, comprising:

[0099] The mechanism structure module is used to obtain multiple sets of internal microstructure images; segment the multiple sets of internal microstructure images into different component regions, and perform mechanism structure quantitative analysis to generate mechanism structure parameters of different regions;

[0100] The stress load module is used to monitor the environmental parameters of the concrete to be monitored in real time based on multiple sensor nodes to obtain the concrete environmental perception parameters; the environmental stress load mining of the concrete environmental perception parameters is carried out to generate the concrete environmental stress load characteristics;

[0101] The 3D point cloud modeling module is used to perform multi-frequency filtering and noise reduction on the internal 3D microstructure image based on the mechanism structural parameters of different regions, and to perform regional structure 3D point cloud modeling to construct a 3D point cloud model of concrete;

[0102] The dynamic simulation evolution module is used to dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics, and to construct a dynamic twin evolution model; to identify potential structural defects in the dynamic twin evolution model and to extract concrete structural defect data;

[0103] Defect prediction module, used to analyze the defect coupling evolution of concrete structure defect data, reconstruct multiple time series trends, and construct defect evolution prediction trend curve;

[0104] The comprehensive performance evaluation module is used to analyze the change trend of the anti-crack performance of the defect evolution prediction trend curve, conduct maintenance decision analysis, and build a concrete performance maintenance decision strategy.

[0105] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above-mentioned methods for simulating and monitoring the anti-cracking performance of concrete when executing the computer program.

[0106] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for simulating and monitoring the anti-cracking performance of concrete are implemented.

[0107] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0108] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks.

[0109] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0110] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0111] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A simulation monitoring method for concrete crack resistance, characterized in that: The following steps are involved: Step S1: acquiring multiple sets of internal microstructure images; segmenting the multiple sets of internal microstructure images into different component regions, and performing mechanism structure quantitative analysis to generate mechanism structure parameters of different regions; Step S2: Based on the multi-sensor nodes, real-time environmental parameter monitoring is performed on the concrete to be monitored to obtain concrete environmental perception parameters; environmental stress load mining is performed on the concrete environmental perception parameters to generate concrete environmental stress load characteristics; The specific steps of step S2 are: Step S21: Real-time environmental parameter monitoring of the concrete to be monitored is performed based on multiple sensor nodes to obtain concrete environmental perception parameters; Step S22: performing temperature fluctuation analysis on concrete environment perception parameters to generate concrete temperature fluctuation data; Step S23: performing regional temperature difference trend fitting on the concrete temperature fluctuation data to obtain a regional temperature difference trend curve; Step S24: identifying the time-series humidity change of concrete environment perception parameters and extracting the time-series humidity change data of concrete; Step S25: Perform environmental stress load mining on the temperature difference trend curve between regions and the concrete time series humidity change data to generate concrete environmental stress load characteristics; Step S3: Based on the mechanism structural parameters of different regions, multi-frequency filtering is performed on the internal three-dimensional microstructure image to reduce noise, and regional structure three-dimensional point cloud modeling is performed to construct a three-dimensional point cloud model of concrete; the specific steps of step S3 are: Step S31: performing multi-frequency filtering and noise reduction on the internal three-dimensional microstructure image to obtain a filtered and noise-reduced microstructure image; Step S32: performing texture detail feature analysis on the filtered denoised microstructure image based on the internal three-dimensional brightness distribution information to extract image texture detail features; Step S33: performing cluster analysis on the image texture detail features to generate concrete texture cluster data, wherein the concrete texture cluster data includes concrete fissures, voids and cracks; Step S34: performing regional structural three-dimensional point cloud modeling of concrete fissures, voids and cracks based on the mechanism structural parameters of different regions, and constructing a concrete three-dimensional point cloud model; Step S4: dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics to construct a dynamic twin evolution model; identify potential structural defects in the dynamic twin evolution model to extract concrete structural defect data; the specific steps of step S4 are: Step S41: performing time series load dynamics analysis on concrete environmental stress load characteristics, thereby obtaining stress load dynamics evolution law; Step S42: dynamically simulate and evolve the concrete three-dimensional point cloud model according to the dynamic evolution law of stress load, and construct a dynamic twin evolution model; Step S43: defining multiple time windows, and performing time series evolution simulation calculation on the dynamic twin evolution model based on the multiple time windows to obtain concrete time series evolution simulation data; Step S44: identifying potential structural defects of concrete time-series evolution simulation data and extracting concrete structural defect data; Step S5: Conduct defect coupling evolution analysis on the concrete structure defect data, reconstruct multiple time series trends, and construct a defect evolution prediction trend curve; the specific steps of step S5 are: Step S51: diagnose the defect type of the concrete structure defect data to obtain the structural defect type; Step S52: performing defect location analysis on the concrete structure defect data, thereby generating structural defect location points; Step S53: performing defect expansion analysis on each type of structural defect one by one, and generating defect expansion evolution characteristics of all types; Step S54: performing defect location marking on the dynamic twin evolution model based on the structural defect location point, thereby obtaining a defect location evolution model; Step S55: performing defect coupling evolution analysis on the defect location evolution model according to the extended evolution characteristics of all types of defects, thereby obtaining defect coupling evolution effects; Step S56: performing multi-period defect damage evolution prediction on the concrete structure defect data based on the defect coupling evolution effect, and generating defect evolution prediction trends in multiple time periods; Step S57: reconstructing the defect evolution prediction trends in multiple time periods into multiple time series trends, and constructing a defect evolution prediction trend curve; Step S6: Analyze the change trend of the crack resistance performance of the defect evolution prediction trend curve, and perform maintenance decision analysis to build a concrete performance maintenance decision strategy.

2. The method for simulating and monitoring the anti-cracking performance of concrete according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Perform multi-directional CT scanning imaging on the concrete to be monitored to obtain multiple sets of internal microstructure images; Step S12: reconstructing the multiple sets of internal microstructure images by multi-directional projection to construct an internal three-dimensional microstructure image; Step S13: Perform component visual semantic recognition on the internal three-dimensional microstructure image to generate concrete component data; Step S14: segmenting the internal three-dimensional microstructure image into different component regions based on the concrete composition data to generate a plurality of concrete region images; Step S15: performing mechanism structure quantitative analysis on multiple concrete region images to generate mechanism structure parameters of different regions; Wherein, step S15 is specifically as follows: Performing brightness and darkness distribution analysis on multiple concrete area images to obtain internal three-dimensional brightness and darkness distribution information; Quantitative structural analysis of multiple concrete area images is performed based on internal three-dimensional brightness distribution information to generate concrete cement ratio characteristics; Performing morphological feature analysis on multiple concrete region images to generate component morphological feature data; The concrete cement ratio characteristics and component morphology characteristics data are used to conduct quantitative analysis of the concrete mechanism structure to generate the mechanism structure parameters of different regions.

3. The method for simulating and monitoring the anti-cracking performance of concrete according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing multi-point sampling on the defect evolution prediction trend curve to obtain multiple defect evolution prediction points; Step S62: extracting timestamps of multiple defect evolution prediction points, performing time series interval calculation on the timestamps, and generating prediction point time series intervals; Step S63: evaluating the current concrete anti-cracking performance at multiple defect evolution prediction points to obtain anti-cracking performance evaluation values ​​of multiple sampling points; Step S64: performing an anti-crack performance change trend analysis on the anti-crack performance evaluation values ​​of multiple sampling points based on the prediction point time series interval, thereby generating anti-crack performance trend data of the concrete to be monitored; Step S65: performing comprehensive performance life calculation on the anti-cracking performance status data of the concrete to be monitored to generate a comprehensive performance evaluation value of the concrete to be monitored; Step S66: Perform maintenance decision analysis based on the comprehensive performance evaluation value of the concrete to be monitored, and construct a concrete performance maintenance decision strategy.

4. A concrete crack resistance performance simulation monitoring device, characterized in that: The method for implementing the concrete anti-cracking performance simulation monitoring method according to claim 1 comprises: The mechanism structure module is used to obtain multiple sets of internal microstructure images; segment the multiple sets of internal microstructure images into different component regions, and perform mechanism structure quantitative analysis to generate mechanism structure parameters of different regions; The stress load module is used to monitor the environmental parameters of the concrete to be monitored in real time based on multiple sensor nodes to obtain the concrete environmental perception parameters; the environmental stress load mining of the concrete environmental perception parameters is carried out to generate the concrete environmental stress load characteristics; Specifically used for: real-time environmental parameter monitoring of concrete to be monitored based on multi-sensor nodes to obtain concrete environmental perception parameters; temperature fluctuation analysis of concrete environmental perception parameters to generate concrete temperature fluctuation data; regional temperature difference trend fitting of concrete temperature fluctuation data to obtain inter-regional temperature difference trend curve; time-series humidity change identification of concrete environmental perception parameters to extract concrete time-series humidity change data; environmental stress load mining of inter-regional temperature difference trend curve and concrete time-series humidity change data to generate concrete environmental stress load characteristics; The 3D point cloud modeling module is used to perform multi-frequency filtering and noise reduction on the internal 3D microstructure image based on the mechanism structural parameters of different regions, and to perform regional structure 3D point cloud modeling to construct a 3D point cloud model of concrete; Specifically used for: performing multi-frequency filtering and denoising on the internal three-dimensional microstructure image to obtain a filtered and denoised microstructure image; performing texture detail feature analysis on the filtered and denoised microstructure image based on the internal three-dimensional brightness distribution information to extract image texture detail features; performing cluster analysis on the image texture detail features to generate concrete texture clustering data, wherein the concrete texture clustering data includes concrete cracks, voids and cracks; performing regional structural three-dimensional point cloud modeling on concrete cracks, voids and cracks based on the mechanism structural parameters of different regions to construct a concrete three-dimensional point cloud model; The dynamic simulation evolution module is used to dynamically simulate and evolve the concrete three-dimensional point cloud model according to the concrete environmental stress load characteristics, and to construct a dynamic twin evolution model; to identify potential structural defects in the dynamic twin evolution model and to extract concrete structural defect data; Specifically used for: performing time series load dynamics analysis on concrete environmental stress load characteristics, thereby obtaining stress load dynamics evolution law; performing dynamic simulation evolution on concrete three-dimensional point cloud model according to stress load dynamics evolution law, and constructing dynamic twin evolution model; defining multiple time windows, and performing time series evolution simulation calculation on dynamic twin evolution model based on the multiple time windows, and obtaining concrete time series evolution simulation data; identifying potential structural defects on concrete time series evolution simulation data, and extracting concrete structure defect data; Defect prediction module, used to analyze the defect coupling evolution of concrete structure defect data, reconstruct multiple time series trends, and construct defect evolution prediction trend curve; Specifically used for: diagnosing the defect type of concrete structure defect data to obtain the structural defect type; performing defect location analysis on concrete structure defect data to generate structural defect location points; performing defect expansion analysis on structural defect types one by one to generate all types of defect expansion evolution characteristics; performing defect location marking on the dynamic twin evolution model based on the structural defect location points to obtain the defect location evolution model; performing defect coupling evolution analysis on the defect location evolution model according to all types of defect expansion evolution characteristics to obtain the defect coupling evolution effect; performing multi-period defect damage evolution prediction on concrete structure defect data based on the defect coupling evolution effect to generate defect evolution prediction trends for multiple time periods; performing multi-time series trend reconstruction on the defect evolution prediction trends for multiple time periods to construct defect evolution prediction trend curves; The comprehensive performance evaluation module is used to analyze the change trend of the anti-crack performance of the defect evolution prediction trend curve, conduct maintenance decision analysis, and build a concrete performance maintenance decision strategy.

5. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method for simulating and monitoring the anti-cracking performance of concrete according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for simulating and monitoring the anti-cracking performance of concrete according to any one of claims 1 to 3 are implemented.

Images