A bridge structure health monitoring and early warning system
By integrating a variety of high-precision sensors and advanced monitoring equipment in the bridge structure health monitoring and early warning system, combining prediction models and BIM platforms, the lag problem of bridge monitoring and early warning within the city is solved, and real-time monitoring of bridge health status is achieved and efficient early warning improve the accuracy and response speed of early warning.
Patent Information
- Application Number
- CN202411239277.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-05
AI Technical Summary
The existing bridge structure monitoring and early warning system lacks overall management capabilities within the city. The process from data collection to processing and then to early warning is lagging, and it is difficult to respond to emergencies or bad weather in a timely manner, resulting in delays in warning information or inability to provide timely.
A bridge structure health monitoring and early warning system was designed, including collection modules, monitoring modules, early warning modules, processing modules and output modules. The bridge information data is stored through the database, and a variety of high-precision sensors and advanced monitoring equipment are used for real-time monitoring and prediction. The model predicts the health status of the next week, dynamically adjusts the monitoring frequency based on meteorological data, and visually monitors and early warnings are performed through the BIM platform.
Real-time and accurate monitoring of bridge health status is achieved, the targeted and effective warnings are improved, false alarms and missed reports are reduced, the system adaptability and response speed is enhanced, and the safety and service life of the bridge structure are ensured. .
Smart Images

Figure CN118758377B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of bridge health, and in particular to a bridge structure health monitoring and early warning system. Background Art
[0002] Traditional bridge structure monitoring uses manual detection methods to regularly or irregularly detect key parts of the bridge structure, and manually analyzes and processes the on-site test data. This has high labor costs and is prone to subjective errors. There are also methods that install various detection equipment on the bridge to monitor the corresponding bridge information, classify the early warning plans through artificial intelligence, and accurately match the response early warning plans according to the type of abnormal data. Different response plans can then be provided according to different data types, facilitating timely abnormal data alarms and reporting of response plans. However, there is still a certain lag in monitoring various data through detection equipment.
[0003] The publication number is CN113865549A and the name is a bridge structure health monitoring and early warning system and early warning method, including a bridge monitoring module, the bridge monitoring module is electrically connected to the data acquisition module, the data acquisition module is communicatively connected to the data management system, the data management system is communicatively connected to the bridge early warning system, and the bridge early warning system includes a data receiving module, a scheme allocation module, a terminal early warning module, a voice broadcast module and a data processing module; by setting up a bridge early warning system, when the bridge data is abnormal, not only can an alarm be given to the bridge maintenance personnel, but also the vehicle can be broadcast according to the scheme corresponding to the abnormal data, and the driver can be reminded in time to take corresponding measures according to the broadcast response plan, thereby reducing the continuous damage of the vehicle to the bridge before the bridge maintenance, and at the same time guiding the driver to drive safely according to the formulated plan when facing bridge maintenance.
[0004] The above-mentioned technologies focus on reducing the labor costs and subjective errors of manual inspection and improving the accuracy and efficiency of monitoring through automated data collection and intelligent analysis. However, there are basically multiple bridges in a city. The above-mentioned technologies can effectively monitor and warn a single bridge, but lack the ability to coordinate management and warn all bridges in the entire city. Although the above-mentioned technologies reduce human intervention through automated data collection, there is still a certain time delay in the process from data collection to processing and then to warning. This lag is particularly obvious when responding to emergencies or severe weather, and effective warning information may not be provided in a timely manner. Summary of the invention
[0005] The purpose of the present invention is to provide a bridge structure health monitoring and early warning system to solve the problems raised in the above background technology.
[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a bridge structure health monitoring and early warning system, including a collection module, a monitoring module, an early warning module, a processing module and an output module:
[0007] The collection module is provided with a database to store a bridge information data set, a monitoring equipment information data set and a maintenance information data set, wherein the bridge information data set includes a bridge structure information set, a bridge distribution information set, a bridge drawing information set and a geological information set around the bridge, and the maintenance information data set includes a problem information set;
[0008] The monitoring module includes multiple meteorological submodules and multiple structural submodules, and each submodule is matched with the monitoring equipment and assigned a unique identifier. Each bridge installs each submodule on the corresponding monitoring point based on the bridge information data set and according to the equipment laying method. The monitoring information set can be obtained through multiple submodules, and the monitoring module can regularly obtain and update the meteorological data set for the next week, and judge whether bad weather occurs based on the meteorological data set and the monitoring information set. If it occurs, the monitoring frequency of each submodule is adjusted according to the equipment adjustment method. The meteorological submodule includes a meteorological monitoring station, and the monitoring information set includes a real-time monitoring information set and a historical monitoring information set;
[0009] The early warning module sets an early warning level for each monitoring parameter of each bridge according to a customized method based on the bridge information data set and the maintenance information data set, thereby obtaining an early warning information set. When the monitoring parameters in the real-time monitoring information set exceed the corresponding early warning level, an early warning report will be generated;
[0010] The processing module uses mapping software and BIM platform to visualize each bridge drawing in the bridge information data set to obtain a visualization monitoring platform, and adds each submodule to the BIM platform for visualization. A prediction model is provided in the processing module. The prediction model predicts the health status of each bridge in the next week through the monitoring information set and meteorological data, thereby obtaining a prediction information set. The processing module determines whether there is a problem based on the prediction information set according to the problem analysis method. If there is a problem, a problem report can be obtained. The prediction information set includes the predicted values of each bridge monitoring parameter in the next week;
[0011] The output module outputs warning reminders based on the problem report and the warning report;
[0012] The prediction model is created by:
[0013] S1: Based on the database, the bridge information dataset, monitoring information dataset, meteorological data and maintenance information dataset are integrated and preprocessed to obtain standard data, and the standard data is divided into training set, validation set and test set;
[0014] S2: Select target features based on standard data and construct composite features and derived features. The target features include displacement features, stress features, vibration features, meteorological and environmental features, and historical fault and repair records.
[0015] S3: Select a stacked ensemble learning model as the model framework, which is filled with multiple single models as base models. Use the training set to independently train multiple base models to obtain initial prediction results. Use the initial prediction results as new features, and combine the new features with target features, composite features, and derived features to obtain a new feature set. Then select a gradient boosting tree model as a meta-model, and use the new feature set to train the meta-model to obtain an initial model. The initial model is used to integrate the prediction results of the base models to obtain a prediction information set.
[0016] S4: Train and optimize the initial model to obtain a prediction model, and update the prediction model regularly.
[0017] Furthermore, the equipment laying method includes:
[0018] A1: Grid each bridge based on the bridge information data set, and select several first-level monitoring points in each grid area to ensure that several monitoring devices conduct comprehensive monitoring of the grid area, and then the grid area information set can be obtained;
[0019] A2: Extract the fault-prone area information set of each bridge based on the maintenance information data set, and analyze the structural sensitive area information set and environmental impact area information set of each bridge using finite element software based on the bridge information data set. The structural sensitive area information set includes stress concentration areas, crack-prone areas and key support points, and the environmental impact area information set includes wind load concentration areas and water flow scouring areas.
[0020] A3: Based on the bridge information data set, GIS technology is used to integrate and optimize the grid area information set, fault-prone area information set, structural sensitive area information set and environmental impact area information set of each bridge to obtain the final monitoring point information set;
[0021] A4: Match the needs of each monitoring point in the monitoring point information set with the performance of each monitoring device in the monitoring device information data set, and install corresponding monitoring devices at each monitoring point on each bridge.
[0022] Furthermore, the customized method includes:
[0023] B1: Evaluate the overall condition of each bridge based on the bridge information dataset and the maintenance information dataset to obtain overall condition information, wherein the overall condition information includes design features, material properties, structural form, service life and historical maintenance records;
[0024] B2: Determine the monitoring parameters related to the health of each bridge structure based on the overall condition information set, monitoring information set and maintenance information data set, that is, obtain the closely monitored parameter set;
[0025] B3: Based on the close monitoring parameter set, corresponding safety thresholds, threshold buffers and severe thresholds are set for the close monitoring parameters of each bridge, and the warning levels are further divided based on the safety thresholds, threshold buffers and severe thresholds, and finally a warning information set is obtained. The warning levels are divided into four levels, namely normal level, attention level, warning level and severe level.
[0026] Furthermore, the device adjustment method includes:
[0027] C1: Matching the weather type in the weather data set with the severe weather type in the problem information set. If the match is successful, the corresponding weather in the weather data set is preliminarily determined to be dangerous weather, and a dangerous weather information set is obtained, wherein the dangerous weather information set includes dangerous weather parameters;
[0028] C2: Based on the dangerous weather in the dangerous weather information set, the affected bridges are extracted from the problem information set, that is, the target bridge set. Based on the target bridge set and the dangerous weather parameters, the safety thresholds corresponding to the current dangerous weather are extracted from the warning information set and compared to obtain the comparison results;
[0029] C3: Based on the comparison results in B2, if the dangerous weather parameters are within the safety threshold, no adjustment is required. If the dangerous weather parameters exceed or fall below the corresponding safety threshold, the current dangerous weather is considered to be severe weather, and the dangerous weather information set is updated to the severe weather information set;
[0030] C4: Determine the time range of severe weather occurrence and the affected area based on the severe weather information set and meteorological data set, and then obtain the corresponding monitoring equipment information through the BIM platform based on the target bridge set. The remote control software can be used to increase the monitoring frequency of the corresponding monitoring equipment.
[0031] Furthermore, the problem analysis method includes:
[0032] D1: Based on the prediction information set and the warning information set, the predicted value of each bridge monitoring parameter is compared with the corresponding safety threshold to obtain the comparison result;
[0033] D2: Based on the comparison results, if the predicted value of the monitoring parameter is within the normal range of the safety threshold, it is considered to be a normal level; if the predicted value of the monitoring parameter is within the threshold buffer of the safety threshold, it is considered to be a caution level; if the predicted value of the monitoring parameter has exceeded the safety threshold, it is considered to be a warning level; and finally, if the predicted value of the monitoring parameter far exceeds the safety threshold and reaches the severe threshold, it is considered to be a severe level;
[0034] D3: Based on D2, when the predicted value of the monitoring parameter in the prediction information set reaches the attention level or above, the corresponding problem report can be generated.
[0035] Furthermore, the method for creating the visual monitoring platform includes:
[0036] K1: Based on the bridge drawing information set, the 3D model of each bridge is established using Revit drawing software to obtain a 3D model set;
[0037] K2: Based on the 3D model set, the 3D models of each bridge are imported into the BIM platform. The 3D models of the bridges are displayed using the visualization function of the BIM platform, and the data of the monitoring module are integrated to obtain a visualization monitoring platform.
[0038] Furthermore, the method for training, optimizing and updating the prediction model includes:
[0039] T1: Model evaluation: evaluate the trained initial model based on the validation set to obtain the evaluation results, which are used to analyze the performance of the model and identify possible problems and improvements.
[0040] T2: Model optimization, optimizing the model based on the evaluation results and using the grid search method for parameter tuning;
[0041] T3: Model verification: verify the optimized model based on the test set to ensure the generalization ability of the model on unknown data;
[0042] T4: Model update: regularly update the matching model and use incremental learning methods to update the model in real time.
[0043] Furthermore, the processing module is connected to a control terminal, and the collection module, the monitoring module, the early warning module, the processing module and the output module are all connected through a proprietary local area network, and the method for establishing the proprietary local area network includes:
[0044] T1: Information acquisition, obtaining the network information of the collection module, monitoring module, early warning module, processing module and output module, and the network information includes the device IP;
[0045] T2: Device connection, the control terminal automatically allocates the communication channel to match the IP of the collection module, the IP of the monitoring module, the IP of the early warning module, the IP of the processing module and the IP of the output module;
[0046] T3: Configure networking, configure corresponding network services and security measures for communication channels, and create a private LAN.
[0047] Furthermore, the monitoring equipment includes meteorological monitoring equipment, structural monitoring equipment and environmental monitoring equipment, and the meteorological monitoring equipment includes a meteorological monitoring station, the structural monitoring equipment includes a displacement sensor, a stress sensor, a strain gauge, a vibration sensor, an accelerometer, a crack monitor, an inclinometer and a deflection meter, and the environmental monitoring equipment includes a water flow meter, a water level meter, an anemometer and a soil moisture meter.
[0048] Compared with the prior art, the present invention has the following beneficial effects:
[0049] A bridge structure health monitoring and early warning system, by deploying a variety of high-precision sensors and advanced monitoring equipment, can comprehensively cover all key structures of the bridge, thereby ensuring real-time, accurate and comprehensive grasp of the health status of the bridge, which not only improves the accuracy and reliability of the data, but also lays a solid foundation for subsequent early warning and maintenance work. It fully considers the uniqueness and differences of each bridge, and sets personalized safety thresholds and early warning levels according to the actual situation and historical data of the bridge, which can more accurately reflect the unique health status of each bridge in the city, thereby improving the pertinence and effectiveness of the early warning. The prediction model can predict the health status of each bridge structure in the next week through various monitoring data and the meteorological data of the next week, providing a scientific basis for future maintenance work.
[0050] At the same time, through the equipment laying method, the comprehensive monitoring of the bridge structure can be carried out. Combined with the identification of fault-prone areas and structural sensitive areas, the monitoring is more accurate and potential problems can be discovered in time. Through customized early warning, according to the overall condition of the bridge, monitoring parameters and historical data, personalized safety thresholds and early warning levels are set for each bridge, which can more accurately reflect the actual health status of the bridge, reduce false alarms and missed alarms, and improve the effectiveness of early warnings. The equipment adjustment method enables the system to dynamically adjust the monitoring frequency of the monitoring equipment according to changes in meteorological conditions. Under severe weather conditions, by increasing the monitoring frequency, the system can capture the possible impact on the bridge structure more timely, improve the adaptability and response speed of the system, and the problem analysis method can quickly judge the health status of the bridge by comparing the predicted value of the monitoring parameter with the safety threshold, and generate a problem report, which helps managers quickly understand the problems existing in the bridge and take corresponding maintenance measures to avoid further deterioration of the problem. The creation method of the visual monitoring platform enables the system to integrate the three-dimensional model of the bridge with the monitoring data to form an intuitive visual interface, so that managers can more intuitively understand the structure and health status of the bridge and facilitate decision-making. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 It is a schematic diagram of the principle of the present invention;
[0052] Figure 2It is a schematic diagram of the principle of the customization method of the present invention;
[0053] Figure 3 It is a schematic diagram of the principle of the equipment adjustment method of the present invention;
[0054] Figure 4 Schematic diagram of the visualization platform of the present invention. DETAILED DESCRIPTION
[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 creative work are within the scope of protection of the present invention.
[0056] The present invention provides a bridge structure health monitoring and early warning system that can comprehensively monitor the real-time status of the bridge, and can accurately identify the potential risks of the bridge and issue early warnings in time through equipment laying methods, customized methods, prediction models, equipment adjustment methods, and problem analysis methods. The system not only improves the accuracy and efficiency of bridge structure health monitoring, but also enhances the timeliness and pertinence of bridge maintenance, thereby significantly improving the safety and service life of the bridge. For example, in traditional bridge monitoring, there are often problems such as unreasonable monitoring point settings, incomplete monitoring parameters, and insensitive early warning mechanisms, which make it difficult to timely discover and deal with potential safety hazards in the bridge. After the present invention is introduced, the scientific layout and comprehensive coverage of monitoring points are achieved through grid division and sensitive area identification based on bridge information data sets. At the same time, close monitoring parameters and early warning levels are customized for the specific structural and environmental characteristics of the bridge, ensuring the pertinence and effectiveness of monitoring. When encountering severe weather or emergencies, the system can automatically adjust the monitoring frequency, obtain the response data of the bridge in real time, and compare it with the safety threshold. Once the threshold is exceeded, the early warning mechanism is immediately triggered to notify relevant personnel to handle it.
[0057] like Figure 1-Figure 4 As shown, the present invention provides a technical solution: a bridge structure health monitoring and early warning system, including a collection module, a monitoring module, an early warning module, a processing module and an output module:
[0058] The collection module is provided with a database to store bridge information data sets, monitoring equipment information data sets and maintenance information data sets. The bridge information data sets include bridge structure information sets, bridge distribution information sets, bridge drawing information sets and geological information sets around bridges. The maintenance information data sets include problem information sets.
[0059] It should be noted that when choosing a MySQL database management system, you need to design the overall architecture of the database, including the name of the database, the table structure, and the relationship between tables. You need to determine the table structure of each data set, including the field name, data type, length, and constraints. You need to create a database in the MySQL database management system. According to the designed table structure, you need to create a bridge information table, a monitoring equipment information table, and a maintenance information table. You need to clean the collected data, remove duplicate, erroneous, or invalid data, and organize them into a unified format. You need to use database management tools to import the cleaned and organized data into the corresponding tables. You need to back up the database regularly to prevent data loss or damage. You need to use SQL queries to perform statistical analysis on the data in the database and extract key indicators and trends (such as the health status of the bridge or maintenance needs). The bridge structure information set includes: bridge type, design life, main structural materials, structural parameters such as the span and height of the bridge, the load-bearing capacity and design standards of the bridge, and the bridge distribution information set: the geographical location of the bridge, the bridge in the traffic The location in the network, the surrounding environment and landscape description of the bridge. The bridge drawing information set includes: the design drawings of the bridge, the construction drawings, the structural details of the bridge, the cross-section and elevation drawings, the storage path or reference ID of the drawings (which can be quickly retrieved when needed). The geological information set around the bridge includes: the geological conditions of the area where the bridge is located, the groundwater level, the groundwater flow direction and the risk assessment of natural disasters such as earthquakes and landslides. The monitoring equipment information data set includes: the type of monitoring equipment, the installation location of the equipment (which part of the bridge is associated with it), the installation time of the equipment and the manufacturer information, the monitoring parameters and monitoring frequency of the equipment and the maintenance records and calibration information of the equipment. The maintenance information data set includes: the time, location, specific content of the maintenance, the maintenance measures taken, the repair method, the person in charge of the maintenance, the participants and the evaluation of the effect after maintenance. The problem information set: description of the problems found (cracks, rust and deformation), the location of the problem (which part of the bridge is associated with it), the severity and urgency of the problem, the time when the problem was found and the person who found it.
[0060] The monitoring module includes multiple meteorological submodules and multiple structural submodules, and each submodule is matched with the monitoring equipment and assigned a unique identifier. Each bridge installs each submodule on the corresponding monitoring point based on the bridge information data set and according to the equipment laying method. The monitoring information set can be obtained through multiple submodules, and the monitoring module can regularly obtain and update the meteorological data set for the next week, and judge whether there is severe weather based on the meteorological data set and the monitoring information set. If it occurs, the monitoring frequency of each submodule is adjusted according to the equipment adjustment method. The meteorological submodule includes a meteorological monitoring station, and the monitoring information set includes a real-time monitoring information set and a historical monitoring information set;
[0061] It should be noted that for the submodules designed to monitor meteorological conditions (temperature, humidity, wind speed, wind direction, and rainfall, etc.), each meteorological submodule is matched with one or more meteorological monitoring devices (weather stations, anemometers, rain gauges, etc.) and assigned a unique identifier (device ID, serial number, etc.) for easy management and identification. For the submodules designed to monitor the health status of bridge structures (stress, vibration, displacement, cracks, etc.), each structural submodule is matched with a specific structural monitoring device (stress sensor, accelerometer, crack detector, etc.) and also assigned a unique identifier. The monitoring module collects the monitoring data of the bridge and the monitoring requirements, and installs each submodule on the corresponding monitoring point according to the equipment laying method, and configures the parameters of each submodule, such as monitoring frequency, data transmission mode, alarm threshold, etc., to ensure that it can monitor and transmit data according to the predetermined requirements. Each submodule collects monitoring data in real time through the monitoring equipment connected to it, and summarizes the data into a monitoring information set. The real-time monitoring information set contains the monitoring data at the current time or in the recent period, and the historical monitoring information set contains the monitoring data records in the past period. The monitoring module obtains the meteorological data set for the next week from the external data source (meteorological department, meteorological forecast system, etc.) at regular intervals. The meteorological data set includes the predicted values of meteorological parameters such as temperature, humidity, wind speed, wind direction, and rainfall, and then updates the meteorological data set in the monitoring module. Based on the meteorological data set and the monitoring information set, the monitoring module determines whether there is severe weather (strong wind, heavy rain, lightning, etc.). If severe weather occurs, the monitoring module adjusts the monitoring frequency of each submodule according to the equipment adjustment method. For example, during strong winds, the monitoring frequency of the stress sensor is increased to more accurately capture the stress changes of the bridge, and during heavy rains, the monitoring frequency of the crack detector is increased to timely discover potential crack expansion.
[0062] The early warning module sets the early warning level for each monitoring parameter of each bridge according to the customized method based on the bridge information data set and the maintenance information data set, thereby obtaining an early warning information set. When the monitoring parameters in the real-time monitoring information set exceed the corresponding early warning level, an early warning report will be generated;
[0063] It should be noted that based on the bridge information data set and the maintenance information data set, a customized method is used to set corresponding safety thresholds, threshold buffers and severe thresholds for each monitoring parameter of each bridge, and four warning levels are divided based on the corresponding safety thresholds, threshold buffers and severe thresholds. The monitoring parameters in the real-time monitoring information set will be continuously collected and updated, and then these monitoring parameters will be compared with the preset safety thresholds to determine which level the current state belongs to. The warning information set contains all triggered warning events, including bridge name, monitoring parameters, warning level and trigger time, etc. Once the level of the monitoring parameters reaches the attention level, a warning message will be automatically generated and the relevant information will be included in the warning information. The warning report is a detailed description and analysis of the warning information, which is mainly to help managers quickly understand the warning situation and make corresponding treatment. The warning information mainly includes: basic information such as bridge name, location, monitoring point, report generation time and warning trigger time, a brief description of the type and level of the warning event and the triggered monitoring parameters, and a display of the monitoring parameters that triggered the warning and their historical change trend chart or table, so that managers can understand the changes in parameters and conduct a preliminary analysis of the warning event, including possible causes, scope of impact and potential consequences, etc. According to the warning analysis results, put forward corresponding treatment suggestions or measures, such as strengthening monitoring, emergency maintenance, restricting traffic, etc.
[0064] The processing module uses mapping software and BIM platform to visualize the drawings of each bridge in the bridge information data set, obtains a visualization monitoring platform, and adds each submodule to the BIM platform for visualization. A prediction model is provided in the processing module. The prediction model predicts the health status of each bridge in the next week through the monitoring information set and meteorological data, thereby obtaining a prediction information set. The processing module determines whether there is a problem based on the prediction information set according to the problem analysis method. If there is a problem, a problem report can be obtained. The prediction information set includes the predicted values of each bridge monitoring parameter in the next week;
[0065] The output module outputs warning reminders based on problem reports and warning reports;
[0066] Method for creating a prediction model: S1: Based on the database, the bridge information data set, monitoring information set, meteorological data and maintenance information data set are integrated and preprocessed to obtain standard data, and the standard data is divided into a training set, a validation set and a test set. S2: Based on the standard data, target features are selected, and composite features and derived features are constructed. The target features include displacement features, stress features, vibration features, meteorological and environmental features, and historical fault and repair records. S3: A stacked ensemble learning model is selected as the model framework. The model framework is filled with multiple single models used as base models, and the training set is used to independently train multiple base models to obtain initial prediction results. The initial prediction results are used as new features, and the new features are combined with target features, composite features and derived features to obtain a new feature set. Then, a gradient boosting tree model is selected as a meta-model, and the new feature set is used to train the meta-model to obtain an initial model. The initial model is used to integrate the prediction results of the base model to obtain a prediction information set. S4: Training and optimization are performed based on the initial model to obtain a prediction model, and the prediction model is updated regularly.
[0067] It should be noted that the collected data should be cleaned, duplicates, missing or outliers should be removed, and the data should be standardized to ensure that data of different dimensions can be compared on the same scale. The data should be normalized as needed, and the preprocessed data should be divided into training set, validation set and test set, with a ratio of 70%, 15% and 15% respectively. Features directly related to the health status of the bridge (displacement features, stress features, vibration features, meteorological and environmental features, historical failure and repair records) should be selected from the standard data, and composite features and derived features should be constructed based on the target features. The stacking ensemble learning model (Stacking Ensemble) should be used as the model framework, and multiple single models (such as decision trees, random forests, SVMs, etc.) should be filled in the model framework as base models. The training set should be used to independently train multiple base models to obtain their respective initial prediction results. The initial prediction results of the base models should be used as new features, and the new features should be combined with the target features, composite features and derived features to form a new feature set. The XGBoost gradient boosting tree model should be selected as the meta-model, and the meta-model should be trained using the new feature set to obtain the initial model for integrating the prediction results of the base models and generating a prediction information set.
[0068] The equipment laying method includes: A1: gridding each bridge based on the bridge information data set, and selecting several first-level monitoring points in each grid area to ensure that several monitoring equipment conduct comprehensive monitoring of the grid area, so as to obtain the grid area information set; A2: extracting the fault-prone area information set of each bridge based on the maintenance information data set, and using finite element software to analyze the bridge information data set to obtain the structural sensitive area information set and environmental impact area information set of each bridge. The structural sensitive area information set includes stress concentration areas, crack-prone areas and key support points, and the environmental impact area information set includes wind load concentration areas and water flow scouring areas; A3: integrating and optimizing the grid area information set, fault-prone area information set, structural sensitive area information set and environmental impact area information set of each bridge based on the bridge information data set using GIS technology to obtain the final monitoring point information set; A4: matching the needs of each monitoring point in the monitoring point information set with the performance of each monitoring equipment in the monitoring equipment information data set, so that each monitoring point on each bridge is installed with the corresponding monitoring equipment.
[0069] It should be noted that, firstly, GIS software is used to accurately grid each bridge according to the bridge information data set. The size and shape of the grid should be determined according to the specific situation of the bridge and the monitoring needs, to ensure that it can cover the entire bridge and reasonably distribute the monitoring points. In each grid area, several first-level monitoring points are selected according to the monitoring needs and actual conditions. The first-level monitoring points should be able to represent the overall state of the grid area and facilitate the installation of monitoring equipment. Based on the maintenance information data set, the fault-prone area information set of each bridge is extracted through data analysis technology. The bridge is structurally analyzed using finite element software. Combined with the bridge information data set, the structural sensitive area information set of each bridge is determined. The structural sensitive area information set should include stress concentration areas, crack-prone areas and key support points, etc. The bridge information data set and GIS technology are also used to analyze and determine the environmental impact area information set of each bridge. The environmental impact area information set should include wind load concentration areas and water flow scouring areas, etc. The grid area information set, the fault-prone area information set and the structural sensitive area information set of each bridge are determined. The regional information set, structural sensitive area information set and environmental impact area information set are integrated. GIS technology is used to intuitively display these information sets on the map, and spatial analysis and overlay analysis are performed. According to the integrated information, the initially selected monitoring points are optimized and adjusted to ensure that the monitoring points can cover all key areas and potential risk areas, while avoiding redundancy and waste of monitoring points. Finally, the optimized monitoring point information set is obtained. According to the specific needs of each monitoring point in the monitoring point information set and the performance parameters of each device in the monitoring equipment information data set, equipment matching is carried out, and appropriate monitoring equipment (high-precision displacement sensors, stress strain gauges, vibration accelerometers, etc.) are selected to ensure that the equipment can meet the monitoring needs and has sufficient stability and reliability. The corresponding monitoring equipment is installed at the monitoring points of each bridge. During the installation process, attention should be paid to the fixation and protection of the equipment to ensure that the equipment can operate stably for a long time and accurately collect data. After the installation is completed, the equipment is debugged and tested to ensure the accuracy and real-time nature of data collection.
[0070] like Figure 2 As shown, the customized method includes: B1: Based on the bridge information data set and the maintenance information data set, the overall condition of each bridge is evaluated to obtain the overall condition information, which includes design features, material properties, structural form, service life and historical maintenance records; B2: Based on the overall condition information set, the monitoring information set and the maintenance information data set, the monitoring parameters related to the structural health of each bridge are determined, that is, the close monitoring parameter set is obtained; B3: Based on the close monitoring parameter set, the corresponding safety threshold, threshold buffer zone and severe threshold are set for the close monitoring parameters of each bridge, and the warning level is further divided based on the safety threshold, threshold buffer zone and severe threshold, and finally the warning information set is obtained. The warning level is divided into four levels, including normal level, attention level, warning level and severe level.
[0071] It should be noted that the design, material, structure, service life and historical maintenance records of the bridge are comprehensively analyzed, and the overall condition is quantitatively evaluated using expert evaluation methods to generate overall condition information. This information should fully reflect the current status and historical performance of the bridge. Based on the overall condition information set, combined with the monitoring information set and the maintenance information data set, analyze which monitoring parameters are closely related to the health of the bridge structure, use statistical methods to determine the close monitoring parameters, and organize the analyzed close monitoring parameters into a close monitoring parameter set. For each close monitoring parameter, a reasonable safety threshold is set based on historical data, engineering experience and expert opinions. At the same time, a threshold buffer is set for each parameter to provide a certain fault tolerance space to avoid false alarms. A severe threshold is set to issue an emergency warning when the parameter value deviates seriously from the normal range. According to the safety threshold, threshold buffer and severe threshold, an emergency warning is issued. Threshold, divide the current status of the monitoring parameters into four warning levels, normal level: parameter value is within the safety threshold, the bridge status is normal, attention level: parameter value is close to but has not exceeded the safety threshold, and attention should be paid to the changing trend of the bridge status, warning level: parameter value exceeds the safety threshold but has not reached the serious threshold, there is a potential risk in the bridge status, and measures need to be taken for intervention, serious level: parameter value seriously exceeds the safety threshold, the bridge status is critical, and immediate measures need to be taken for emergency treatment, real-time monitoring of the close monitoring parameters of each bridge, comparing the monitoring results with the set safety threshold, determining the warning level, generating a warning information set, including bridge name, monitoring parameters, current values, warning level and recommended measures, etc., feedback the warning information set to relevant personnel in a timely manner, formulate corresponding response measures according to the warning level, and ensure the safe operation of the bridge.
[0072] like Figure 3 As shown, the equipment adjustment method includes: C1: matching the meteorological type in the meteorological data set with the severe meteorological type in the problem information set. If the match is successful, the corresponding meteorological data set is preliminarily determined to be dangerous weather, and a dangerous weather information set is obtained. The dangerous weather information set includes dangerous weather parameters. C2: based on the dangerous weather in the dangerous weather information set, the affected bridges are extracted from the problem information set, that is, the target bridge set. Based on the target bridge set and the dangerous weather parameters, the safety threshold corresponding to the current dangerous weather is extracted from the warning information set and compared to obtain the comparison result. C3: based on the comparison result in B2, if the dangerous weather parameter is within the safety threshold, no adjustment is required. If the dangerous weather parameter exceeds or is lower than the corresponding safety threshold, the current dangerous weather is determined to be severe weather, and the dangerous weather information set is updated to the severe weather information set. C4: based on the severe weather information set and the meteorological data set, the time range of severe weather occurrence and the range of the affected area are determined. Then, based on the target bridge set, the corresponding monitoring equipment information is obtained through the BIM platform, and the monitoring frequency of the corresponding monitoring equipment can be increased by using the remote control software.
[0073] It should be noted that real-time or predicted weather type data is obtained from the meteorological data set, and these weather types are compared with the severe weather types in the problem information set to find matches. If a match is found, the weather type is preliminarily identified as dangerous weather, and relevant dangerous weather parameters are collected to form a dangerous weather information set. Based on the dangerous weather information set, bridges that may be affected by the dangerous weather are extracted from the problem information set to form a target bridge set. For each bridge in the target bridge set, combined with its closely monitored parameters (as described in B2) and the current dangerous weather type, the corresponding safety threshold is extracted from the warning information set, and the dangerous weather parameters are compared with the safety threshold to analyze whether the dangerous weather parameters are within the safety threshold range. If the dangerous weather parameters do not exceed or fall below the corresponding safety threshold, it is considered For routine weather that does not require special adjustment, if the dangerous weather parameters exceed or fall below the safety threshold, it is determined to be severe weather, and the dangerous weather information set is updated to the severe weather information set to emphasize its severity and urgency. Based on the severe weather information set and the meteorological data set, the time range of severe weather and the affected area are further determined. The BIM (Building Information Model) platform is used to quickly locate the detailed model of each bridge based on the information of the target bridge set. The monitoring equipment information installed on the corresponding bridge is obtained through the BIM platform, including the equipment location, model, function, etc. According to the characteristics and impact range of severe weather, the monitoring equipment on the target bridge is adjusted using remote control software, and the monitoring frequency of the monitoring equipment in the affected area is increased to ensure that the changes of the bridge in severe weather can be captured in real time.
[0074] The problem analysis method includes: D1: Based on the prediction information set and the warning information set, the predicted value of each bridge monitoring parameter is compared with the corresponding safety threshold to obtain the comparison result. D2: Based on the comparison result, if the predicted value of the monitoring parameter is within the normal range of the safety threshold, it is determined to be a normal level. If the predicted value of the monitoring parameter is within the threshold buffer of the safety threshold, it is determined to be an attention level. If the predicted value of the monitoring parameter has exceeded the safety threshold, it is determined to be a warning level. Finally, if the predicted value of the monitoring parameter far exceeds the safety threshold and reaches the serious threshold, it is determined to be a serious level. D3: Based on D2, when the predicted value of the monitoring parameter in the prediction information set reaches the attention level or above, the corresponding problem report can be generated.
[0075] It should be noted that the predicted value of each bridge monitoring parameter is obtained from the prediction information set, and the safety threshold of the corresponding monitoring parameter is obtained from the warning information set, including the normal threshold, threshold buffer zone, warning threshold and severe threshold. The predicted value of each monitoring parameter is compared with the safety threshold to determine in which threshold interval the predicted value falls. The comparison result of the predicted value of each monitoring parameter with the safety threshold is recorded, including whether the predicted value is within the normal range, within the threshold buffer zone, exceeds the warning threshold or reaches the severe threshold. According to the comparison result in step D1, the level of the monitoring parameter is determined according to the following logic: if the predicted value is within the normal range of the safety threshold, it is determined to be normal level; if the predicted value is below the normal range, it is determined to be below the normal level. If the predicted value is within the threshold buffer of the safety threshold, it is judged as the attention level; if the predicted value has exceeded the safety threshold but has not reached the serious threshold, it is judged as the warning level; if the predicted value far exceeds the safety threshold and reaches the serious threshold, it is judged as the serious level. Each monitoring parameter is marked according to its judgment level for subsequent processing. Based on the prediction information set, those monitoring parameters whose predicted values reach the attention level and above are screened out. For each screened monitoring parameter, relevant information is collected, including the bridge name, monitoring parameter name, predicted value, judgment level, possible impact, etc. Based on this information, the content of the problem report is written and formatted to make it easy to read and understand.
[0076] like Figure 4 As shown, the method for creating a visualization monitoring platform includes: K1: using Revit drawing software to establish a 3D model of each bridge based on the bridge drawing information set to obtain a 3D model set; K2: importing the 3D model of each bridge into the BIM platform based on the 3D model set, using the visualization function of the BIM platform to display the 3D model of the bridge, and integrating the data of the monitoring module to obtain a visualization monitoring platform.
[0077] It should be noted that when starting the Revit drawing software, according to the bridge drawing information set, each part of the bridge (bridge deck, bridge piers, bridge towers, etc.) should be drawn one by one in Revit, and the modeling tools of Revit should be used to accurately build the 3D model of the bridge. During the modeling process, attention should be paid to the restoration of the details such as the proportion, size, and material of the bridge to ensure that the 3D model is consistent with the actual bridge. After completing the preliminary construction of the 3D model of the bridge, the model should be verified to check whether there are any errors or unreasonable aspects in the model. According to the verification results, the model should be optimized and adjusted to ensure the accuracy and completeness of the model, and all the 3D models of the bridge should be organized into a set for subsequent import into the BIM platform. Perform operations to export the 3D model of the bridge created in Revit to a format supported by the BIM platform, import the exported 3D model in the BIM platform, ensure that the model can be displayed and operated normally in the BIM platform, use the visualization tools of the BIM platform to display the 3D model of the bridge, integrate the data of the monitoring module, combine the real-time monitored bridge status information with the 3D model, realize visual monitoring of the bridge status, set the monitoring parameters and corresponding safety thresholds of the bridge in the BIM platform, and when the monitoring data exceeds or falls below the set threshold, the BIM platform should be able to automatically issue a warning signal to remind relevant personnel to pay attention to changes in the bridge status.
[0078] The training optimization and updating methods of the prediction model include: T1: model evaluation, evaluating the trained initial model based on the validation set to obtain the evaluation results, which are used to analyze the performance of the model and find out possible problems and improvements; T2: model optimization, optimizing the model based on the evaluation results, and using the grid search method for parameter tuning; T3: model verification, verifying the optimized model based on the test set to ensure the generalization ability of the model on unknown data; T4: model update, regularly updating the matching model, and using the incremental learning method to update the model in real time.
[0079] It should be noted that the validation set data is input into the trained model to obtain the prediction results of the model. Evaluation indicators such as accuracy, recall, F1 score, area under the ROC curve (AUC), etc. are calculated based on the prediction results and actual results. The evaluation results are analyzed to identify areas where the model performance is poor, such as overfitting, underfitting, and category imbalance. According to the model evaluation results, the goals that need to be optimized are determined, such as improving accuracy and reducing false alarm rates. The grid search method is used to tune the model parameters within the predetermined parameter range. The grid search finds the optimal parameter combination by traversing all possible parameter combinations to maximize the performance of the model. A test set different from the validation set is divided from the original data set for the final verification of the model performance, ensuring that the data in the test set is unknown, that is, the model has not been used in the training process. Have been exposed to these data, input the test set data into the optimized model, obtain the model's prediction results, calculate the evaluation indicators, and compare them with the results on the validation set to confirm the model's generalization ability on unknown data. Update the model regularly every week. When updating, you can collect new data samples again and add them to the training set. Use incremental learning methods to update the model in real time. Incremental learning allows the model to learn only new knowledge from new data while retaining existing knowledge. It can be implemented through online learning algorithms, such as variants of stochastic gradient descent (SGD), which can process new data batch by batch without retraining the entire model. Accuracy is the ratio of the number of samples correctly classified by the model to the total number of samples. Accuracy definition: the ratio of the number of samples correctly classified by the model to the total number of samples. Formula: Accuracy = (TP + TN) / (TP + TN + FP + FN), where TP is a true positive example, TN is a true negative example, FP is a false positive example, and FN is a false negative example. Recall definition: Recall is the ratio of the number of samples correctly predicted as positive examples by the model to the number of samples that are actually positive examples. Formula: Recall = TP / (TP + FN). Recall reflects the sensitivity of the model to positive examples. Precision definition: Precision is the ratio of samples predicted as positive examples by the model to samples that are actually positive examples. Formula: Precision = TP / (TP + FP). Precision reflects the reliability of the model's prediction of positive examples. F1 score definition: The F1 score is the harmonic mean of precision and recall, which is used to balance the importance of precision and recall. Formula: F1 = 2 * (Precision * Recall) / (Precision + Recall), ROC curve and AUC value, ROC curve: evaluates model performance by plotting the true positive rate (TPR) and false positive rate (FPR) at different thresholds, AUC value: the area under the ROC curve, the larger the value, the better the model performance. These indicators are used to quantify the performance of the model, analyze the evaluation results, and identify the performance differences of the model on different categories or data subsets.Find out possible problems and areas for improvement.
[0080] The processing module is connected to the control terminal, and the collection module, monitoring module, early warning module, processing module and output module are all connected through a proprietary LAN. The method for creating a proprietary LAN includes: T1: information acquisition, obtaining the networking information of the collection module, monitoring module, early warning module, processing module and output module, and the networking information includes the device IP, T2: device connection, the control terminal automatically allocates the communication channel to match the IP of the collection module, the IP of the monitoring module, the IP of the early warning module, the IP of the processing module and the IP of the output module, T3: configuring the network, configuring the corresponding network services and security measures for the communication channel, and creating a proprietary LAN.
[0081] It should be noted that the networking information of each module is obtained from the database to determine the IP address of each module (collection module, monitoring module, warning module, processing module, output module), including subnet mask, gateway, etc. The control terminal allocates the communication channel by itself according to the obtained networking information, and uses the network management tool to configure the IP addresses of the collection module, monitoring module, warning module, processing module and output module to the corresponding communication channel, and then performs a connection test between devices to ensure that all modules can communicate with each other through the network, configure network security measures, including firewall rules, access control lists (ACLs), VPN connections (if remote access is required), etc., configure network devices and routing protocols, ensure that data packets can be correctly routed and exchanged between the collection module, monitoring module, warning module, processing module and output module, and adjust bandwidth allocation according to network traffic and application requirements.
[0082] Monitoring equipment is mainly divided into meteorological monitoring equipment, structural monitoring equipment and environmental monitoring equipment. Meteorological monitoring equipment mainly includes meteorological monitoring stations, structural monitoring equipment mainly includes displacement sensors, stress sensors, strain gauges, vibration sensors, accelerometers, crack monitors, inclinometers and deflection meters, and environmental monitoring equipment mainly includes water flow meters, water level meters, anemometers and soil moisture meters.
[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.
Claims
1. A bridge structure health monitoring and early warning system, comprising a collection module, a monitoring module, an early warning module, a processing module and an output module, characterized in that: The collection module is provided with a database to store a bridge information data set, a monitoring equipment information data set and a maintenance information data set, wherein the bridge information data set includes a bridge structure information set, a bridge distribution information set, a bridge drawing information set and a geological information set around the bridge, and the maintenance information data set includes a problem information set; The monitoring module includes multiple meteorological submodules and multiple structural submodules, and each submodule is matched with the monitoring equipment and assigned a unique identifier. Each bridge installs each submodule on the corresponding monitoring point based on the bridge information data set and according to the equipment laying method, and obtains the monitoring information set through multiple submodules. The monitoring module periodically obtains and updates the meteorological data set for the next week, and determines whether severe weather occurs based on the meteorological data set and the monitoring information set. If severe weather occurs, the monitoring frequency of each submodule is adjusted according to the equipment adjustment method. The meteorological submodule includes a meteorological monitoring station, and the monitoring information set includes a real-time monitoring information set and a historical monitoring information set. The early warning module sets an early warning level for each monitoring parameter of each bridge according to a customized method based on the bridge information data set and the maintenance information data set, thereby obtaining an early warning information set. When the monitoring parameters in the real-time monitoring information set exceed the corresponding early warning level, an early warning report will be generated; The processing module uses mapping software and BIM platform to visualize each bridge drawing in the bridge information data set to obtain a visualization monitoring platform, and adds each submodule to the BIM platform for visualization. A prediction model is provided in the processing module. The prediction model predicts the health status of each bridge in the next week through the monitoring information set and meteorological data, thereby obtaining a prediction information set. The processing module determines whether there is a problem based on the prediction information set according to the problem analysis method, and obtains a problem report if there is a problem. The prediction information set includes the predicted values of each bridge monitoring parameter in the next week; The output module outputs warning reminders based on the problem report and the warning report; The prediction model is created by: S1: Based on the database, the bridge information dataset, monitoring information dataset, meteorological data and maintenance information dataset are integrated and preprocessed to obtain standard data, and the standard data is divided into training set, validation set and test set; S2: Select target features based on standard data and construct composite features and derived features. The target features include displacement features, stress features, vibration features, meteorological and environmental features, and historical fault and repair records. S3: Select a stacked ensemble learning model as the model framework, which is filled with multiple single models as base models. Use the training set to independently train multiple base models to obtain initial prediction results. Use the initial prediction results as new features, and combine the new features with target features, composite features, and derived features to obtain a new feature set. Then select a gradient boosting tree model as a meta-model, and use the new feature set to train the meta-model to obtain an initial model. The initial model is used to integrate the prediction results of the base models to obtain a prediction information set. S4: Train and optimize the initial model to obtain a prediction model, and regularly update the prediction model; The equipment laying method comprises: A1: Grid each bridge based on the bridge information data set, and select several first-level monitoring points in each grid area to ensure that several monitoring devices conduct comprehensive monitoring of the grid area, that is, to obtain the grid area information set; A2: Extract the fault-prone area information set of each bridge based on the maintenance information data set, and analyze the structural sensitive area information set and environmental impact area information set of each bridge using finite element software based on the bridge information data set. The structural sensitive area information set includes stress concentration areas, crack-prone areas and key support points, and the environmental impact area information set includes wind load concentration areas and water flow scouring areas. A3: Based on the bridge information data set, GIS technology is used to integrate and optimize the grid area information set, fault-prone area information set, structural sensitive area information set and environmental impact area information set of each bridge to obtain the final monitoring point information set; A4: Based on the needs of each monitoring point in the monitoring point information set and the performance of each monitoring device in the monitoring device information data set, the corresponding monitoring device is installed at each monitoring point on each bridge; The customized method includes: B1: Evaluate the overall condition of each bridge based on the bridge information dataset and the maintenance information dataset to obtain overall condition information, wherein the overall condition information includes design features, material properties, structural form, service life and historical maintenance records; B2: Determine the monitoring parameters related to the health of each bridge structure based on the overall condition information set, monitoring information set and maintenance information data set, that is, obtain the closely monitored parameter set; B3: Based on the close monitoring parameter set, corresponding safety thresholds, threshold buffers and severe thresholds are set for the close monitoring parameters of each bridge, and the warning levels are further divided based on the safety thresholds, threshold buffers and severe thresholds, and finally a warning information set is obtained. The warning levels are four levels, including normal level, attention level, warning level and severe level; The equipment adjustment method includes: C1: Matching the weather type in the weather data set with the severe weather type in the problem information set. If the match is successful, the corresponding weather in the weather data set is preliminarily determined to be dangerous weather, and a dangerous weather information set is obtained, wherein the dangerous weather information set includes dangerous weather parameters; C2: Based on the dangerous weather in the dangerous weather information set, the affected bridges are extracted from the problem information set, that is, the target bridge set. Based on the target bridge set and the dangerous weather parameters, the safety thresholds corresponding to the current dangerous weather are extracted from the warning information set and compared to obtain the comparison results; C3: Based on the comparison results in B2, if the dangerous weather parameters are within the safety threshold, no adjustment is required. If the dangerous weather parameters exceed or fall below the corresponding safety threshold, the current dangerous weather is considered to be severe weather, and the dangerous weather information set is updated to the severe weather information set; C4: Determine the time range and affected area of severe weather based on the severe weather information set and meteorological data set, then obtain the corresponding monitoring equipment information through the BIM platform based on the target bridge set, and use the remote control software to increase the monitoring frequency of the corresponding monitoring equipment; The problem analysis method includes: D1: Based on the prediction information set and the warning information set, the predicted value of each bridge monitoring parameter is compared with the corresponding safety threshold to obtain the comparison result; D2: Based on the comparison results, if the predicted value of the monitoring parameter is within the normal range of the safety threshold, it is considered to be a normal level; if the predicted value of the monitoring parameter is within the threshold buffer of the safety threshold, it is considered to be a caution level; if the predicted value of the monitoring parameter has exceeded the safety threshold, it is considered to be a warning level; and finally, if the predicted value of the monitoring parameter far exceeds the safety threshold and reaches the severe threshold, it is considered to be a severe level; D3: Based on D2, when the predicted value of a monitoring parameter in the prediction information set reaches the attention level or above, a corresponding problem report is generated.
2. A bridge structure health monitoring and early warning system according to claim 1, characterized in that: The method for creating the visual monitoring platform includes: K1: Based on the bridge drawing information set, the 3D model of each bridge is established using Revit drawing software, that is, a 3D model set is obtained; K2: Based on the 3D model set, the 3D models of each bridge are imported into the BIM platform. The 3D models of the bridges are displayed using the visualization function of the BIM platform, and the data of the monitoring module are integrated to obtain a visualization monitoring platform.
3. A bridge structure health monitoring and early warning system according to claim 1, characterized in that: The method for training, optimizing and updating the prediction model includes: T1: Model evaluation: evaluate the trained initial model based on the validation set to obtain the evaluation results, which are used to analyze the performance of the model and identify existing problems and improvements. T2: Model optimization, optimizing the model based on the evaluation results and using the grid search method for parameter tuning; T3: Model verification: verify the optimized model based on the test set to ensure the generalization ability of the model on unknown data; T4: Model update: regularly update the prediction model and use incremental learning methods to update the model in real time.
4. A bridge structure health monitoring and early warning system according to claim 1, characterized in that: The processing module is connected to a control terminal, and the collection module, the monitoring module, the early warning module, the processing module and the output module are all connected through a proprietary local area network. The method for establishing the proprietary local area network includes: Step 1: Information acquisition, obtaining the network information of the collection module, monitoring module, early warning module, processing module and output module, the network information including the device IP; Step 2: Device connection, the control terminal automatically allocates the communication channel to match the IP of the collection module, the IP of the monitoring module, the IP of the early warning module, the IP of the processing module and the IP of the output module; Step 3: Configure the network, configure corresponding network services and security measures for the communication channel, and create a private LAN.
5. A bridge structure health monitoring and early warning system according to claim 1, characterized in that: The monitoring equipment mainly includes meteorological monitoring equipment, structural monitoring equipment and environmental monitoring equipment. The meteorological monitoring equipment includes a meteorological monitoring station, the structural monitoring equipment includes a displacement sensor, a stress sensor, a strain gauge, a vibration sensor, an accelerometer, a crack monitor, an inclinometer and a deflection meter, and the environmental monitoring equipment includes a water flow meter, a water level meter, an anemometer and a soil moisture meter.
Citation Information
Patent Citations
Bridge structure health monitoring and early warning system and early warning method
CN113865549A
Bridge health monitoring early warning system and working method thereof
CN109887243A
Bridge intelligent online monitoring and early warning system based on big data analysis
CN112380599A
Bridge health monitoring system and method based on big data
CN114282398A
Bridge health monitoring method and system based on wireless sensor network
CN114894411A
Cited By
State monitoring method for bridge structure
CN120744629A
A method for condition monitoring of a bridge structure
CN120744629B
Bridge structure health monitoring and early warning system
CN122468200A
Mountainous in-service highway bridge safety operation method based on large model
CN122777928A
