Tunnel detection data informatization management platform based on Internet of Things

Abstract

The invention discloses a tunnel detection data informatization management platform based on the Internet of Things. The tunnel detection data informatization management platform comprises a data acquisition module, a data processing module, an informatization management module, a real-time early warning module and a linkage feedback module. Through the synergistic effect of the five modules, various state data in a tunnel can be collected, the collected data are subjected to standardization processing and fusion association, the data standardization degree is improved, data islands are eliminated, and information can be efficiently integrated, so that the sharing level and the deep analysis and utilization level are improved; the method is advantaged in that effective decision support is provided for tunnel management operation, effective processing and analysis can be further carried out on integrated data, key information can be rapidly and accurately extracted from massive detection data, comprehensive evaluation and prediction of the tunnel structure safety state are facilitated, and increasing tunnel safety operation requirements are satisfied.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel detection, and in particular to an Internet of Things-based tunnel detection data information management platform. Background Art

[0002] In the field of tunnel engineering, the safe and stable operation of tunnels is of vital importance. Traditional tunnel inspection methods have many problems, which seriously affect the maintenance and management of tunnels.

[0003] On the one hand, data collection methods are limited and inefficient. In the past, they relied heavily on manual inspections, which required inspectors to enter the tunnel and conduct inspections with simple tools and experience. This was not only labor-intensive and risky, but also limited the scope of inspection, making it difficult to obtain comprehensive and accurate data. Furthermore, data sources are diverse and formatted in inconsistent ways, leading to a low degree of data standardization. This has led to serious data silos, inefficient information integration, and low levels of sharing, in-depth analysis, and utilization. The system does not yet have the ability to effectively support tunnel management and operational decisions.

[0004] On the other hand, data processing and analysis capabilities are insufficient. Most of the collected data is stored in the form of paper documents or simple spreadsheets. There is a lack of effective data processing and analysis methods. Faced with massive amounts of detection data, it is difficult to quickly and accurately extract key information, and it is impossible to comprehensively evaluate and predict the structural safety status of the tunnel.

[0005] In summary, the existing tunnel detection and management methods can no longer meet the growing demand for tunnel safety operations. There is an urgent need for an efficient and intelligent tunnel detection data information and management platform to solve the above problems. Summary of the Invention

[0006] In order to solve the existing problems, the present invention provides a tunnel detection data information management platform based on the Internet of Things. The specific solution is as follows:

[0007] An Internet of Things-based tunnel inspection data information management platform, including:

[0008] Data acquisition module: used to collect the tunnel's three-dimensional point cloud data, image data, and inspection vehicle operating status information;

[0009] Data processing module: standardizes the collected data and integrates and associates the data in standard formats to eliminate data silos and form a complete and coherent data set;

[0010] Information management module: stores data and visually displays 3D models, disease distribution, historical inspection records, and standardized inspection reports;

[0011] Real-time warning module: Set tunnel disease thresholds, compare data in real time and trigger warning signals;

[0012] Linkage feedback module: Generates maintenance tasks based on received warning information and standardized inspection reports, dispatches maintenance personnel to handle the tasks, and re-inspects the maintenance results to provide feedback, forming a closed-loop management.

[0013] Preferably, the data acquisition module includes:

[0014] 3D laser scanning unit: The laser scanner mounted on the rail tunnel inspection vehicle acquires 3D point cloud data of the tunnel section and performs pre-processing;

[0015] Image acquisition unit: uses a high-resolution camera fixed on the rail tunnel inspection vehicle to capture images of the tunnel inner wall;

[0016] Sensor integration unit: Integrates inertial navigation, attitude correction and positioning sensors to monitor the position and motion status of the inspection vehicle in real time.

[0017] Preferably, the data processing module includes:

[0018] Data standardization unit: converts the data format collected by the 3D laser scanning unit, image acquisition unit and sensor integration unit into a standardized format;

[0019] Point cloud data processing unit: denoises and filters, registers and stitches the collected 3D point cloud data, and performs 3D modeling and analysis;

[0020] Image recognition and processing unit: pre-processes the image data collected by the image acquisition unit, and automatically recognizes and classifies the image data based on the deep learning algorithm to identify tunnel defects;

[0021] Data fusion and analysis unit: fuses the processed 3D point cloud data with the image recognition results;

[0022] In-depth analysis and decision support unit: Compare and analyze the integrated data with historical data, conduct a comprehensive assessment and prediction of the overall condition of the tunnel, and convert the analysis and prediction results into standardized inspection reports to provide decision support for tunnel management and operation;

[0023] Adaptive adjustment unit: intelligently adjusts the parameters and acquisition frequency of the 3D laser scanning unit, image acquisition unit, and sensor integration unit according to the real-time status of the tunnel and detection requirements.

[0024] Preferably, the information management module includes:

[0025] Database management unit: receives and stores various types of data from other modules, and classifies, organizes and stores the collected data to establish the database structure;

[0026] Visualization display unit: responsible for providing an intuitive three-dimensional visualization interface for displaying three-dimensional models, disease distribution display and standardized inspection reports.

[0027] Preferably, the real-time warning module includes:

[0028] Threshold setting unit: sets early warning thresholds for various types of hazards based on tunnel design standards and safety regulations;

[0029] Real-time monitoring and early warning unit: responsible for real-time monitoring of tunnel status data and making judgments based on preset thresholds. Once it is detected that the disease parameters exceed the early warning threshold, the early warning signal will be triggered immediately.

[0030] Preferably, the linkage feedback module includes:

[0031] Information push unit: responsible for pushing monitored key data, early warning information and standardized test reports to relevant personnel in real time;

[0032] Task scheduling unit: responsible for automatically generating maintenance task lists based on early warning information and standardized inspection reports, and dispatching maintenance personnel to the site for processing;

[0033] Effect evaluation unit: responsible for re-inspecting the tunnel after maintenance, evaluating the maintenance effect, and forming a closed-loop management.

[0034] The beneficial effects of the present invention are:

[0035] Through the synergistic effect of five modules, the present invention can realize the collection of various status data in the tunnel, standardize and integrate the collected data, improve the degree of data standardization, eliminate data silos, and enable efficient integration of information, thereby improving the level of shareability, in-depth analysis and utilization, and providing effective decision-making support for tunnel management and operation. At the same time, it can also effectively process and analyze the integrated data, and realize the rapid and accurate extraction of key information from massive detection data, which is conducive to the comprehensive assessment and prediction of the structural safety status of the tunnel, thereby meeting the growing demand for tunnel safety operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0039] like Figure 1 ,A tunnel detection data information management platform based on the Internet of Things, includes a data acquisition module, a data processing module, an information management module, a real-time warning module, and a linkage feedback module.

[0040] 1. Data Acquisition Module

[0041] The data acquisition module is used to collect the tunnel's three-dimensional point cloud data, image data, and inspection vehicle operating status information.

[0042] The data acquisition module includes: a three-dimensional laser scanning unit, an image acquisition unit and a sensor integration unit.

[0043] The 3D laser scanning unit is responsible for acquiring and pre-processing the 3D point cloud data of the tunnel cross section using a laser scanner mounted on a rail tunnel inspection vehicle. It uses a portable, modular rail vehicle equipped with a 3D laser scanner to perform its work. Specific tasks include:

[0044] 1. High-precision scanning: Use a 3D laser scanner to perform high-precision scanning of the tunnel section to obtain detailed 3D point cloud data of the tunnel structure. Common 3D point cloud data formats are .las and .pcd. These data can truly reflect the shape, size and surface characteristics of the tunnel;

[0045] 2. Data processing and transmission: The scanned 3D point cloud data is pre-processed, such as denoising and filtering, to improve the accuracy and usability of the data. Subsequently, the processed data is transmitted in real time to the data processing module for further analysis.

[0046] The image acquisition unit uses a high-resolution camera mounted on a tunnel inspection vehicle to capture image data of the tunnel's inner wall. Specific tasks include:

[0047] Image capture: The camera can automatically adjust parameters such as gain, exposure time, and white balance to adapt to shooting requirements under different lighting conditions. By capturing images of key areas such as the tunnel vault, arch waist, and arch foot, it achieves all-round, no-blind-angle image acquisition. The collected high-quality image data provides an important foundation for subsequent image recognition and processing. This image data can be used to detect cracks, water leakage, damage, and other defects on the tunnel wall and assess their severity.

[0048] Sensor integration unit: Integrates inertial navigation, attitude correction and positioning sensors to monitor the position and motion status of the inspection vehicle in real time. Specific work content includes:

[0049] 1. State monitoring: The inertial navigation sensor monitors the acceleration, speed and other motion status information of the inspection vehicle in real time, and the posture correction sensor adjusts the posture of the inspection vehicle in real time to ensure its stability and accuracy during the inspection process;

[0050] 2. Position information acquisition: The real-time position information of the inspection vehicle is obtained using the positioning sensors (such as GPS, Beidou, etc.) integrated in the sensor integration unit to provide an accurate reference coordinate system for the data processing module. This information is crucial for subsequent data processing, analysis, and precise positioning of the tunnel structure.

[0051] The data acquisition module integrates a variety of advanced inspection technologies and equipment, including a 3D laser scanning unit, an image acquisition unit, and a sensor integration unit, enabling comprehensive, high-precision inspection of tunnel structures. These units work collaboratively to collect 3D point cloud data of tunnel sections, image data, and the operating status and position of the inspection vehicle. This data provides a solid foundation for subsequent data processing, analysis, and decision-making, and is crucial for improving the efficiency, accuracy, and reliability of tunnel inspections.

[0052] 2. Data Processing Module

[0053] The data processing module includes a data standardization unit, a point cloud data processing unit, an image recognition and processing unit, a data fusion and analysis unit, a depth analysis and decision support unit, and an adaptive adjustment unit. It integrates multiple data processing technologies and algorithms to efficiently and accurately process and analyze collected 3D point cloud data and image data. It converts data in different formats into a unified standard format and fuses and correlates the standard format data, eliminating data silos and forming a complete and coherent data set.

[0054] Data standardization unit: converts the data format collected by the 3D laser scanning unit, image acquisition unit and sensor integration unit into a standardized format, and uses data cleaning algorithms to remove duplications, errors and outliers in the data.

[0055] Point cloud data processing unit: denoises and filters the collected 3D point cloud data, performs registration and splicing, and performs 3D modeling and analysis. Specific work includes:

[0056] 1. Denoising and filtering: Since the acquisition process may be affected by factors such as environmental noise and equipment errors, the point cloud data will contain some noise points or redundant information. The denoising and filtering steps are designed to remove these noise points and retain useful point cloud data to improve the accuracy and efficiency of subsequent processing.

[0057] The following algorithm is used for denoising. The algorithm calculates the distance between each point and its neighboring points based on the statistical characteristics of the point cloud data. Assume that the point cloud data set is: P = {p1, p2, ..., p i ,……,p n}.

[0058] For each point Pi, calculate its average distance di to the k nearest neighboring points, set the global average distance a and standard deviation b, and if di is greater than a+bc (c is an adjustable parameter, usually 2-3), then the point is determined to be a noise point and removed.

[0059] For example, in a tunnel inspection project, the collected point cloud data was processed by statistical filtering, which effectively removed the noise points caused by equipment reflection interference and improved the data quality.

[0060] 2. Registration and stitching: During the acquisition process, the tunnel may need to be scanned from multiple angles or positions to obtain a complete 3D model. The registration and stitching step is responsible for registering and stitching the point cloud data from these different angles or positions to generate a complete 3D tunnel model.

[0061] The following algorithm is used for point cloud registration and stitching. The algorithm continuously iterates to find the optimal rigid body transformation (rotation matrix R and translation vector t) between two sets of point clouds so that the sum of the squares of the distances between the corresponding points of the two sets of point clouds is minimized. Suppose the two sets of point clouds are

[0062] P={p1,p2,……,p i ,……,p n}

[0063] Q={q1,q2,……,q j ,……,q m}

[0064] The objective function is:

[0065] In practical applications, feature extraction algorithms are first used to obtain the feature points of the two sets of point clouds, which are then used for initial registration. This provides a good initial value for the above-mentioned algorithm and accelerates convergence. For example, after segmented scanning of a long tunnel, the algorithm can be used to successfully and accurately stitch together multiple segments of point cloud data to generate a complete three-dimensional model of the tunnel.

[0066] 3. 3D Modeling and Analysis: Construct a 3D structural model of the tunnel to truly reflect the tunnel's shape, size, and internal structure. Specifically, a 3D model of the tunnel is generated based on the processed point cloud data, and further analysis is performed on it, such as the detection and analysis of parameters such as tunnel clearance, stagger, and ellipticity. These parameters are important for assessing the structural safety status of the tunnel.

[0067] When calculating tunnel clearance, a tunnel design model is constructed and the processed point cloud data is compared with it. Assuming that the tunnel design contour is M, the shortest distance dmin from each point P in the point cloud data to the design contour M is the clearance value at that point.

[0068] For misalignment detection, the position and size of the misalignment are determined by analyzing the height difference of adjacent section point cloud data.

[0069] When calculating ellipticity, an ellipse is fitted on the tunnel cross-section point cloud data. The major semi-axis of the ellipse is a, and the minor semi-axis is b. The ellipticity formula is:

[0070] Through the analysis of these parameters, the structural safety status of the tunnel can be accurately assessed. For example, the ellipticity calculated based on the point cloud data of a certain section of a tunnel is 0.05, indicating that the ellipticity of the section is within the normal range and the tunnel structure is relatively stable.

[0071] Image recognition and processing unit: pre-processes the image data collected by the image acquisition unit, and automatically recognizes and classifies the image data based on deep learning algorithms to identify tunnel defects. Specific work content includes:

[0072] 1. Image preprocessing: Preprocess the collected image data, such as denoising and contrast enhancement, to improve image quality and provide a good foundation for subsequent recognition steps.

[0073] The Gaussian filter algorithm is used to denoise the image. The algorithm is implemented by taking a weighted average of each pixel in the image and its neighboring pixels. Let the image be I(x,y) and the Gaussian filter be G(x,y,σ), where σ is the standard deviation of the Gaussian distribution, which determines the smoothness of the filter. The filtered image I ′ (x,y) is:

[0074] I ′ (x,y)=∑ m∑ n I(x+m,y+n)G(m,n,σ)

[0075] In terms of contrast enhancement, the histogram equalization algorithm is used to transform the grayscale histogram of the image so that the grayscale of the image is evenly distributed, thereby enhancing the contrast of the image.

[0076] 2. Defect identification and classification: Based on deep learning algorithms, the unit automatically identifies and classifies image data to identify defects such as cracks, water leakage, and damage. At the same time, the unit can also automatically calculate key parameters such as the location, width, and length of the defect, achieving accurate positioning and quantitative analysis of the defect.

[0077] The Faster R-CNN model within the convolutional neural network (CNN) is used. This model consists of a region proposal network (RPN) and a Fast R-CNN detector. The RPN is used to generate candidate regions that may contain defects. A sliding window is used to generate a series of anchor boxes of different scales and proportions on the feature map. These anchor boxes are then classified and regressed to determine whether they contain defects and the location offset of the defects. The Fast R-CNN detector further classifies the candidate regions and accurately regresses their locations, identifying defects such as cracks, water leaks, and damage. It also automatically calculates key parameters such as the defect's location, width, and length. The model is trained using a large amount of annotated tunnel defect image data to optimize the model's parameters and improve recognition accuracy.

[0078] For example, in a test of tunnel image data, the trained Faster R-CNN model achieved an accuracy rate of over 90% in identifying crack damage, and was able to accurately detect parameters such as the location and width of the cracks.

[0079] 3. Damage assessment and prediction: Through further analysis and evaluation of identified damage conditions, potential damage development trends are predicted, providing important reference for tunnel maintenance and management.

[0080] The ARIMA model (autoregressive integrated moving average model) in time series analysis is used. Assuming that the time series of a characteristic parameter of the disease (such as crack width) is Yt, the general form of the ARIMA model is ARIMA (p, d, q);

[0081] Where p is the autoregressive order, d is the difference order, and q is the sliding average order. By analyzing historical disease data, appropriate p, d, and q values ​​are determined and a prediction model is established.

[0082] For example, based on the historical data of crack width in a tunnel, after analysis, it was determined that p = 2, d = 1, q = 1, and an ARIMA (2, 1, 1) model was established to predict the development trend of crack width in the future, providing an important reference for tunnel maintenance and management.

[0083] Data fusion and analysis unit: fuses the processed 3D point cloud data with the image recognition results. Specific work content includes:

[0084] Data fusion: The processed 3D point cloud data is integrated with the image recognition results to generate a complete tunnel inspection report. This fusion not only improves the accuracy and reliability of the inspection results, but also provides richer information for subsequent analysis and evaluation.

[0085] Using a feature-based fusion algorithm, geometric features (such as curvature and normal vectors) are first extracted from the point cloud data, and texture features (such as gray-level co-occurrence matrix features) are extracted from the image data. Then, a feature matching algorithm (such as a descriptor-based matching algorithm) is used to match the point cloud features with the image features, establish a corresponding relationship, and fuse the matched features to subsequently generate a complete tunnel comprehensive inspection report.

[0086] For example, in a tunnel inspection, by fusing the geometric features of point cloud data and the texture features of image data, the location and nature of the defect were determined more accurately, improving the accuracy and reliability of the inspection results.

[0087] In-depth analysis and decision support unit: Compare and analyze the integrated data with historical data, conduct comprehensive assessment and prediction of the overall condition of the tunnel, and convert the analysis and prediction results into standardized inspection reports to provide decision support for tunnel management and operation. Specific work content includes:

[0088] 1. Comparative analysis of historical data: By comparing and analyzing historical inspection data, the structural safety status of the tunnel can be evaluated, potential development trends of defects can be discovered, and a scientific basis can be provided for tunnel maintenance and management.

[0089] The grey correlation analysis algorithm is used to determine the similarity between the reference sequence (such as the key parameter sequence in the current test data) and the comparison sequence (the corresponding parameter sequence in the historical test data).

[0090] Assume that the reference sequence is: X0 = {x0(1), x0(2), ..., x0(n)};

[0091] The comparison sequence is: X i ={x i (1),x i (2),……,x i(n)}(i=1,2,……,m);

[0092] Calculate the correlation coefficient:

[0093] Where ρ is the resolution coefficient, which is generally taken as 0.5, and the correlation degree is:

[0094] The greater the correlation, the more similar the current detection data is to the historical data. By calculating the correlation between different historical data and current data, we can analyze the changing trends of tunnel structural parameters and assess the safety status of the tunnel.

[0095] 2. Comprehensive evaluation and standardized inspection report generation: Based on the comparative analysis results of the fused data and historical data, a comprehensive evaluation of the overall condition of the tunnel is conducted, and standardized inspection reports are generated. These reports include historical disease statistics, analysis conclusions, maintenance recommendations, etc., providing an important reference for tunnel maintenance and management. The generation of standardized inspection reports specifically includes the following processes: 1) Data extraction and analysis: Extract inspection data from the database and perform necessary analysis and processing, such as disease statistics, trend analysis, etc.; 2) Report template design: Design a standardized inspection report template, including the cover, table of contents, content, conclusions, etc., to ensure the standardization and readability of the report; 3) Automatic report generation: Based on the analysis results and template design, an inspection report is automatically generated, including a disease statistics table, analysis conclusions, maintenance recommendations, etc. These reports can provide a scientific basis for tunnel maintenance and management and guide the subsequent governance work.

[0096] The analytic hierarchy process (AHP) was used to determine the weights of different disease and structural parameters in the comprehensive evaluation.

[0097] First, a hierarchical model was constructed, with the overall tunnel condition as the target layer, defect types (such as cracks and water leakage) and structural parameters (such as clearance and misalignment) as the criterion layer, and specific inspection data as the indicator layer. A judgment matrix was constructed using expert scoring and other methods, and the relative weights of the elements at each layer were calculated. The tunnel's comprehensive assessment score was then calculated by combining the actual inspection values ​​and weights of each defect and structural parameter.

[0098] For example, based on a comparative analysis of a tunnel's fused data and historical data, the AHP method determined that the weight of crack defects was 0.4, the weight of clearance parameters was 0.3, and so on. Combined with the actual test values, a comprehensive evaluation score of 80 points (out of 100) was calculated, indicating that the tunnel was in good overall condition, but attention still needed to be paid to the development of some defects. Finally, based on the comprehensive evaluation results, a standardized inspection report containing defect statistics, analysis conclusions, and maintenance recommendations was generated, providing an important reference for tunnel maintenance and management.

[0099] The adaptive adjustment unit is responsible for intelligently adjusting the parameters and acquisition frequency of the 3D laser scanning unit, image acquisition unit, and sensor integration unit according to the real-time status and detection requirements of the tunnel. For example, when an abnormality is detected in a certain area of ​​the tunnel, the data acquisition density of that area is automatically increased to accurately capture key information.

[0100] Through the cooperation of various units, the data processing module realizes efficient and accurate processing and analysis of the collected raw data. For data in different formats, it converts them into unified standard format data, and integrates and associates the standard format data to eliminate data silos and form a complete and coherent data set. This not only provides an important basis for the structural safety assessment of the tunnel, but also provides scientific guidance for the maintenance and management of the tunnel.

[0101] 3. Information management module:

[0102] The information management module is used to store data and visually display 3D models, disease distribution, historical inspection records, and standardized inspection reports. It includes a database management unit and a visual display unit.

[0103] Database management unit: Receives and stores various types of data from other modules, and classifies, organizes and stores the collected data to establish a database structure. Specific work content includes:

[0104] 1. Data collection and input: Receive and store various data from the tunnel detection system, including 3D point cloud data, image data, sensor data, etc., to ensure data integrity and accuracy;

[0105] 2. Data organization and storage: Classify, organize and store the collected data, and establish a reasonable database structure to facilitate subsequent data retrieval and analysis;

[0106] 3. Data security and backup: Take necessary data security measures, such as encryption and access control, to ensure data security and confidentiality. At the same time, perform data backup regularly to prevent data loss or damage.

[0107] Visualization Display Unit: Responsible for providing an intuitive 3D visualization interface for displaying 3D models, disease distribution, and standardized inspection reports. Specific work includes:

[0108] 1. 3D model display: The 3D structural model of the tunnel constructed by the display point data processing unit truly reflects the shape, size and internal structure of the tunnel;

[0109] 2. Display of defect distribution: Identified defects (such as cracks, water leakage, etc.) are marked and displayed in the 3D model, allowing management personnel to intuitively understand the distribution and severity of the defects;

[0110] 3. Standardized inspection report display: The standardized inspection report generated by the in-depth analysis and decision support unit displays the time, location, method, results and other information of previous inspections, providing a historical reference for tunnel maintenance and management.

[0111] Through the synergy of various units, the information management module realizes the comprehensive management, efficient retrieval and intuitive display of tunnel detection data. It not only improves the efficiency and accuracy of tunnel detection and management, but also provides strong information support for tunnel maintenance, management and decision-making. In future tunnel detection and management, the information management module will continue to play an important role and promote the continuous improvement of the intelligence and automation level of tunnel detection and management.

[0112] 4. Real-time warning module:

[0113] The real-time warning module is used to set tunnel disease thresholds, compare data in real time, and trigger warning signals. The module comprises a threshold setting unit and a real-time monitoring and warning unit. These units monitor key parameters such as tunnel structural deformation, environmental quality, and traffic conditions in real time, making judgments based on preset thresholds. If an anomaly is detected, a warning signal is immediately triggered and the warning information is transmitted to relevant personnel or systems through various means, enabling timely response measures to ensure tunnel safety.

[0114] Threshold Setting Unit: Based on the tunnel's design standards and safety regulations, it sets early warning thresholds for various types of hazards. These thresholds typically include key indicators such as tunnel structural deformation, environmental quality parameters (such as temperature, humidity, and hazardous gas concentrations), and traffic flow. The setting of thresholds requires comprehensive consideration of multiple aspects, including the tunnel's structural characteristics, geological conditions, environmental factors, and operational requirements, to ensure the accuracy and effectiveness of early warnings. Specific work includes:

[0115] 1. Data collection and analysis: Collect relevant information such as tunnel design drawings, geological survey reports, and historical operational data, and conduct analysis and evaluation to determine a reasonable warning threshold;

[0116] 2. Set warning thresholds: Based on the analysis results and in combination with tunnel safety standards and specifications, set warning thresholds for various types of diseases. These thresholds are usually expressed in numerical form, such as displacement, deformation rate, and harmful gas concentration;

[0117] 3. Update and adjust thresholds: As tunnel operations and geological conditions change, thresholds may need to be updated and adjusted. The threshold setting unit needs to regularly evaluate the rationality of the warning thresholds and make adjustments based on actual conditions.

[0118] Real-time monitoring and early warning unit: This unit is responsible for real-time monitoring of tunnel status data and making judgments based on preset thresholds. Once a disease parameter is detected exceeding the early warning threshold, the unit will immediately trigger an early warning signal and send the warning information to relevant personnel or systems through IoT technology. Specific work content includes:

[0119] 1. Triggering early warning signals: Through the cooperation of the data acquisition module and the data processing module, the real-time data is processed and analyzed. When the disease parameters are detected to exceed the early warning threshold, the real-time monitoring and early warning unit will immediately trigger the early warning signal. These signals can be sent to relevant personnel or systems through various means such as sound and light alarms, text messages, and emails, so that timely response measures can be taken;

[0120] 2. Recording and storage: The real-time monitoring and early warning unit also needs to record and store relevant information of each early warning, including warning time, warning type, warning level, handling measures, etc., for subsequent analysis and evaluation.

[0121] The real-time warning module realizes comprehensive monitoring and early warning of the tunnel status through the coordinated work of the threshold setting unit and the real-time monitoring and early warning unit. It can promptly detect and handle abnormal situations in the tunnel to ensure the safe operation of the tunnel. In future tunnel safety monitoring systems, the real-time warning module will continue to play an important role and provide strong support for tunnel maintenance and management.

[0122] 5. Linkage Feedback Module

[0123] The linkage feedback module includes an information push unit, a task scheduling unit, and an effect evaluation unit, which realizes rapid response and efficient processing of tunnel safety monitoring information, ensures the timely transmission of early warning information, the rapid generation and scheduling of maintenance tasks, and the accurate evaluation of maintenance effects, thus forming a complete management closed loop.

[0124] The information push unit is the front end of the linkage feedback module, responsible for pushing the monitored key data, early warning information and test reports to relevant personnel in real time, as follows:

[0125] Through the platform's data collection and analysis functions, the unit obtains key parameters such as tunnel deformation, stress, cracks, water seepage, as well as early warning information and inspection reports. It then sends this information to tunnel managers, maintenance personnel and other relevant personnel in real time via text messages, emails, and APP push notifications, ensuring that they can understand the tunnel's safety status at the first time, and that relevant personnel can respond quickly to early warning information and take necessary measures to prevent safety accidents.

[0126] The task scheduling unit is responsible for automatically generating a maintenance task list based on early warning information and inspection reports, and dispatching maintenance personnel to the site for processing, as follows:

[0127] After receiving the early warning information or inspection report, the unit will automatically analyze the damage and maintenance needs of the tunnel, and then generate a detailed maintenance task list, which includes information such as the maintenance location, maintenance content, required materials, and maintenance personnel. Then, the unit will intelligently dispatch maintenance personnel to the site for processing based on their availability and geographical location.

[0128] The intelligence and automation of the task scheduling unit can greatly improve the efficiency and quality of maintenance task execution. It can ensure that maintenance personnel arrive at the site in the shortest time possible and take effective measures to carry out repairs, thereby ensuring the normal operation of the tunnel.

[0129] The effect evaluation unit is the final part of the linkage feedback module. It is responsible for re-inspecting the tunnel after repair, evaluating the repair effect, and forming a closed-loop management. The details are as follows:

[0130] After the maintenance personnel complete the maintenance task, the unit will re-inspect the tunnel to check whether the maintenance quality meets the standards and whether the safety hazards have been eliminated. At the same time, the unit will also collect relevant data and information during the maintenance process, such as maintenance time, maintenance costs, maintenance personnel performance, etc., for subsequent evaluation and analysis. Finally, the unit will form a maintenance effect evaluation report based on the re-inspection results and data analysis results, and feedback to relevant personnel.

[0131] The review and evaluation functions of the effectiveness evaluation unit can ensure the quality and effectiveness of maintenance tasks. It can promptly identify and correct problems and deficiencies in the maintenance process, providing improvement directions for subsequent maintenance work. At the same time, the unit can also provide strong guarantees for the safe operation of the tunnel.

[0132] The linkage feedback module achieves rapid response and efficient processing of tunnel safety monitoring information through information push, task scheduling and effect evaluation, providing strong guarantees for the safe operation of the tunnel.

[0133] In this embodiment, the linkage feedback module further includes a system interconnection monitoring unit, which has the following functions:

[0134] 1. Multi-system interface adaptation: Develop a variety of interface adapters for different types of systems in tunnels, such as tunnel monitoring systems, emergency management systems, geographic information systems, ventilation systems, lighting systems, and fire protection systems. These adapters can identify and be compatible with the data transmission protocols and interface standards of different systems. For example, for systems using the Modbus protocol, use the corresponding Modbus interface adapter for connection; for systems based on the TCP / IP protocol, connect through the network interface.

[0135] Establish an interface management mechanism to monitor and manage the connection status, data transmission frequency, data format, etc. of each interface in real time to ensure stable connection with each system and avoid data loss or monitoring interruption due to interface incompatibility or connection failure.

[0136] 2. Data collection and integration: Real-time operational data is collected from each connected system, including equipment status information (such as the operating status of ventilation fans and the on / off status of lighting fixtures), environmental parameters (such as temperature, humidity, and air quality in the tunnel), and system operating parameters (such as the water pressure and water level of the fire protection system). The collected data from different systems are integrated and standardized, converted into a unified data format and structure, and data mapping and conversion algorithms are used to map the data fields of different systems into a unified data model to facilitate subsequent analysis and processing.

[0137] 3. Module and unit monitoring: Comprehensively monitor each module and its subordinate units, including the data acquisition module, data processing module, information management module, and real-time warning module. By embedding monitoring probes in each module and unit, real-time operating status information such as CPU usage, memory usage, and data processing speed can be obtained.

[0138] Establish a monitoring indicator system and set the normal operation indicator range for each module and unit. When the operating indicators of a module or unit exceed the normal range, issue an early warning signal in time to prompt management personnel to handle it. For example, when the CPU usage of the data processing module continues to exceed 80%, it is determined that the module may have performance problems and an alarm will be issued immediately.

[0139] 4. Abnormal analysis and prompts: Use data analysis and machine learning algorithms to conduct in-depth analysis of the collected monitoring data to identify abnormal patterns and potential problems. For example, by comparing and analyzing the historical data and real-time data of the ventilation system, it is possible to determine whether the ventilation system has hidden faults. Use association rule mining algorithms to find abnormal correlations between different modules and systems.

[0140] When an abnormal situation is discovered, the system automatically generates a detailed abnormality report, including the time and location of the abnormality, the modules or units involved, the abnormal manifestations and possible causes, etc. The abnormality report is sent to relevant managers in a timely manner through various means (such as SMS, email, system pop-up windows, etc.) to ensure that they can understand the problem in time and take appropriate measures.

[0141] 5. Linkage processing mechanism: When a problem occurs in a module or unit, the system not only provides timely prompts but also automatically triggers corresponding processing measures according to preset linkage rules. For example, if the real-time warning module fails, the system automatically switches some warning functions to the backup module and notifies technicians to carry out repairs to ensure the safe operation of the tunnel.

[0142] The workflow of the present invention is as follows:

[0143] S1: The 3D laser scanning unit, image acquisition unit, and sensor integration unit in the data acquisition module collect data. After processing by the data standardization unit, the 3D point cloud data, image data, and the operating status and location information of the inspection vehicle are transmitted to the point cloud data processing unit and image recognition and processing unit of the data processing module.

[0144] Among them, the three-dimensional point cloud data is received and processed by the point cloud data processing unit, the image data is received and processed by the image recognition and processing unit, and the running status and position information of the detection vehicle provide auxiliary information for data processing.

[0145] S2: After the point cloud data processing unit, image recognition and processing unit, and data fusion and analysis unit of the data processing module process the data, the data fusion and analysis unit will synthesize the generated processed data into a standardized inspection report and transmit it to the database management unit of the information management module. After receiving the report, the database management unit will classify, organize and store it to provide data support for the visualization display unit and report generation unit.

[0146] S3: The real-time data collected by the 3D laser scanning unit, image acquisition unit, and sensor integration unit of the data acquisition module, as well as the analysis results of the point cloud data processing unit, image recognition and processing unit, and data fusion and analysis unit of the data processing module, are transmitted to the real-time monitoring and warning unit of the real-time warning module. The real-time monitoring and warning unit compares these data with the warning threshold set by the threshold setting unit to determine whether to trigger a warning signal.

[0147] S4: The real-time monitoring of the real-time warning module and the warning information triggered by the warning unit, as well as the detection report stored in the database management unit of the information management module, are transmitted to the information push unit and task scheduling unit of the linkage feedback module. The information push unit pushes the information to the relevant personnel. The task scheduling unit generates a maintenance task list based on the warning information and the detection report and dispatches the maintenance personnel. After the maintenance is completed, the effect evaluation unit conducts a re-inspection and evaluation and feeds back the results to the relevant personnel.

[0148] S5: The system interconnection monitoring unit in the linkage feedback module is connected to the data acquisition, processing, information management, real-time warning and other modules and their subordinate units through the multi-system interface adapter unit. The system interconnection monitoring unit collects operating status data from these modules, such as CPU usage, memory occupancy, etc., to monitor modules and units. At the same time, according to the results of the abnormal analysis and prompt unit, the modules with problems are processed according to the linkage processing mechanism to ensure the normal operation of each module.

[0149] Through the synergistic effect of five modules, the present invention can realize the collection of various status data in the tunnel, standardize and integrate the collected data, improve the degree of data standardization, eliminate data silos, and enable efficient integration of information, thereby improving the level of shareability, in-depth analysis and utilization, and providing effective decision-making support for tunnel management and operation. At the same time, it can also effectively process and analyze the integrated data, and realize the rapid and accurate extraction of key information from massive detection data, which is conducive to the comprehensive assessment and prediction of the structural safety status of the tunnel, thereby meeting the growing demand for tunnel safety operation.

[0150] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A tunnel detection data information management platform based on the Internet of Things, characterized by: include: Data acquisition module: used to collect the tunnel's three-dimensional point cloud data, image data, and inspection vehicle operating status information; Data processing module: standardizes the collected data and integrates and associates the data in standard formats to eliminate data silos and form a complete and coherent data set; Information management module: stores data and visually displays 3D models, disease distribution, historical inspection records, and standardized inspection reports; Real-time warning module: Set tunnel disease thresholds, compare data in real time and trigger warning signals; Linkage feedback module: Generates maintenance tasks based on received warning information and standardized inspection reports, dispatches maintenance personnel to handle the tasks, and re-inspects the maintenance results to provide feedback, forming a closed-loop management.

2. The method according to claim 1, characterized in that The data acquisition module includes: 3D laser scanning unit: The laser scanner mounted on the rail tunnel inspection vehicle acquires 3D point cloud data of the tunnel section and performs pre-processing; Image acquisition unit: uses a high-resolution camera fixed on the rail tunnel inspection vehicle to capture images of the tunnel inner wall; Sensor integration unit: Integrates inertial navigation, attitude correction and positioning sensors to monitor the position and motion status of the inspection vehicle in real time.

3. The method according to claim 2, characterized in that The data processing module includes: Data standardization unit: converts the data format collected by the 3D laser scanning unit, image acquisition unit and sensor integration unit into a standardized format; Point cloud data processing unit: denoises and filters, registers and stitches the collected 3D point cloud data, and performs 3D modeling and analysis; Image recognition and processing unit: pre-processes the image data collected by the image acquisition unit, and automatically recognizes and classifies the image data based on the deep learning algorithm to identify tunnel defects; Data fusion and analysis unit: fuses the processed 3D point cloud data with the image recognition results; In-depth analysis and decision support unit: Compare and analyze the integrated data with historical data, conduct a comprehensive assessment and prediction of the overall condition of the tunnel, and convert the analysis and prediction results into standardized inspection reports to provide decision support for tunnel management and operation; Adaptive adjustment unit: intelligently adjusts the parameters and acquisition frequency of the 3D laser scanning unit, image acquisition unit, and sensor integration unit according to the real-time status of the tunnel and detection requirements.

4. The method according to claim 3, characterized in that The information management module includes: Database management unit: receives and stores various types of data from other modules, and classifies, organizes and stores the collected data to establish the database structure; Visualization display unit: responsible for providing an intuitive three-dimensional visualization interface for displaying three-dimensional models, disease distribution display and standardized inspection reports.

5. The method according to claim 1, characterized in that The real-time warning module includes: Threshold setting unit: sets early warning thresholds for various types of hazards based on tunnel design standards and safety regulations; Real-time monitoring and early warning unit: responsible for real-time monitoring of tunnel status data and making judgments based on preset thresholds. Once it is detected that the disease parameters exceed the early warning threshold, the early warning signal will be triggered immediately.

6. The method according to claim 1, characterized in that The linkage feedback module includes: Information push unit: responsible for pushing monitored key data, early warning information and standardized test reports to relevant personnel in real time; Task scheduling unit: responsible for automatically generating maintenance task lists based on early warning information and standardized inspection reports, and dispatching maintenance personnel to the site for processing; Effect evaluation unit: responsible for re-inspecting the tunnel after maintenance, evaluating the maintenance effect, and forming a closed-loop management.

Images