A BIM-based highway construction expansion joint detection management method and system

Abstract

The present invention relates to the technical field of highway expansion joint detection and management, and more particularly to a BIM-based highway construction expansion joint detection and management method and system. The method comprises the following steps: obtaining highway construction plan data; performing highway structural semantic extraction on the highway construction plan data to obtain highway construction structural semantic data; constructing a three-dimensional digital model of the highway construction structural semantic data to generate a highway construction BIM model; and performing construction simulation on the highway construction BIM model to generate highway construction simulation data. This invention improves the comprehensiveness and real-time performance of BIM-based highway construction expansion joint detection and management through systematic information integration, real-time monitoring, scientific inspections, data-driven damage assessment and repair strategy development, and flexible management process adjustments.

Description

Technical Field

[0001] The present invention relates to the technical field of highway deformation joint detection and management, and in particular to a BIM-based highway construction deformation joint detection and management method and system. Background Art

[0002] In the early days, highway construction relied primarily on traditional design drawings and manual inspections, resulting in poor information transfer and data sharing during construction, impacting project quality and safety. With the rapid development of computer technology, Building Information Modeling (BIM) technology has gradually emerged. Through digital modeling, BIM provides a visual platform for project design, construction, and operations, effectively integrating information from multiple sources. In the mid-2000s, BIM technology gained widespread application in the construction sector and subsequently expanded to highway construction. In recent years, the rapid development of sensor technology and the Internet of Things has enabled real-time data collection and analysis. Combining BIM with sensor data enables dynamic monitoring of expansion joints. By creating a three-dimensional model of expansion joints and combining it with real-time monitoring data, managers can promptly identify changes in expansion joints and formulate appropriate maintenance strategies, thereby improving highway safety and durability. However, existing technologies often lag in identifying areas prone to expansion joints during the construction phase, failing to detect potential problems in a timely manner. Furthermore, traditional inspection plans often lack specificity, resulting in wasted resources or missed inspections. Consequently, the detection and management of expansion joint damage is fragmented and lacks real-time effectiveness. Summary of the Invention

[0003] Based on this, it is necessary to provide a BIM-based highway construction deformation joint detection and management method and system to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a BIM-based highway construction expansion joint detection and management method is provided, the method comprising the following steps:

[0005] Step S1: Obtain highway construction plan data; perform highway structure semantic extraction on the highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model;

[0006] Step S2: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; performing virtual reality identification of deformation joint-prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint-prone area identification data and deformation joint detection area data; performing regional matching inspection division on the virtual deformation joint-prone area identification data and the deformation joint detection area data to generate a first deformation joint inspection plan and a second deformation joint inspection plan;

[0007] Step S3: Periodic inspection data collection is performed on the highway construction BIM model using the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; expansion joint damage assessment is performed on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; expansion joint repair strategies are formulated based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies;

[0008] Step S4: Update the deformation joint status of the highway construction BIM model according to the deformation joint abnormality repair strategy, and generate deformation joint status inspection update data; adjust the inspection management process based on the deformation joint status inspection update data, and generate a highway construction deformation joint inspection management adjustment plan to execute the highway construction deformation joint inspection management operation.

[0009] This invention lays the foundation for subsequent processing by initially collecting all construction-related data. By analyzing the proposed data, structural information from highway construction is extracted, enabling a clear definition of the highway's components and functions. The extracted structural semantic data is converted into a BIM model, providing a visual three-dimensional representation, facilitating subsequent construction and management. By simulating the construction process, it is possible to predict potential problems and rationally allocate resources, improving construction efficiency. Virtual reality technology is used to identify problem areas where expansion joints may occur, enhancing the ability to proactively identify potential risks. Subdividing inspection areas into different inspection plans improves the relevance and effectiveness of inspections, providing a scientific basis for subsequent periodic inspections. Regular inspection data collection ensures dynamic monitoring of highway conditions. The collected data is analyzed to generate damage assessment data, enabling rapid and accurate identification of expansion joint damage. Based on the damage assessment results, a corresponding repair strategy is formulated to ensure rapid response and resolution when problems occur. The BIM model status is updated according to the repair strategy, ensuring the model's timeliness and accuracy, providing the latest data for subsequent decision-making. Based on the latest status data, the detection management process is optimized, management efficiency is improved, and it is ensured that the deformation joint detection during highway construction is always in the best condition. Through systematic construction simulation and real-time inspections, potential risks can be identified at an early stage, thereby reducing the probability of accidents. The implementation of each step provides reliable data support for subsequent decision-making, ensuring the scientificity and rationality of the decision. By recycling data, resource waste is reduced, management and construction efficiency is improved, and costs are reduced. Therefore, the present invention improves the comprehensiveness and real-time nature of BIM-based highway construction deformation joint detection management through systematic information integration, real-time monitoring, scientific inspections, data-driven damage assessment and repair strategy formulation, and flexible management process adjustments.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtaining highway construction plan data;

[0012] Step S12: performing data preprocessing on the highway construction plan data to generate standard highway construction plan data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0013] Step S13: extracting highway structure semantics from the standard highway construction plan to obtain highway construction structure semantic data;

[0014] Step S14: Use BIM technology to construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model.

[0015] By acquiring highway construction plan data, the present invention ensures that the initial data source for project construction is authentic and comprehensive, providing a fundamental guarantee for subsequent digital processing. This step lays the data foundation for the entire process. The data cleaning and standardization process can remove redundant and erroneous information in the data and fill in missing values to ensure data consistency and integrity. By generating standardized highway construction plan data, the accuracy and reliability of the subsequent analysis and modeling processes are guaranteed. By performing semantic extraction on standard data, the structural information in the highway construction plan can be better understood. This step can effectively convert complex construction plan data into recognizable highway structure semantic information, providing a precise structural foundation for subsequent model construction. Utilizing BIM (Building Information Modeling) technology, the semantic data of highway construction is converted into a three-dimensional digital model, generating a highway construction BIM model. This step enables the project to move from conceptual design to actual visualization, enabling better construction planning and management, and improving the efficiency and quality of the construction process. This step S1 not only improves the data accuracy and availability of highway construction plans through standardized data processing, highway structure semantic extraction, and BIM modeling, but also enables projects to more intuitively manage and optimize the highway construction process in a 3D visualization environment. This helps reduce design errors, improve construction efficiency, and support subsequent operations, maintenance, and management.

[0016] Preferably, step S14 includes the following steps:

[0017] Step S141: classifying highway construction structure semantic data into functional structural components to generate highway construction functional facility classification data, wherein the functional structural component classification includes road structure classification, bridge structure classification, tunnel structure classification, and roadbed structure classification;

[0018] Step S142: performing IFC standard format conversion on the highway construction functional facility classification data to generate highway construction format conversion data; performing structural semantic mapping on the highway construction format conversion data using BIM technology to generate highway construction structural semantic mapping data;

[0019] Step S143: performing 3D geometric modeling based on the highway construction structure semantic mapping data to generate highway construction 3D geometric modeling data; performing GIS geographic information integration on the highway construction 3D geometric modeling data to generate a preliminary 3D structural model;

[0020] Step S144: Associating model components of the preliminary three-dimensional structure model based on the highway construction structure semantic data to generate three-dimensional structure attribute association data; inputting the three-dimensional structure attribute association data into the preliminary three-dimensional structure model to fill in model component information to generate a highway construction BIM model.

[0021] By classifying highway construction structural semantic data, this invention can categorize complex highway facilities by functional structure (roads, bridges, tunnels, roadbeds, etc.), generating clear categorized data. This step ensures precise differentiation of the structural attributes of each facility, facilitating subsequent modeling and analysis, and improving the efficiency and accuracy of systematic processing. By converting the highway construction functional facility classification data into the internationally recognized IFC (Industry Foundation Classes) standard format, data interoperability between different systems is achieved. Subsequently, structural semantic mapping is performed using BIM technology to accurately match the semantic information to the structural model. This not only improves data standardization and compatibility but also ensures the integrity and usability of the semantic information. Based on 3D geometric modeling, spatial geographic information integration using GIS (Geographic Information System) enables the positioning and association of highway construction models within their actual geographic environment. This step integrates the highway construction model with its real-world environment, generating a preliminary 3D structural model that incorporates not only 3D geometric information but also spatial positioning and geographic attributes, significantly enhancing the model's realism and practicality. Model component association processing based on structural semantic data ensures correct attribute associations between components within the 3D model. The final highway construction BIM model is then generated by filling in the attribute information of the model components. This step not only achieves the digitization and semantic association of the components but also provides rich attribute information for subsequent project management, construction planning, and maintenance, further enhancing the integrity and practicality of the BIM model. Through functional classification, standardized conversion, 3D modeling, geographic information integration, and information filling, an accurate, comprehensive, and visual highway construction BIM model is gradually established. This BIM model not only reflects the geometric structure of the highway construction but also integrates rich semantic, functional, and geographic information, facilitating efficient collaboration and management during the design, construction, and maintenance processes. This will help optimize the project's construction process, improve construction efficiency, and reduce potential errors and rework.

[0022] Preferably, step S2 includes the following steps:

[0023] Step S21: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; identifying virtual deformation joint prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint prone area identification data;

[0024] Step S22: Based on the virtual deformation joint prone area identification data, a total station is used to perform actual deformation joint detection, thereby generating actual deformation joint detection data; the actual deformation joint detection data is divided into deformation joint areas, thereby generating deformation joint detection area data;

[0025] Step S23: performing regional matching calculation on the deformation joint detection area data and the virtual deformation joint prone area identification data to obtain the deformation joint area detection matching degree;

[0026] Step S24: Compare the deformation joint area detection matching degree with the preset area detection matching threshold. When the deformation joint area detection matching degree is less than or equal to the preset area detection matching threshold, a first deformation joint inspection plan is generated; when the deformation joint area detection matching degree is greater than the preset area detection matching threshold, a second deformation joint inspection plan is generated.

[0027] By performing construction simulation on the highway construction BIM model, the present invention can predict and analyze potential problems in the construction process in advance, especially areas prone to deformation joints. Virtual deformation joint prone area identification can detect parts of the structure that are deformed before construction, helping to take preventive measures in advance, which helps to reduce the risk of deformation joints in actual construction and improve construction accuracy and safety. Based on the virtual identification results, the use of precision equipment such as total stations to perform real-world deformation joint detection can combine virtual simulation with real-world detection to ensure the accuracy of the detection results. By dividing the deformation joint detection data into regions, the specific location and range of the deformation joint can be clearly defined, which facilitates construction management and subsequent processing. The degree of matching between the deformation joint detection area data and the virtual identification data can be calculated to evaluate the degree of difference between the virtual simulation and the real-world detection. This step can effectively verify the accuracy of the virtual prediction, help discover errors or omissions in the virtual model, and provide a basis for subsequent construction decisions. According to the matching results, compared with the preset regional detection matching threshold, an inspection plan can be dynamically generated. A low match indicates a significant discrepancy between the virtual prediction and reality, necessitating more frequent and rigorous inspections (the first inspection plan). A high match indicates accurate virtual predictions, necessitating a reduced inspection frequency (the second inspection plan). This intelligent inspection plan generation mechanism not only improves inspection efficiency but also reduces unnecessary resource waste. Through construction simulation, real-world testing, match calculation, and intelligent inspection plan development, precise inspection and management of expansion joints during both virtual and real-world construction processes are achieved. This step proactively identifies potential risks, improving construction quality and safety. Furthermore, the inspection plan dynamically generated based on the matching results enhances work efficiency, reduces rework and waste during construction, and provides a reliable guarantee for the smooth implementation of the project.

[0028] Preferably, performing construction simulation on a highway construction BIM model includes:

[0029] Decompose construction tasks on highway construction BIM model data to generate construction task planning data; perform resource consumption analysis on construction task planning data to generate resource usage analysis data; perform resource allocation optimization processing on resource usage analysis data to generate construction resource optimization data;

[0030] Perform timeline correlation processing on construction task planning data based on construction resource optimization data to generate construction schedule data; perform three-dimensional construction simulation on construction schedule data to generate construction dynamic simulation data; perform construction collision detection on construction dynamic simulation data to generate construction simulation conflict detection data;

[0031] The construction dynamic simulation data and the construction simulation conflict detection data are integrated to generate highway construction simulation data.

[0032] By decomposing construction tasks within highway construction BIM model data, this invention can refine the entire construction process, breaking down complex construction tasks into specific, actionable tasks. The resulting construction task planning data helps clarify the requirements and objectives of each construction phase, ensuring that construction steps proceed in an orderly manner and reducing confusion and work delays during construction. Resource consumption analysis quantifies resource requirements (such as materials, equipment, and manpower) for each construction task, generating detailed resource usage analysis data. By optimizing resource allocation based on this data, resource waste can be reduced, costs can be lowered, and resources can be rationally allocated. The resulting construction resource optimization data enables smooth project execution even under resource constraints, improving overall construction efficiency and effectiveness. Timeline correlation processing based on the optimized resource allocation data generates construction schedule data that accurately plans the timing of each task. Reasonable time management not only shortens construction periods but also avoids time conflicts and delays between tasks, ensuring that construction progress is on schedule and enhancing project time management capabilities. Three-dimensional construction simulation of the construction schedule dynamically presents the construction process, providing intuitive progress display and simulation results. The dynamic construction simulation data generated through simulation allows for a comprehensive assessment of construction feasibility and potential risks. Clash detection in construction simulations can proactively identify conflicts or issues that may arise during construction (such as clashes between structural components or restricted equipment movement). The resulting construction simulation clash detection data provides a valuable reference for further optimizing the construction process. Integrating dynamic construction simulation data with clash detection data allows for comprehensive evaluation of simulation results and generation of final highway construction simulation data. This comprehensive data provides valuable insights for actual project construction, ensuring an efficient and conflict-free construction process and minimizing potential construction risks. Through steps such as task decomposition and planning, resource analysis and optimization, schedule development, 3D dynamic simulation, and clash detection, the construction simulation process comprehensively assesses project feasibility and risk. This not only improves the accuracy of construction plans, reduces resource waste and time delays, but also proactively identifies and addresses construction conflicts, ensuring an efficient and smooth construction process. The resulting construction simulation data provides a reliable basis for actual construction, facilitating smooth project implementation and management optimization.

[0033] Preferably, step S23 includes the following steps:

[0034] Step S231: Binarizing the deformation joint detection region data and the virtual deformation joint prone region identification data to generate deformation joint detection region binary data and virtual deformation joint prone region binary data;

[0035] Step S232: performing pixel-by-pixel intersection region comparison calculation on the binary data of the deformation joint detection region and the binary data of the virtual deformation joint prone region to generate intersection region data; performing region overlapping pixel calculation on the intersection region data to obtain the region intersection area;

[0036] Step S233: performing pixel-by-pixel union region comparison calculation on the binary data of the deformation joint detection region and the binary data of the virtual deformation joint prone region to generate union region data; performing regional non-overlapping pixel calculation on the union region data to obtain the area of the region union;

[0037] Step S234: Calculate the intersection-and-union ratio of the region intersection area and the region union area, thereby generating a deformation joint region detection matching degree.

[0038] By binarizing the deformation joint detection region data and virtual deformation joint-prone region identification data, the present invention simplifies complex regional data into binary form, making subsequent calculations more efficient and accurate. Generating binary data for the deformation joint detection region and the virtual deformation joint-prone region clearly isolates regions of interest and lays the foundation for subsequent pixel-level comparisons, improving data operability and analysis efficiency. By performing pixel-by-pixel intersection area comparison on the binarized data, the overlap between the virtual identification and real-world detection data can be accurately determined. The generation of intersection area data helps assess the consistency between the actual deformation joint and the predicted region, while the calculation of the intersection area quantifies this consistency, providing a basis for further judgment and optimization. This process can reveal potential errors or undetected areas, thereby improving matching accuracy. The pixel-by-pixel union area comparison calculation helps determine the maximum value of the entire deformation joint coverage, encompassing both the virtual predicted region and the real-world detection region. The generated union area data provides the basis for subsequent regional difference analysis, while the calculation of the union area quantifies the non-overlapping areas between the virtual and real-world data. Through this process, the coverage of virtual predictions can be better evaluated and the virtual model can be optimized. The final intersection-to-union ratio calculation step generates the expansion joint area detection matching degree by calculating the ratio of the intersection area to the union area. This ratio can accurately reflect the degree of fit between the virtual prediction and the actual detection. Through the quantitative representation of the matching degree, the prediction accuracy of the virtual model can be intuitively judged, providing data support for subsequent construction decisions and providing direction for optimizing virtual modeling. By binarizing the expansion joint detection area data and the virtual expansion joint prone area data, performing intersection and union calculations, and performing intersection-to-union ratio analysis, accurate comparison and matching degree evaluation of virtual and real data are achieved. This step not only improves the accuracy of detection, but also quantifies the degree of match between virtual predictions and actual detection, helping to identify potential risk areas and errors. The generated matching degree data provides a strong basis for subsequent construction optimization, risk management, and decision-making, ultimately improving safety and efficiency during the construction process.

[0039] Preferably, step S24 includes the following steps:

[0040] Step S241: comparing the deformation joint region detection matching degree with a preset region detection matching threshold. When the deformation joint region detection matching degree is less than or equal to the preset region detection matching threshold, marking the key deformation joint risk region on the actual deformation joint detection data according to the deformation joint region detection matching degree to obtain the key deformation joint risk marking region.

[0041] Step S242: Perform high-frequency inspections on the key deformation joint risk-marked areas to generate high-frequency inspection frequency data, and perform non-destructive testing of hidden deformation joints on the key deformation joint risk-marked areas using an ultrasonic detector based on the high-frequency inspection frequency data to generate non-destructive testing data for hidden deformation joints; integrate the non-destructive testing data for hidden deformation joints into the highway construction BIM model for inspection visualization, and generate a first deformation joint inspection plan;

[0042] Step S243: When the deformation joint area detection matching degree is greater than a preset area detection matching threshold, the actual deformation joint detection data is marked as a foundation deformation joint risk area according to the deformation joint area detection matching degree to obtain a foundation deformation joint risk marking area;

[0043] Step S244: Perform low-frequency inspections on the foundation deformation joint risk marked areas to generate low-frequency inspection frequency data, and use strain gauges to perform explicit deformation joint detection on the foundation deformation joint risk marked areas based on the low-frequency inspection frequency data to generate explicit deformation joint detection data; integrate the explicit deformation joint detection data into the highway construction BIM model for inspection visualization to generate a second deformation joint inspection plan.

[0044] The present invention can effectively judge the actual condition of the expansion joint by comparing the detection matching degree of the expansion joint area with the preset matching threshold. When the matching degree is less than or equal to the preset threshold, emphasizing the marking of the risk area helps to identify potential risk points. The generation of such key risk marking areas enables subsequent detection and monitoring work to be more centralized, thereby improving the overall inspection efficiency and pertinence, and reducing losses caused by failure to discover problems in a timely manner. High-frequency inspections are carried out on key risk marking areas, and the high-frequency inspection frequency data generated can ensure the timely detection of potential problems. Combined with the use of ultrasonic detectors, non-destructive testing of hidden expansion joints can deeply evaluate the integrity and safety of the structure. This process can not only discover hidden problems in advance and reduce safety hazards, but also realize visual inspections by integrating the non-destructive testing data of hidden expansion joints into the BIM model, providing important data support for subsequent decision-making. The generated first expansion joint inspection plan provides detailed guidance for construction and maintenance. When the matching degree exceeds a preset threshold, a risk marker area for foundation expansion joints is generated, allowing for appropriate risk classification of the relevant areas. This classification helps clarify strategies for addressing different risk levels and ensures that, given limited resources, high-risk areas are prioritized for monitoring and maintenance, thereby optimizing resource allocation and improving management efficiency. Low-frequency inspections are conducted in key risk-marked areas. The generated low-frequency inspection frequency data, combined with strain gauges, allows for the detection of visible expansion joints, providing a more comprehensive understanding of the area's health status. Obtaining visible expansion joint detection data provides a substantial information foundation for risk management, ensuring effective monitoring of different risk levels. This data is integrated into the BIM model for inspection visualization, generating a secondary expansion joint inspection plan. This systematizes and visualizes inspection work, facilitating subsequent construction monitoring and maintenance decision-making. By comparing and marking regional matching degrees, implementing high- and low-frequency inspections, and combining visible and invisible expansion joint detection, comprehensive support is provided for highway construction safety management. By identifying and monitoring key risk areas, we can not only improve construction safety and reduce potential risks, but also ensure that problems are discovered and addressed in a timely manner during maintenance, ultimately promoting the efficient and safe operation of highway construction. The generated inspection plan provides detailed guidance and decision-making support for the construction team, helping to optimize management processes and improve the overall quality and safety of highway construction.

[0045] Preferably, step S3 includes the following steps:

[0046] Step S31: Periodic inspection data collection is performed on the highway construction BIM model using the first expansion joint inspection plan and the second expansion joint inspection plan to obtain periodic expansion joint inspection data;

[0047] Step S32: performing deformation joint damage assessment on the periodic deformation joint inspection data to generate periodic deformation joint inspection damage assessment data;

[0048] Step S33: Automated early warning is performed based on the periodic expansion joint inspection damage assessment data to generate periodic expansion joint inspection early warning data;

[0049] Step S34: Formulate a deformation joint repair strategy based on the periodic deformation joint inspection warning data to generate a deformation joint abnormality repair strategy.

[0050] The present invention performs periodic inspections on the highway construction BIM model through the first and second expansion joint inspection plans, and can systematically collect the status data of the expansion joints. Regular data collection ensures the timely updating and comprehensiveness of information, and helps to form long-term monitoring records, thereby providing a solid foundation for subsequent analysis and decision-making. Damage assessment of periodic expansion joint inspection data helps to timely identify potential problems and severity of expansion joints. This assessment can not only clearly show the current health status of the expansion joints, but also provide an important basis for subsequent management and maintenance work, making targeted maintenance possible and avoiding the development of small problems into major hidden dangers. Automated early warning based on damage assessment data can achieve real-time monitoring and response. This mechanism improves the efficiency of expansion joint management, reduces the time and workload of manual evaluation, and enables any potential risks to be discovered and handled in the shortest time possible. The automated early warning system enhances the reliability of inspection work, ensures that timely response measures can be taken, and thus reduces the risk of accidents. Developing a repair strategy for abnormal expansion joints based on periodic expansion joint inspection and early warning data ensures prompt action upon discovery. This strategy-making process provides clear guidance for construction and maintenance teams, enabling efficient and orderly repair work, thereby reducing additional losses caused by improper repairs. Systematizing repair strategies can also improve construction quality and extend the service life of expansion joints. Through the collection of periodic inspection data, damage assessment, automated early warning, and the development of repair strategies, a complete expansion joint monitoring and management mechanism is provided for highway construction. This mechanism not only improves the safety and reliability of expansion joints but also optimizes resource allocation and management processes. Through effective monitoring and timely repairs, safety hazards in highway construction can be significantly reduced, overall construction quality can be improved, and the long-term safe operation of highways can be ensured. This systematic management approach lays a solid foundation for highway construction management.

[0051] Preferably, step S32 includes the following steps:

[0052] Step S321: screening the historical deformation joint abnormal data from the periodic deformation joint inspection data to obtain historical deformation joint abnormal inspection data; extracting abnormal inspection features from the historical deformation joint abnormal inspection data to obtain abnormal inspection feature data;

[0053] Step S322: Divide the abnormal inspection feature data into data sets to generate a model training set and a model test set; use a convolutional neural network algorithm to train the model training set to generate a pre-model for expansion joint damage assessment;

[0054] Step S323: performing model optimization iteration on the expansion joint damage assessment pre-model according to the model test set, thereby generating a expansion joint damage assessment model; importing the periodic expansion joint inspection data into the expansion joint damage assessment model to perform expansion joint damage assessment, thereby generating periodic expansion joint inspection damage assessment data.

[0055] By screening historical abnormal expansion joint inspection data, the present invention can clearly identify past expansion joint problems and then extract abnormal inspection features from this data. This feature extraction process helps understand the manifestations and patterns of expansion joint anomalies, providing key basic data for subsequent analysis and modeling. By analyzing historical data, potential risks can be better identified, laying a good foundation for model training. Dividing the abnormal inspection feature data into a model training set and a test set can ensure the scientific nature and rationality of model training. Training the model training set using a convolutional neural network algorithm can improve the model's recognition ability and accuracy. Convolutional neural networks perform well in processing images and time series data. Therefore, applying its algorithm in this step can effectively capture the complex features of expansion joint anomalies, thereby generating a preliminary damage assessment pre-model. Optimizing and iterating the expansion joint damage assessment pre-model based on the model test set can improve the model's performance and generalization ability. Through this optimization process, the model can better adapt to new inspection data, reduce the risk of overfitting, and ensure the reliability of the model in practical applications. During this process, periodic expansion joint inspection data was imported into the optimized model for evaluation, ensuring the scientific and practical nature of the assessment results and generating periodic expansion joint inspection damage assessment data. Through historical data analysis, feature extraction, rational data set partitioning, and model training and optimization, a scientific expansion joint damage assessment system was constructed. This system not only improves the ability to monitor expansion joint status but also enhances the ability to predict expansion joint damage risks. Through efficient data processing and model training, potential expansion joint problems can be promptly identified and addressed, thereby reducing the probability of accidents and ensuring the safety and reliability of highway construction.

[0056] In this specification, a BIM-based highway construction deformation joint detection and management system is provided, which is used to implement the above-mentioned BIM-based highway construction deformation joint detection and management method. The BIM-based highway construction deformation joint detection and management system includes:

[0057] The BIM model construction module is used to obtain highway construction plan data; extract highway structure semantics from the highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model;

[0058] The expansion joint inspection module is used to perform construction simulation on the highway construction BIM model and generate highway construction simulation data; based on the highway construction simulation data, the expansion joint-prone areas of the highway construction BIM model are identified by virtual reality to obtain virtual expansion joint-prone area identification data and expansion joint detection area data; the virtual expansion joint-prone area identification data and expansion joint detection area data are divided into regional matching inspections to generate the first expansion joint inspection plan and the second expansion joint inspection plan;

[0059] The damage assessment module is used to collect periodic inspection data of the highway construction BIM model through the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; perform expansion joint damage assessment on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; formulate expansion joint repair strategies based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies;

[0060] The detection management optimization module is used to update the deformation joint status of the highway construction BIM model according to the deformation joint abnormal repair strategy and generate deformation joint status inspection update data; adjust the detection management process through the deformation joint status inspection update data, and generate a highway construction deformation joint detection management adjustment plan to execute highway construction deformation joint detection management operations.

[0061] The present invention provides the following beneficial effects: by acquiring highway construction plan data, the accuracy and completeness of basic data are ensured, providing a reliable basis for subsequent analysis and modeling. Converting complex construction plans into structured data facilitates information management and processing, generating a visual BIM model, enhancing understanding and communication of highway construction projects, and facilitating collaboration among different stakeholders. Construction simulation data generates a virtual environment for the actual construction process, identifying potential problems through simulation analysis and predicting construction risks in advance. Virtual reality identification of vulnerable areas can efficiently identify areas prone to expansion joints, reducing the possibility of missed inspections and false detections, and improving construction safety. Scientifically dividing inspection plans ensures the rational allocation and use of resources, improving the relevance and effectiveness of inspections. Through regular data collection, a expansion joint monitoring database is established, providing continuous tracking of construction status. Expansion joint damage assessment provides a scientific basis for timely detection and assessment of expansion joint damage, facilitating proactive maintenance measures. Targeted repair strategies are formulated based on the assessment results, ensuring the effectiveness and timeliness of repair work and extending the service life of expansion joints. Real-time updates of expansion joint status in the BIM model ensure that all relevant parties have access to the latest information, reducing communication errors. By dynamically adjusting management processes to adapt to project progress and changes in expansion joint status, management efficiency is improved and construction safety is ensured. Standardized management solutions are implemented, enhancing the systematic and standardized nature of expansion joint detection, thus safeguarding highway construction safety. Therefore, this invention improves the comprehensiveness and real-time nature of BIM-based expansion joint detection management in highway construction through systematic information integration, real-time monitoring, scientific inspections, data-driven damage assessment and repair strategy development, and flexible management process adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flowchart of a BIM-based highway construction expansion joint detection and management method.

[0063] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0064] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0065] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0066] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0067] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0068] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0069] To achieve this, please refer to Figures 1 to 3 A BIM-based highway construction expansion joint detection and management method comprises the following steps:

[0070] Step S1: Obtain highway construction plan data; perform highway structure semantic extraction on the highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model;

[0071] Step S2: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; performing virtual reality identification of deformation joint-prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint-prone area identification data and deformation joint detection area data; performing regional matching inspection division on the virtual deformation joint-prone area identification data and the deformation joint detection area data to generate a first deformation joint inspection plan and a second deformation joint inspection plan;

[0072] Step S3: Periodic inspection data collection is performed on the highway construction BIM model using the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; expansion joint damage assessment is performed on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; expansion joint repair strategies are formulated based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies;

[0073] Step S4: Update the deformation joint status of the highway construction BIM model according to the deformation joint abnormality repair strategy, and generate deformation joint status inspection update data; adjust the inspection management process based on the deformation joint status inspection update data, and generate a highway construction deformation joint inspection management adjustment plan to execute the highway construction deformation joint inspection management operation.

[0074] This invention lays the foundation for subsequent processing by initially collecting all construction-related data. By analyzing the proposed data, structural information from highway construction is extracted, enabling a clear definition of the highway's components and functions. The extracted structural semantic data is converted into a BIM model, providing a visual three-dimensional representation, facilitating subsequent construction and management. By simulating the construction process, it is possible to predict potential problems and rationally allocate resources, improving construction efficiency. Virtual reality technology is used to identify problem areas where expansion joints may occur, enhancing the ability to proactively identify potential risks. Subdividing inspection areas into different inspection plans improves the relevance and effectiveness of inspections, providing a scientific basis for subsequent periodic inspections. Regular inspection data collection ensures dynamic monitoring of highway conditions. The collected data is analyzed to generate damage assessment data, enabling rapid and accurate identification of expansion joint damage. Based on the damage assessment results, a corresponding repair strategy is formulated to ensure rapid response and resolution when problems occur. The BIM model status is updated according to the repair strategy, ensuring the model's timeliness and accuracy, providing the latest data for subsequent decision-making. Based on the latest status data, the detection management process is optimized, management efficiency is improved, and it is ensured that the deformation joint detection during highway construction is always in the best condition. Through systematic construction simulation and real-time inspections, potential risks can be identified at an early stage, thereby reducing the probability of accidents. The implementation of each step provides reliable data support for subsequent decision-making, ensuring the scientificity and rationality of the decision. By recycling data, resource waste is reduced, management and construction efficiency is improved, and costs are reduced. Therefore, the present invention improves the comprehensiveness and real-time nature of BIM-based highway construction deformation joint detection management through systematic information integration, real-time monitoring, scientific inspections, data-driven damage assessment and repair strategy formulation, and flexible management process adjustments.

[0075] In the embodiment of the present invention, reference Figure 1The above is a schematic flow chart of the steps of a BIM-based highway construction expansion joint detection and management method of the present invention. In this example, the BIM-based highway construction expansion joint detection and management method includes the following steps:

[0076] Step S1: Obtain highway construction plan data; perform highway structure semantic extraction on the highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model;

[0077] In this embodiment of the present invention, the sources of highway construction plan data are determined, including design drawings (such as CAD drawings), engineering planning documents (such as design specifications and project bidding documents), and Geographic Information System (GIS) data (such as topographic maps and soil properties). If the data is paper documents or drawings, it is digitized using a scanner. Existing digital files (such as DWG, DXF, Shapefile, etc.) are imported into the data processing system. The data is converted into a unified format (such as GeoJSON, CSV, etc.) to facilitate subsequent processing. The data is checked for completeness and accuracy, and missing values and erroneous information are corrected. Based on relevant highway construction standards (such as the "Highway Engineering Technical Standards"), a semantic model of the highway structure is constructed, defining the categories of various components (such as roadbed, pavement, bridges, culverts, etc.) and their attributes (such as material, size, and load capacity). Natural language processing (NLP) techniques are used to extract key information, such as material type, structural form, and design parameters, from text data such as project bidding documents and design specifications. For drawing data, image recognition techniques (such as image segmentation and feature extraction) are used to extract structural information from CAD drawings and identify individual components and their corresponding attributes. Integrate the extracted semantic data with other data (such as GIS data) to form a comprehensive highway structure semantic dataset. Select specific Building Information Modeling (BIM) software (such as Revit, Navisworks, or SketchUp) to construct the 3D model. Based on the highway structure semantic data, create 3D models of each component in the BIM software, including the roadbed, pavement, bridges, etc. Based on the extracted semantic data, assign attributes such as material, size, and construction process to each component in the model, providing rich information. Perform geometric checks on the generated 3D model to ensure its accuracy and compliance with design standards. Use the simulation functions of the BIM software to analyze the model, such as construction sequence simulation, cost estimation, and environmental impact assessment. Export the completed highway construction BIM model to common formats (such as IFC, OBJ, FBX) for subsequent use and sharing.

[0078] Step S2: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; performing virtual reality identification of deformation joint-prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint-prone area identification data and deformation joint detection area data; performing regional matching inspection division on the virtual deformation joint-prone area identification data and the deformation joint detection area data to generate a first deformation joint inspection plan and a second deformation joint inspection plan;

[0079] In this embodiment of the present invention, the entire construction process is divided into multiple construction tasks (such as roadbed construction, bridge construction, and pavement paving) based on highway construction design drawings and construction plans. Each construction task is further broken down into specific construction steps, such as earthwork, concrete pouring, and pavement paving. Based on the requirements of each construction task, the required construction resources (such as manpower, machinery, and materials) are analyzed. A resource allocation plan is developed for each construction task to ensure the rational allocation and efficient utilization of resources. Specific timelines are assigned to each construction task, and a construction schedule is set within BIM software. Dynamic construction simulation is performed using BIM software (such as Navisworks and Revit) to observe the execution of each construction task, including timelines, resource usage, and interactions. Key data from the construction simulation is recorded, including construction time, resource usage, and bottlenecks. The construction simulation results are analyzed to generate highway construction simulation data. Virtual reality technology is used to create a three-dimensional virtual environment of the construction site, realistically recreating every detail of the highway construction process. User-friendly features are designed to allow users to interact within the virtual environment, such as viewing different construction stages, material application, and expansion joint locations. Based on construction simulation data, factors that cause expansion joints (such as construction loads, temperature changes, and soil settlement) are identified. Through data analysis and model simulation, expansion joint-prone areas are identified and marked in the virtual environment. This generates virtual expansion joint-prone area identification data and expansion joint detection area data for subsequent use. This virtual expansion joint-prone area identification data is compared and analyzed with historical expansion joint detection area data to assess the degree of match between each area. Match evaluation criteria are defined, such as similarity thresholds, overlap, and the accuracy of historical monitoring data. Based on the match analysis results, high-risk expansion joint-prone areas are selected and a primary expansion joint inspection plan is developed. The frequency and schedule of inspections are determined to ensure timely detection of problems. A secondary expansion joint inspection plan is developed for areas with lower match, conducting less frequent inspections. A feedback mechanism is established to compare inspection results with the inspection plan and dynamically adjust the inspection strategy.

[0080] Step S3: Periodic inspection data collection is performed on the highway construction BIM model using the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; expansion joint damage assessment is performed on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; expansion joint repair strategies are formulated based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies;

[0081] In this embodiment of the present invention, regular inspection schedules are arranged according to the first and second expansion joint inspection plans to ensure that all relevant areas are inspected. A professional inspection team is established to collect and record on-site inspection data. According to the plan, the inspection team conducts on-site inspections of identified expansion joint-prone areas, including visual inspections and data collection using specialized testing equipment (such as laser rangefinders and strain gauges). The team records the expansion joint conditions observed during the inspection, including information such as crack width, deformation, and environmental impact, to generate periodic expansion joint inspection data. The collected on-site data is organized, including standardization of data formats and information completion, to ensure data integrity and usability. The organized data is stored in the BIM system for subsequent analysis and use. Based on industry standards and historical data, standards and indicators for expansion joint damage assessment, such as crack width, deformation amplitude, and influencing factors, are developed. The periodic expansion joint inspection data is cleaned to remove outliers and ensure data quality. Machine learning or deep learning algorithms (such as convolutional neural networks) are applied to the periodic expansion joint inspection data for damage assessment. Based on the analysis results, damage assessment data for periodic expansion joint inspections is generated, including assessment conclusions (such as normal, slightly damaged, and severely damaged) and recommended treatment measures. Based on the damage assessment data for periodic expansion joint inspections, abnormal expansion joints are identified, including areas with slight damage and severe damage. Corresponding repair strategies are formulated for different levels of damage. Repair strategies include: Minor damage: Regular monitoring and recommended material filling. Moderate damage: Local repair and the use of repair materials. Severe damage: After a comprehensive assessment, structural reinforcement or replacement is required. Integrate the repair strategies to generate a detailed repair strategy for expansion joint anomalies, including information such as repair methods, required materials, construction time, and personnel arrangements. After implementing the repair strategy, continuously monitor the status of the expansion joints and feed the monitoring results back to the BIM system so that the repair strategy can be dynamically adjusted and optimized based on the new data.

[0082] Step S4: Update the deformation joint status of the highway construction BIM model according to the deformation joint abnormality repair strategy, and generate deformation joint status inspection update data; adjust the inspection management process based on the deformation joint status inspection update data, and generate a highway construction deformation joint inspection management adjustment plan to execute the highway construction deformation joint inspection management operation.

[0083] In this embodiment of the present invention, by collecting and integrating information on previous expansion joint status, inspection results, and repair strategies, all data is accessible on a single platform. An initial status is set for each expansion joint, including information on damage, repair history, and monitoring frequency. Based on the abnormal expansion joint repair strategy, the expansion joint status in the highway construction BIM model is updated. This update includes identifying which expansion joints have been repaired and which are still under monitoring. A detailed record of each expansion joint's historical status changes, repair time, and repair method is generated to generate expansion joint status inspection update data, including the current status, historical status changes, repair history, and subsequent monitoring plan. The updated expansion joint status is visualized in the BIM model to ensure a clear understanding of the current situation for all parties. The existing expansion joint inspection management process is evaluated to identify deficiencies or areas for improvement. Based on the expansion joint status inspection update data, the repair status, monitoring frequency, and resource allocation of different expansion joints are analyzed to drive management decisions. Based on the evaluation results, a new expansion joint inspection management process is developed, including adjusting the inspection frequency for expansion joints in different states. For repaired expansion joints, the inspection frequency can be reduced; for expansion joints with potential risks, the inspection frequency should be increased. Based on the status of the expansion joints, optimize the allocation of human and material resources to improve inspection efficiency. Evaluate existing detection equipment and technical means, and update or introduce new equipment and technology as needed. Organize the adjustment plan into a document, including information such as flow charts, step instructions, responsible persons, time nodes, and expected results. Submit the adjustment plan for review to ensure the recognition and approval of the plan by relevant management. Based on the approved adjustment plan, formulate a detailed implementation plan and arrange the implementation of various tasks, including personnel training and equipment adjustments. Establish a feedback mechanism to ensure that feedback from all parties is collected during the implementation process so that the plan can be adjusted and optimized in a timely manner.

[0084] Preferably, step S1 includes the following steps:

[0085] Step S11: Obtaining highway construction plan data;

[0086] Step S12: performing data preprocessing on the highway construction plan data to generate standard highway construction plan data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0087] Step S13: extracting highway structure semantics from the standard highway construction plan to obtain highway construction structure semantic data;

[0088] Step S14: Use BIM technology to construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model.

[0089] In this embodiment of the present invention, highway construction plan data is collected from various sources, including information provided by design units and relevant data from project management software. This data includes information such as project name, construction location, design drawings, bill of quantities, and construction plan. The dataset is checked for duplicate records and deleted. Data formats, such as date format and numerical units, are ensured to be consistent. Missing values are filled based on project type, historical data, or statistical methods such as mean and median. Records are maintained to facilitate subsequent analysis. Numerical data is normalized to ensure that different features are on the same scale. Categorical variables are converted to numerical data and, using methods such as one-hot encoding, standard highway construction plan data is generated for use in subsequent steps. Natural language processing (NLP) techniques and machine learning algorithms are used to analyze the standard highway construction plan data to extract structural semantic information about the highway, including structural elements such as bridges, tunnels, pavement, and drainage systems, as well as design parameters such as width, height, slope, and materials. This extracted highway construction structural semantic information is stored in a structured format to facilitate subsequent model construction. Appropriate BIM software (such as Revit or Civil 3D) is selected for modeling. Import semantic data of highway construction structures into BIM software. Based on this semantic data, design a 3D digital model of the highway, including the geometry, location, and material properties of each structural element. Detailed adjustments are made to the model based on design requirements and construction specifications to generate the final highway construction BIM model, facilitating visualization, collision detection, and construction simulation.

[0090] Preferably, step S14 includes the following steps:

[0091] Step S141: classifying highway construction structure semantic data into functional structural components to generate highway construction functional facility classification data, wherein the functional structural component classification includes road structure classification, bridge structure classification, tunnel structure classification, and roadbed structure classification;

[0092] Step S142: performing IFC standard format conversion on the highway construction functional facility classification data to generate highway construction format conversion data; performing structural semantic mapping on the highway construction format conversion data using BIM technology to generate highway construction structural semantic mapping data;

[0093] Step S143: performing 3D geometric modeling based on the highway construction structure semantic mapping data to generate highway construction 3D geometric modeling data; performing GIS geographic information integration on the highway construction 3D geometric modeling data to generate a preliminary 3D structural model;

[0094] Step S144: Associating model components of the preliminary three-dimensional structure model based on the highway construction structure semantic data to generate three-dimensional structure attribute association data; inputting the three-dimensional structure attribute association data into the preliminary three-dimensional structure model to fill in model component information to generate a highway construction BIM model.

[0095] In an embodiment of the present invention, highways are classified into different types, such as main roads, secondary roads, and branch roads. Bridges are also classified according to their form (e.g., beam bridges, arch bridges, and suspension bridges). Different types of tunnels (e.g., highway tunnels and railway tunnels) are distinguished, including classifications of soil foundations, stone foundations, and concrete foundations. This generates highway construction functional facility classification data, recording detailed information and characteristics of each functional structural component. Data conversion is performed using the IFC (Industry Foundation Classes) standard to ensure compatibility with BIM tools. The functional facility classification data is converted to the IFC format, including information defining the component geometry, material properties, and component relationships. Using BIM technology, the converted highway construction format data is subjected to structural semantic mapping to generate highway construction structural semantic mapping data. This process involves associating the IFC data with highway construction semantic information to ensure data consistency and availability. Based on the highway construction structural semantic mapping data, 3D geometric modeling is performed in BIM software to construct 3D models of each functional structural component. The generated 3D geometric modeling data for highway construction is integrated with GIS (Geographic Information System) data to obtain the highway project's geographic location information (such as terrain and environment) to generate a preliminary 3D structural model. This preliminary 3D structural model provides a foundation for subsequent model construction and refinement. Based on the highway construction structural semantic data, the relationships and associations between the various model components are analyzed to generate 3D structural attribute association data, including information such as material properties, load-bearing capacity, and usage functions. The generated 3D structural attribute association data is input into the preliminary 3D structural model to populate the model components with information. This ensures that each component contains the necessary attribute information for subsequent analysis and optimization, generating the final highway construction BIM model with complete geometric shape and attribute information, capable of supporting visualization, collision detection, construction simulation, and other functions.

[0096] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0097] Step S21: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; identifying virtual deformation joint prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint prone area identification data;

[0098] Step S22: Based on the virtual deformation joint prone area identification data, a total station is used to perform actual deformation joint detection, thereby generating actual deformation joint detection data; the actual deformation joint detection data is divided into deformation joint areas, thereby generating deformation joint detection area data;

[0099] Step S23: performing regional matching calculation on the deformation joint detection area data and the virtual deformation joint prone area identification data to obtain the deformation joint area detection matching degree;

[0100] Step S24: Compare the deformation joint area detection matching degree with the preset area detection matching threshold. When the deformation joint area detection matching degree is less than or equal to the preset area detection matching threshold, a first deformation joint inspection plan is generated; when the deformation joint area detection matching degree is greater than the preset area detection matching threshold, a second deformation joint inspection plan is generated.

[0101] In an embodiment of the present invention, a construction simulation of a highway construction BIM model is performed by using BIM software (such as Navisworks, Tekla, etc.). A construction schedule is set, including the start and end time of each stage. Various tasks in the construction process are simulated, such as earthwork, roadbed paving, bridge construction, etc. Necessary resources (such as personnel, equipment, and materials) are allocated to ensure the smooth progress of construction, and highway construction simulation data is generated to record key parameters in the construction process and potential locations of expansion joints. Based on the construction simulation data, an analysis algorithm is applied to identify areas where deformation occurs. Numerical simulation methods, finite element analysis, and other technologies can be used to predict the location of expansion joints and obtain virtual expansion joint-prone area identification data, which includes the location information of potential expansion joints and their degree of influence. A total station is used to measure and detect actual expansion joints. The total station can provide high-precision three-dimensional coordinate data. A total station is set up in areas prone to expansion joints to perform measurement work. The actual location, morphology, and changes of expansion joints are recorded to generate real-world expansion joint detection data, including information about the actual expansion joints detected and their precise locations. This data is then used to generate expansion joint detection area data, facilitating subsequent analysis and comparison. Region matching algorithms (such as overlap ratio and distance metrics) are used to compare the expansion joint detection area data with the virtual expansion joint prone area identification data. The matching degree between the two sets of data is calculated to determine the degree of overlap between the actual detection area and the virtual prone area. This results in the expansion joint region detection matching degree, quantifying the relationship between the two. A preset region detection matching threshold is set as the criterion for determining the expansion joint inspection plan. If the expansion joint region detection matching degree is less than or equal to the preset region detection matching threshold, a first expansion joint inspection plan is generated, focusing on detailed inspections of the prone area. If the matching degree is greater than the preset region detection matching threshold, a second expansion joint inspection plan is generated, which may include expanding the inspection scope or implementing other monitoring measures. Two different expansion joint inspection plans are generated, each tailored to the matching degree, to ensure effective monitoring of expansion joints.

[0102] Preferably, performing construction simulation on a highway construction BIM model includes:

[0103] Decompose construction tasks on highway construction BIM model data to generate construction task planning data; perform resource consumption analysis on construction task planning data to generate resource usage analysis data; perform resource allocation optimization processing on resource usage analysis data to generate construction resource optimization data;

[0104] Perform timeline correlation processing on construction task planning data based on construction resource optimization data to generate construction schedule data; perform three-dimensional construction simulation on construction schedule data to generate construction dynamic simulation data; perform construction collision detection on construction dynamic simulation data to generate construction simulation conflict detection data;

[0105] The construction dynamic simulation data and the construction simulation conflict detection data are integrated to generate highway construction simulation data.

[0106] In this embodiment of the present invention, a complete highway construction BIM model, including geometric information, material properties, and component information, is obtained from the design team. Based on the BIM model, key tasks in the construction process are identified, such as foundation construction, pavement paving, and bridge construction. Each key task is further broken down into subtasks, such as earth excavation and foundation pouring in the case of foundation construction. Based on these subdivided tasks, a detailed construction task list is generated, including task name, task description, and estimated duration. The resources required for each construction task are determined, including manpower, machinery, equipment, and materials. Based on the nature of the construction task, the resource consumption for each task is calculated using historical data and industry standards. A resource consumption analysis report is generated, covering the consumption and cost of each resource. Resource consumption data is analyzed to identify bottleneck resources or high-consumption tasks. Using optimization methods such as linear programming and genetic algorithms, a resource allocation optimization model is designed to minimize cost and duration. The optimization model is implemented to generate optimized construction resource data, ensuring rational resource allocation and efficient use. Time parameters are defined for each task, including start time, end time, and duration. Link resource optimization data with construction task planning data to generate a timeline and a complete construction schedule, listing the timing of each task and its resource allocation. Select specific BIM construction simulation software (such as Navisworks, Tekla, BIM 360, etc.) and import the construction schedule data and BIM model. Perform construction simulation according to the schedule and generate construction dynamic simulation data to display construction progress and resource usage. Set collision detection parameters in the simulation software, such as detection accuracy and type (for example, collisions between equipment and components). Run the collision detection algorithm to identify potential conflicts in the construction dynamic simulation data and generate a conflict detection report that lists all conflicts and their locations. Use data management tools or scripts to integrate the construction dynamic simulation data and the construction simulation conflict detection data. Create a final construction simulation data report that integrates construction progress, resource usage, and collision detection results to support decision-making.

[0107] Preferably, step S23 includes the following steps:

[0108] Step S231: Binarizing the deformation joint detection region data and the virtual deformation joint prone region identification data to generate deformation joint detection region binary data and virtual deformation joint prone region binary data;

[0109] Step S232: performing pixel-by-pixel intersection region comparison calculation on the binary data of the deformation joint detection region and the binary data of the virtual deformation joint prone region to generate intersection region data; performing region overlapping pixel calculation on the intersection region data to obtain the region intersection area;

[0110] Step S233: performing pixel-by-pixel union region comparison calculation on the binary data of the deformation joint detection region and the binary data of the virtual deformation joint prone region to generate union region data; performing regional non-overlapping pixel calculation on the union region data to obtain the area of the region union;

[0111] Step S234: Calculate the intersection-and-union ratio of the region intersection area and the region union area, thereby generating a deformation joint region detection matching degree.

[0112] In an embodiment of the present invention, deformation joint detection area data (such as high-resolution images, point cloud data, etc.) is collected. Virtual deformation joint prone area identification data (generated based on a model or historical data) is collected. The collected detection area data and prone area data are converted into grayscale images. An appropriate threshold (T) is selected, which can be determined using the Otsu method or an adaptive threshold. Pixel values in the grayscale image are compared with the threshold: if the pixel value is greater than T, it is set to 1 (foreground). If the pixel value is less than or equal to T, it is set to 0 (background). Binarized deformation joint detection area data and virtual deformation joint prone area data are generated and saved in binary image format. The binary deformation joint detection area data and the virtual deformation joint prone area data are compared pixel by pixel, and the intersection area is calculated: the intersection area is the set of pixels where both are 1. Intersection area data is generated from the pixels in the intersection area and stored as a new binary image. The number of pixels with a value of 1 in the intersection area data is counted to obtain the area of intersection (A_intersect). Compare the binary data of the deformation joint detection area and the binary data of the virtual deformation joint prone area pixel by pixel, and calculate the union area: the union area is the set of pixels where either value is 1. Generate union area data from the pixels in the union area and store it as a new binary image. Count the number of pixels with a value of 1 in the union area data to obtain the union area (A_union). Calculate the Jaccard Index using the formula: Where, Indicates the matching degree of deformation joint area detection, Expressed as the area of region intersection, Expressed as the area of the union of regions. The calculation results are output as a data report on the matching degree of expansion joint area detection, including the matching degree value and the corresponding regional data. The matching degree value is analyzed to determine the effectiveness of expansion joint detection and generate a corresponding feedback report to provide a basis for subsequent expansion joint treatment and repair.

[0113] Preferably, step S24 includes the following steps:

[0114] Step S241: comparing the deformation joint region detection matching degree with a preset region detection matching threshold. When the deformation joint region detection matching degree is less than or equal to the preset region detection matching threshold, marking the key deformation joint risk region on the actual deformation joint detection data according to the deformation joint region detection matching degree to obtain the key deformation joint risk marking region.

[0115] Step S242: Perform high-frequency inspections on the key deformation joint risk-marked areas to generate high-frequency inspection frequency data, and perform non-destructive testing of hidden deformation joints on the key deformation joint risk-marked areas using an ultrasonic detector based on the high-frequency inspection frequency data to generate non-destructive testing data for hidden deformation joints; integrate the non-destructive testing data for hidden deformation joints into the highway construction BIM model for inspection visualization, and generate a first deformation joint inspection plan;

[0116] Step S243: When the deformation joint area detection matching degree is greater than a preset area detection matching threshold, the actual deformation joint detection data is marked as a foundation deformation joint risk area according to the deformation joint area detection matching degree to obtain a foundation deformation joint risk marking area;

[0117] Step S244: Perform low-frequency inspections on the foundation deformation joint risk marked areas to generate low-frequency inspection frequency data, and use strain gauges to perform explicit deformation joint detection on the foundation deformation joint risk marked areas based on the low-frequency inspection frequency data to generate explicit deformation joint detection data; integrate the explicit deformation joint detection data into the highway construction BIM model for inspection visualization to generate a second deformation joint inspection plan.

[0118] In this embodiment of the present invention, by collecting expansion joint area detection matching data (J), a preset area detection matching threshold (T) is set. The expansion joint area detection matching degree J is compared with the threshold T. If J ≤ T, key expansion joint risk areas are marked. Based on the expansion joint area detection matching degree J, actual expansion joint detection data is analyzed to identify key risk areas. Data for key expansion joint risk marking areas is generated and visualized. A high-frequency inspection plan is developed based on the key expansion joint risk marking areas. A high-frequency inspection frequency is set (for example, daily, weekly, etc.). High-frequency inspection frequency data is recorded and generated for subsequent analysis. An ultrasonic detector is used to detect hidden expansion joints in the key expansion joint risk marking areas. Inspection parameters (such as frequency and wavelength) are set, non-destructive testing is performed, and inspection data is collected. The hidden expansion joint non-destructive inspection data is integrated into the highway construction BIM model. The inspection results are visualized in the BIM model, and a first expansion joint inspection plan is generated. When the expansion joint area detection matching degree J > T, foundation expansion joint risk areas are marked. Analyze the actual expansion joint inspection data based on the expansion joint area detection matching degree J, identify foundation risk areas, generate and visualize foundation expansion joint risk marker area data. Develop a low-frequency inspection plan based on the foundation expansion joint risk marker areas. Set the low-frequency inspection frequency (for example: monthly, quarterly, etc.). Record and generate low-frequency inspection frequency data for subsequent analysis. Use strain gauges to perform explicit expansion joint inspections in the foundation expansion joint risk marker areas: Set inspection parameters (such as sensitivity, response time, etc.). Perform explicit expansion joint inspections and collect inspection data. Integrate the explicit expansion joint inspection data into the highway construction BIM model. Visualize the inspection results in the BIM model and generate a second expansion joint inspection plan.

[0119] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0120] Step S31: Periodic inspection data collection is performed on the highway construction BIM model using the first expansion joint inspection plan and the second expansion joint inspection plan to obtain periodic expansion joint inspection data;

[0121] Step S32: performing deformation joint damage assessment on the periodic deformation joint inspection data to generate periodic deformation joint inspection damage assessment data;

[0122] Step S33: Automated early warning is performed based on the periodic expansion joint inspection damage assessment data to generate periodic expansion joint inspection early warning data;

[0123] Step S34: Formulate a deformation joint repair strategy based on the periodic deformation joint inspection warning data to generate a deformation joint abnormality repair strategy.

[0124] In this embodiment of the present invention, regular inspections are scheduled based on a first and second expansion joint inspection plan. An inspection schedule is set to ensure periodic execution (e.g., daily, weekly, or monthly). During the inspection process, information such as expansion joint status, hidden and visible damage, and environmental impacts is recorded. Sensors, cameras, and data recorders are used to collect data to ensure accuracy and completeness. The collected expansion joint status data is integrated to generate a periodic expansion joint inspection dataset. This data includes expansion joint location, inspection time, damage status, and inspection personnel information. Damage assessment criteria are established, including acceptable damage levels for expansion joints and risk classification. Assessment indicators such as crack width, depth, and displacement are defined. Periodic expansion joint inspection data is analyzed, and actual inspection results are compared with the established assessment criteria. Data analysis tools (e.g., statistical analysis software or machine learning models) are used to process the data. The assessment results generate periodic expansion joint inspection damage assessment data, which includes the expansion joint damage level (minor, moderate, or severe), a detailed report on the damage location and extent, and a risk impact assessment. Automated early warning rules are set based on damage assessment results. For example, an alert is automatically triggered when the damage level reaches "severe." Different early warning thresholds are set for specific damage types (such as displacement and cracks). Damage assessment data is connected to an automated monitoring system for real-time monitoring of expansion joint status. Dynamic updates of monitoring data ensure real-time and accurate data. Based on the set early warning rules, the system automatically generates periodic expansion joint inspection early warning data, including the warning type (e.g., hidden damage, visible damage), warning level (e.g., caution, warning, emergency), and related recommended measures or solutions. Based on the periodic expansion joint inspection early warning data, the characteristics and repair requirements of each type of damage are analyzed. Considering the time, cost, and resource availability of repairs, a reasonable repair strategy is formulated. A repair strategy for expansion joint anomalies is generated, including repair methods (e.g., grouting, reinforcement, replacement), estimated repair timeframe and resource allocation, expected results, and risk assessment. The repair strategy is integrated into the highway construction BIM model for visual management. After the repair is completed, the repair results are tracked and monitored to provide feedback on the effectiveness of the repair strategy and optimize future repair plans.

[0125] Preferably, step S32 includes the following steps:

[0126] Step S321: screening the historical deformation joint abnormal data from the periodic deformation joint inspection data to obtain historical deformation joint abnormal inspection data; extracting abnormal inspection features from the historical deformation joint abnormal inspection data to obtain abnormal inspection feature data;

[0127] Step S322: Divide the abnormal inspection feature data into data sets to generate a model training set and a model test set; use a convolutional neural network algorithm to train the model training set to generate a pre-model for expansion joint damage assessment;

[0128] Step S323: performing model optimization iteration on the expansion joint damage assessment pre-model according to the model test set, thereby generating a expansion joint damage assessment model; importing the periodic expansion joint inspection data into the expansion joint damage assessment model to perform expansion joint damage assessment, thereby generating periodic expansion joint inspection damage assessment data.

[0129] In this embodiment of the present invention, historical periodic expansion joint inspection data is collected, including information on expansion joint status, damage history, and environmental impacts. Abnormal data criteria are defined, such as those exceeding a specific crack width or displacement. Threshold methods or statistical analysis (such as the Z-score) are used for screening. A dataset of historical abnormal expansion joint inspections that meet these criteria is output. Features associated with expansion joint damage are identified, including crack width, displacement, deformation rate, and environmental conditions. The raw data is preprocessed, including standardization, normalization, and data augmentation, to improve model performance. Abnormal inspection feature data is generated and a feature matrix is constructed. The abnormal inspection feature data is randomly divided into training and test sets, typically with a ratio of 80% training and 20% test. The training set is balanced with samples of each abnormal type to avoid bias in model training. A CNN model is constructed using a deep learning framework (such as TensorFlow or PyTorch), consisting of input, hidden, and output layers. An appropriate network structure is designed, such as convolutional, pooling, and fully connected layers. A specific loss function (such as cross-entropy loss) is selected to evaluate the difference between the model predictions and the actual labels. Use an optimization algorithm (such as Adam or SGD) to adjust model weights to minimize loss. Perform multiple iterations of training on the training set until the loss function converges, generating a pre-model for expansion joint damage assessment. Input the model test set into the pre-model for expansion joint damage assessment to obtain model prediction results. Use evaluation metrics (such as accuracy, precision, recall, and F1 score) to evaluate model performance and determine the model's generalization ability. Based on the evaluation results, perform model optimization iterations, including adjusting hyperparameters (such as learning rate and batch size), increasing the dataset or using data augmentation techniques to improve model robustness, and adopting a more complex model structure (such as a deep CNN or using transfer learning). Save the optimized model in a format suitable for real-time evaluation (such as HDF5 or ONNX). Import the periodic expansion joint inspection data into the final expansion joint damage assessment model, execute the evaluation process, and generate periodic expansion joint inspection damage assessment data.

[0130] In this specification, a BIM-based highway construction deformation joint detection and management system is provided, which is used to implement the above-mentioned BIM-based highway construction deformation joint detection and management method. The BIM-based highway construction deformation joint detection and management system includes:

[0131] The BIM model construction module is used to obtain highway construction plan data; extract highway structure semantics from the highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model;

[0132] The expansion joint inspection module is used to perform construction simulation on the highway construction BIM model and generate highway construction simulation data; based on the highway construction simulation data, the expansion joint-prone areas of the highway construction BIM model are identified by virtual reality to obtain virtual expansion joint-prone area identification data and expansion joint detection area data; the virtual expansion joint-prone area identification data and expansion joint detection area data are divided into regional matching inspections to generate the first expansion joint inspection plan and the second expansion joint inspection plan;

[0133] The damage assessment module is used to collect periodic inspection data of the highway construction BIM model through the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; perform expansion joint damage assessment on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; formulate expansion joint repair strategies based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies;

[0134] The detection management optimization module is used to update the deformation joint status of the highway construction BIM model according to the deformation joint abnormal repair strategy and generate deformation joint status inspection update data; adjust the detection management process through the deformation joint status inspection update data, and generate a highway construction deformation joint detection management adjustment plan to execute highway construction deformation joint detection management operations.

[0135] The present invention provides the following beneficial effects: by acquiring highway construction plan data, the accuracy and completeness of basic data are ensured, providing a reliable basis for subsequent analysis and modeling. Converting complex construction plans into structured data facilitates information management and processing, generating a visual BIM model, enhancing understanding and communication of highway construction projects, and facilitating collaboration among different stakeholders. Construction simulation data generates a virtual environment for the actual construction process, identifying potential problems through simulation analysis and predicting construction risks in advance. Virtual reality identification of vulnerable areas can efficiently identify areas prone to expansion joints, reducing the possibility of missed inspections and false detections, and improving construction safety. Scientifically dividing inspection plans ensures the rational allocation and use of resources, improving the relevance and effectiveness of inspections. Through regular data collection, a expansion joint monitoring database is established, providing continuous tracking of construction status. Expansion joint damage assessment provides a scientific basis for timely detection and assessment of expansion joint damage, facilitating proactive maintenance measures. Targeted repair strategies are formulated based on the assessment results, ensuring the effectiveness and timeliness of repair work and extending the service life of expansion joints. Real-time updates of expansion joint status in the BIM model ensure that all relevant parties have access to the latest information, reducing communication errors. By dynamically adjusting management processes to adapt to project progress and changes in expansion joint status, management efficiency is improved and construction safety is ensured. Standardized management solutions are implemented, enhancing the systematic and standardized nature of expansion joint detection, thus safeguarding highway construction safety. Therefore, this invention improves the comprehensiveness and real-time nature of BIM-based expansion joint detection management in highway construction through systematic information integration, real-time monitoring, scientific inspections, data-driven damage assessment and repair strategy development, and flexible management process adjustments.

[0136] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0137] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily 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 is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A BIM-based highway construction expansion joint detection and management method, characterized in that: The following steps are involved: Step S1: Obtaining highway construction plan data; Extract highway structure semantics from highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of highway construction structure semantic data to generate a highway construction BIM model; Step S2: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; performing virtual reality identification of deformation joint-prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint-prone area identification data and deformation joint detection area data; performing regional matching inspection division on the virtual deformation joint-prone area identification data and the deformation joint detection area data to generate a first deformation joint inspection plan and a second deformation joint inspection plan; wherein, step S2 includes the following steps: Step S21: performing construction simulation on the highway construction BIM model to generate highway construction simulation data; identifying virtual deformation joint prone areas on the highway construction BIM model based on the highway construction simulation data to obtain virtual deformation joint prone area identification data; Step S22: Based on the virtual deformation joint prone area identification data, a total station is used to perform actual deformation joint detection, thereby generating actual deformation joint detection data; the actual deformation joint detection data is divided into deformation joint areas, thereby generating deformation joint detection area data; Step S23: performing regional matching calculation on the deformation joint detection area data and the virtual deformation joint prone area identification data to obtain the deformation joint area detection matching degree; Step S24: Compare the deformation joint area detection matching degree with the preset area detection matching threshold. When the deformation joint area detection matching degree is less than or equal to the preset area detection matching threshold, a first deformation joint inspection plan is generated; when the deformation joint area detection matching degree is greater than the preset area detection matching threshold, a second deformation joint inspection plan is generated. Step S24 includes the following steps: Step S241: comparing the deformation joint region detection matching degree with a preset region detection matching threshold. When the deformation joint region detection matching degree is less than or equal to the preset region detection matching threshold, marking the key deformation joint risk region on the actual deformation joint detection data according to the deformation joint region detection matching degree to obtain the key deformation joint risk marking region. Step S242: Perform high-frequency inspections on the key deformation joint risk-marked areas to generate high-frequency inspection frequency data, and perform non-destructive testing of hidden deformation joints on the key deformation joint risk-marked areas using an ultrasonic detector based on the high-frequency inspection frequency data to generate non-destructive testing data for hidden deformation joints; integrate the non-destructive testing data for hidden deformation joints into the highway construction BIM model for inspection visualization, and generate a first deformation joint inspection plan; Step S243: When the deformation joint area detection matching degree is greater than a preset area detection matching threshold, the actual deformation joint detection data is marked as a foundation deformation joint risk area according to the deformation joint area detection matching degree to obtain a foundation deformation joint risk marking area; Step S244: Perform low-frequency inspections on the foundation deformation joint risk-marked areas to generate low-frequency inspection frequency data, and perform explicit deformation joint detection on the foundation deformation joint risk-marked areas using strain gauges based on the low-frequency inspection frequency data to generate explicit deformation joint detection data; integrate the explicit deformation joint detection data into the highway construction BIM model for inspection visualization, and generate a second deformation joint inspection plan; Step S3: Periodic inspection data collection is performed on the highway construction BIM model using the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; expansion joint damage assessment is performed on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; expansion joint repair strategies are formulated based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies; Step S4: Update the deformation joint status of the highway construction BIM model according to the deformation joint abnormality repair strategy, and generate deformation joint status inspection update data; adjust the inspection management process based on the deformation joint status inspection update data, and generate a highway construction deformation joint inspection management adjustment plan to execute the highway construction deformation joint inspection management operation.

2. The BIM-based highway construction expansion joint detection and management method according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtaining highway construction plan data; Step S12: performing data preprocessing on the highway construction plan data to generate standard highway construction plan data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization; Step S13: extracting highway structure semantics from the standard highway construction plan to obtain highway construction structure semantic data; Step S14: Use BIM technology to construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model.

3. The BIM-based highway construction expansion joint detection and management method according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: classifying highway construction structure semantic data into functional structural components to generate highway construction functional facility classification data, wherein the functional structural component classification includes road structure classification, bridge structure classification, tunnel structure classification, and roadbed structure classification; Step S142: performing IFC standard format conversion on the highway construction functional facility classification data to generate highway construction format conversion data; performing structural semantic mapping on the highway construction format conversion data using BIM technology to generate highway construction structural semantic mapping data; Step S143: performing 3D geometric modeling based on the highway construction structure semantic mapping data to generate highway construction 3D geometric modeling data; performing GIS geographic information integration on the highway construction 3D geometric modeling data to generate a preliminary 3D structural model; Step S144: Associating model components of the preliminary three-dimensional structure model based on the highway construction structure semantic data to generate three-dimensional structure attribute association data; inputting the three-dimensional structure attribute association data into the preliminary three-dimensional structure model to fill in model component information to generate a highway construction BIM model.

4. The BIM-based highway construction expansion joint detection and management method according to claim 1 is characterized in that: Construction simulation of highway construction BIM models includes: Decompose construction tasks on highway construction BIM model data to generate construction task planning data; perform resource consumption analysis on construction task planning data to generate resource usage analysis data; perform resource allocation optimization processing on resource usage analysis data to generate construction resource optimization data; Perform timeline correlation processing on construction task planning data based on construction resource optimization data to generate construction schedule data; perform three-dimensional construction simulation on construction schedule data to generate construction dynamic simulation data; perform construction collision detection on construction dynamic simulation data to generate construction simulation conflict detection data; The construction dynamic simulation data and the construction simulation conflict detection data are integrated to generate highway construction simulation data.

5. The BIM-based highway construction expansion joint detection and management method according to claim 1 is characterized in that: Step S23 includes the following steps: Step S231: Binarizing the deformation joint detection region data and the virtual deformation joint prone region identification data to generate deformation joint detection region binary data and virtual deformation joint prone region binary data; Step S232: performing pixel-by-pixel intersection region comparison calculation on the binary data of the deformation joint detection region and the binary data of the virtual deformation joint prone region to generate intersection region data; performing region overlapping pixel calculation on the intersection region data to obtain the region intersection area; Step S233: performing pixel-by-pixel union region comparison calculation on the binary data of the deformation joint detection region and the binary data of the virtual deformation joint prone region to generate union region data; performing regional non-overlapping pixel calculation on the union region data to obtain the area of the region union; Step S234: Calculate the intersection-and-union ratio of the region intersection area and the region union area, thereby generating a deformation joint region detection matching degree.

6. The BIM-based highway construction expansion joint detection and management method according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Periodic inspection data collection is performed on the highway construction BIM model using the first expansion joint inspection plan and the second expansion joint inspection plan to obtain periodic expansion joint inspection data; Step S32: performing deformation joint damage assessment on the periodic deformation joint inspection data to generate periodic deformation joint inspection damage assessment data; Step S33: Automated early warning is performed based on the periodic expansion joint inspection damage assessment data to generate periodic expansion joint inspection early warning data; Step S34: Formulate a deformation joint repair strategy based on the periodic deformation joint inspection warning data to generate a deformation joint abnormality repair strategy.

7. The BIM-based highway construction expansion joint detection and management method according to claim 1 is characterized in that: Step S32 includes the following steps: Step S321: screening the historical deformation joint abnormal data from the periodic deformation joint inspection data to obtain historical deformation joint abnormal inspection data; extracting abnormal inspection features from the historical deformation joint abnormal inspection data to obtain abnormal inspection feature data; Step S322: Divide the abnormal inspection feature data into data sets to generate a model training set and a model test set; use a convolutional neural network algorithm to train the model training set to generate a pre-model for expansion joint damage assessment; Step S323: performing model optimization iteration on the expansion joint damage assessment pre-model according to the model test set, thereby generating a expansion joint damage assessment model; importing the periodic expansion joint inspection data into the expansion joint damage assessment model to perform expansion joint damage assessment, thereby generating periodic expansion joint inspection damage assessment data.

8. A BIM-based highway construction expansion joint detection and management system, characterized by: Used to execute the BIM-based highway construction deformation joint detection and management method according to claim 1, the BIM-based highway construction deformation joint detection and management system comprises: The BIM model construction module is used to obtain highway construction plan data; extract highway structure semantics from the highway construction plan data to obtain highway construction structure semantic data; construct a three-dimensional digital model of the highway construction structure semantic data to generate a highway construction BIM model; The expansion joint inspection module is used to perform construction simulation on the highway construction BIM model and generate highway construction simulation data; based on the highway construction simulation data, the expansion joint-prone areas of the highway construction BIM model are identified by virtual reality to obtain virtual expansion joint-prone area identification data and expansion joint detection area data; the virtual expansion joint-prone area identification data and expansion joint detection area data are divided into regional matching inspections to generate the first expansion joint inspection plan and the second expansion joint inspection plan; The damage assessment module is used to collect periodic inspection data of the highway construction BIM model through the first and second expansion joint inspection plans to obtain periodic expansion joint inspection data; perform expansion joint damage assessment on the periodic expansion joint inspection data to generate periodic expansion joint inspection damage assessment data; formulate expansion joint repair strategies based on the periodic expansion joint inspection damage assessment data to generate expansion joint abnormality repair strategies; The detection management optimization module is used to update the deformation joint status of the highway construction BIM model according to the deformation joint abnormal repair strategy and generate deformation joint status inspection update data; adjust the detection management process through the deformation joint status inspection update data, and generate a highway construction deformation joint detection management adjustment plan to execute highway construction deformation joint detection management operations.

Images