Large-span suspension bridge girder disease monitoring method and system

Through the combination of BIM model and GIS system, drones and sensors are used to monitor large-span suspension bridge diseases, solving the problems of low efficiency and difficulty in detecting concealed diseases in the existing technology, and realizing intelligent management and risks of bridge health status Assessment, improving the safety and durability of the bridge.

CN119043409APending Publication Date: 2024-11-29广东星层建筑科技股份有限公司

Patent Information

Application Number
CN202411040351.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing large-span suspension bridge disease monitoring methods are inefficient, traditional equipment is difficult to detect concealed diseases, and the lack of an integrated management platform, which leads to difficulties in data analysis and decision-making.

Method used

The BIM model construction and GIS system are combined to monitor the bridge's health status in real time through drones and sensors, and use computer vision algorithms to identify diseases, draw disease distribution maps and conduct risk assessments to achieve intelligent and visual management of bridges.

Benefits of technology

The efficiency and accuracy of disease monitoring of large-span suspension bridges has been improved, integrated management of bridge health has been achieved, and the safety and durability of bridges have been enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119043409A_ABST
    Figure CN119043409A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of bridge structure monitoring, in particular to a large-span suspension bridge damage monitoring method and system, and the method comprises the following steps: constructing a BIM model of a bridge; segmenting a key structure in the BIM model to simulate and analyze the complex positioning problem of the key structure part of the bridge concrete body; deploying a plurality of sensors at key structure parts of the bridge to monitor the health state of the bridge in real time; the unmanned aerial vehicle inspects the bridge concrete body regularly, collects image data and transmits the image data to the central processing system; the central processing system processes the acquired image data and identifies diseases; and drawing a disease distribution diagram by using a GIS system and carrying out risk assessment. According to the method, the health condition of the bridge is evaluated and predicted by using an artificial intelligence technology, and disease identification, analysis and prediction are performed on the monitoring data of the large concrete body, so that intelligent diagnosis and early warning of the large concrete body are realized, and the maintenance effect and prevention capability of the large concrete body are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of bridge structure monitoring, and in particular to a method and system for monitoring defects of a long-span suspension bridge. Background Art

[0002] With the acceleration of urbanization, long-span suspension bridges, as important transportation infrastructure, play a vital role in the modern transportation network. These bridges have complex structures and usually use large concrete components as the main load-bearing parts. Due to the long-term influence of complex environmental factors and use conditions, long-span suspension bridges are prone to various diseases, such as cracks, corrosion, and spalling, which will directly affect the safety and durability of the bridges.

[0003] At present, the disease monitoring of long-span suspension bridges mainly relies on manual inspections and some traditional monitoring equipment, such as strain gauges, accelerometers, etc. However, these methods have the following problems:

[0004] Low efficiency of manual inspection: Manual inspection often takes a long time, is costly, and is difficult to cover all areas, especially for large-span suspension bridges with complex structures.

[0005] Limitations of traditional monitoring equipment: Although traditional monitoring equipment can monitor certain specific types of diseases in real time, it is not effective in detecting hidden diseases and it is difficult to fully assess the overall health of the bridge.

[0006] Lack of an integrated management platform: Most existing monitoring systems operate independently, making it difficult to effectively integrate and share data, making data analysis and decision-making difficult. Summary of the invention

[0007] The purpose of the present invention is to improve the efficiency and accuracy of disease monitoring of long-span suspension bridges, realize the integration, intelligence and visualization of bridge health monitoring, and improve the safety and durability of bridges. To achieve the purpose of the present invention, the following technical solutions are adopted:

[0008] The first aspect of the present invention provides a method for monitoring long-span suspension bridge defects, comprising the following steps:

[0009] Constructing a BIM model of the bridge;

[0010] Segment the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body;

[0011] Deploy several sensors at key structural parts of the bridge to monitor the health status of the bridge in real time;

[0012] Regularly inspect the bridge concrete body through drones and collect image data to transmit to the central processing system;

[0013] The central processing system processes the collected image data and identifies diseases;

[0014] Use GIS system to draw disease distribution map and conduct risk assessment.

[0015] Further improvements are made in that the specific methods for constructing the BIM model of the bridge include:

[0016] According to the design drawings and actual construction records of the bridge, a 3D model of each component of the bridge is established, including the bridge tower, main cable, anchorage, and key structures of the bridge deck;

[0017] Add detailed information of each bridge structure into the BIM model, including geometric dimensions, material properties, construction date, and maintenance records;

[0018] The accuracy of the BIM model was verified by comparing it with the actual bridge structure.

[0019] Further improvements are made by segmenting the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body. The specific methods include:

[0020] Export the BIM model to a format compatible with Rhino software, open the model in Rhino, select the key structural parts that need to be monitored for defects, and use Rhino's "Divide" command to divide the selected structure based on a predetermined distance or structural feature. Through model segmentation, large concrete bodies can be subdivided into multiple small areas to facilitate subsequent defect location and analysis.

[0021] Further improvements are to deploy several sensors at key structural parts of the bridge to monitor the health status of the bridge in real time. The specific methods include:

[0022] According to the structural characteristics of the bridge, a number of sensors are deployed at key parts of the bridge, and the sensors include at least one or more of stress / strain sensors, vibration sensors, displacement sensors, temperature and humidity sensors, and accelerometers;

[0023] The sensors continuously collect real-time data of the bridge and send it to the cloud server for storage via wireless network;

[0024] According to the bridge design specifications and empirical data, the normal range of monitoring indicators is set, and when the data collected by the sensor exceeds the normal range, an alarm is triggered;

[0025] Big data analysis and machine learning techniques are used to process and analyze the data collected by sensors to assess the health of the bridge and predict future performance changes.

[0026] A further improvement is that the specific method of regularly inspecting the bridge concrete body by drone and collecting image data to transmit to the central processing system includes:

[0027] Equip drones with high-precision positioning systems and high-definition cameras, formulate drone flight plans, including take-off points, flight altitudes, speeds, and set flight routes to ensure coverage of all key structural parts, and consider wind speed and weather conditions to ensure safe flight. Use drones to collect high-definition images of the bridge structure surface, and use wireless transmission technology to transmit image data in real time to the central processing system. Image data includes image files, GPS location information, and shooting time.

[0028] A further improvement is that the specific method for the central processing system to process the collected image data and identify the disease includes:

[0029] Preprocessing the received image data in the central monitoring system, including denoising and grayscale conversion;

[0030] Use image enhancement technology to improve image quality and increase the accuracy of subsequent disease identification;

[0031] Use computer vision algorithms to automatically identify defects in images and identify the type, location, size, and shape of the defects;

[0032] The identified defect information is matched with the BIM model, and the specific location where the defect occurs in the BIM model is marked through the image recognition results.

[0033] Further improvements are that the specific methods of using GIS system to draw disease distribution maps and conduct risk assessment include:

[0034] Import structural information and defect identification results from the BIM model into the GIS system;

[0035] Integrate GPS location information collected by drones with coordinate information in the BIM model;

[0036] In the GIS system, the disease distribution map is drawn based on the location information of the disease;

[0037] Analyze the three-dimensional spatial distribution of defects and their changing trends over time, evaluate the impact of defects on the overall safety of the bridge, consider the type, location, size, and shape of the defects, and evaluate the potential impact on the bridge structure.

[0038] A further improvement is that the disease monitoring method further comprises:

[0039] A climbing robot is used to regularly monitor the bridge cables. The sensors on the climbing robot collect the structural response data of the cables under different working conditions, including displacement, strain, and vibration. The high-definition camera on the climbing robot is used to capture all-round images of the cables and record their appearance, cracks, and rust.

[0040] A further improvement is that the disease monitoring method further comprises:

[0041] According to the risk assessment results of the GIS system, the maintenance team is arranged to conduct on-site inspections to confirm the damage situation. According to the severity and development trend of the damage, a corresponding maintenance plan is formulated and maintenance work is carried out according to the maintenance plan to ensure the safe operation of the bridge.

[0042] The second aspect of the present invention provides a long-span suspension bridge disease monitoring system, comprising:

[0043] BIM model building module, used to build the BIM model of the bridge;

[0044] The segmentation module is used to segment the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body;

[0045] A bridge health status detection module is used to monitor the health status of the bridge in real time through a number of sensors deployed at key structural parts of the bridge;

[0046] The drone inspection module is used to regularly inspect the bridge using drones and collect image data to transmit to the central processing system module;

[0047] The central processing system module is used to process the collected image data and identify diseases;

[0048] The disease assessment module is used to draw disease distribution maps and conduct risk assessment using the GIS system.

[0049] The beneficial effects of the present invention are:

[0050] The present invention utilizes BIM technology to construct a three-dimensional model of a bridge, which can accurately reflect the geometric shape, material properties and structural performance of the bridge, and realize the digital design and management of the bridge; utilizes GIS technology to process and publish the spatial data of the bridge, and can associate and analyze data such as the location, status, history and prediction information of the bridge, realize the spatial display and decision support of the bridge, and improve the operation level and safety of the bridge; utilizes artificial intelligence technology to evaluate and predict the health status of the bridge, and identifies, analyzes and predicts diseases of the monitoring data of large concrete bodies, realizes intelligent diagnosis and early warning of large concrete bodies, and improves the maintenance effect and prevention ability of large concrete bodies. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a flow chart of a method for monitoring defects of a long-span suspension bridge according to the present invention;

[0052] Figure 2 It is a schematic diagram of a long-span suspension bridge disease monitoring system of the present invention;

[0053] Figure 3 Some pictures taken by a drone to inspect the concrete body of the bridge. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment 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 should fall within the scope of protection of the present invention.

[0055] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0056] Please refer to the attached Figure 1 A first aspect of an embodiment of the present invention provides a method for monitoring defects of a long-span suspension bridge, comprising the following steps:

[0057] Step S1: construct a BIM model of the bridge. BIM (Building Information Modeling) is a digital technology that can create a three-dimensional model containing all structural components.

[0058] Step S2: Segment the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body.

[0059] It can be understood that by subdividing the model, the key structural components of the bridge, such as pylons, main cables, hangers, etc., can be more accurately defined and simulated, which helps to better understand the response behavior of these components under different environmental conditions.

[0060] Step S3: Deploy several sensors at key structural parts of the bridge to monitor the health status of the bridge in real time.

[0061] Step S4: Regularly inspect the bridge concrete body through drones and collect image data to transmit to the central processing system.

[0062] Understandably, drones can be highly efficient in conducting visual inspections, especially in hard-to-reach locations, e.g. Figure 3 Shown are some pictures taken by a drone inspecting the concrete body of a bridge.

[0063] Step S5: The central processing system processes the collected image data and identifies diseases.

[0064] Types of defects include: Concrete cracking: Identify cracks on the concrete surface, especially early signs of fine cracks. Concrete spalling: Check whether there is spalling on the concrete surface and identify the size of the spalling area. Exposed rebar: Observe whether the rebar is exposed in the concrete structure and assess the length and range of the exposed rebar. Paint deterioration: Check whether the paint layer on the bridge surface has deterioration such as peeling, fading or cracking.

[0065] Step S6: Use the GIS system to draw a disease distribution map and conduct risk assessment.

[0066] It is understandable that GIS (Geographic Information System) can help manage and analyze spatial data. Through the GIS system, the location of the disease can be visualized and combined with other factors (such as traffic flow, environmental impact, etc.) for risk assessment.

[0067] The embodiment of the present invention uses BIM technology to construct a three-dimensional model of the bridge, which can accurately reflect the geometric shape, material properties and structural performance of the bridge, and realize the digital design and management of the bridge; uses GIS technology to process and publish the spatial data of the bridge, and can associate and analyze data such as the location, status, history and prediction information of the bridge, realize spatial display and decision support of the bridge, and improve the operation level and safety of the bridge; uses artificial intelligence technology to evaluate and predict the health status of the bridge, and identifies, analyzes and predicts diseases of the monitoring data of large concrete bodies, realizes intelligent diagnosis and early warning of large concrete bodies, and improves the maintenance effect and prevention ability of large concrete bodies.

[0068] In a feasible solution of this embodiment, the specific method of constructing the BIM model of the bridge in step S1 includes:

[0069] Choose professional BIM software suitable for bridge design, such as Autodesk Revit, Tekla Structures, etc., and build a three-dimensional model of each component of the bridge according to the design drawings and actual construction records of the bridge, including key structures such as bridge towers, main cables, anchors, and bridge decks.

[0070] Add detailed information of each structural component of the bridge to the BIM model, including but not limited to geometric dimensions, material properties, construction date, maintenance records, etc.

[0071] The parametric function of BIM software ensures the editability and scalability of the model, which facilitates subsequent maintenance and updates.

[0072] The accuracy of the BIM model was verified by comparing it with the actual bridge structure.

[0073] In a feasible solution of this embodiment, the specific method of segmenting the key structure in the BIM model in step S2 to simulate and analyze the complex positioning problem of the key structural parts of the bridge concrete body includes:

[0074] Export the BIM model to a format compatible with Rhino software, usually .obj, .3dm or other compatible formats, and open the model in Rhino. Select the key structural parts that need to be monitored for defects, such as the concrete part of the bridge tower, and use Rhino's "Divide" command to divide the selected structure. The division is based on a predetermined distance or structural feature. For example, you can choose to divide once every certain distance, or divide along the natural boundary of the structure; through model division, the large concrete body is subdivided into multiple small areas, each of which can be regarded as a separate monitoring unit to facilitate subsequent defect location and analysis; you can also assign a unique identifier to each small area to track and record the development of the disease.

[0075] In a feasible solution of this embodiment, a specific method of deploying a number of sensors at key structural parts of a bridge to monitor the health status of the bridge in real time includes:

[0076] According to the structural characteristics of the bridge, several sensors are deployed at key parts of the bridge, such as the bridge tower, main cable, and bridge deck. The sensors include at least one or more of stress / strain sensors, vibration sensors, displacement sensors, temperature and humidity sensors, and accelerometers. Among them, the stress / strain sensor is used to monitor the stress changes at key parts of the bridge, the vibration sensor is used to detect abnormal vibration, the displacement sensor is used to monitor the displacement and deformation of the bridge, the temperature and humidity sensor is used to monitor the impact of environmental temperature and humidity changes on the bridge, and the accelerometer is used to measure the vibration frequency of the bridge.

[0077] The sensors continuously collect real-time data of the bridge and send it to the cloud server for storage via wireless networks (such as Wi-Fi, LoRa, NB-IoT, etc.).

[0078] According to the bridge design specifications and empirical data, the normal range of monitoring indicators is set, and an alarm is triggered when the data collected by the sensor exceeds the normal range.

[0079] Big data analysis and machine learning techniques (such as supervised learning, unsupervised learning, reinforcement learning, etc.) are used to process and analyze the data collected by sensors to assess the health of the bridge and predict future performance changes.

[0080] In a feasible solution of this embodiment, the specific method of regularly inspecting the bridge concrete body by using a drone and collecting image data to transmit to the central processing system in step S4 includes:

[0081] Configure drones with high-precision positioning systems (such as RTK GPS) and high-definition camera equipment to ensure that the image quality is not less than 1080p, and ideally 4K resolution. Develop a drone flight plan, including parameters such as take-off point, flight altitude, speed, etc., set the flight route, and ensure that all key structural parts are covered, especially the bridge tower and anchor area. Consider wind speed and weather conditions to ensure safe flight. Use drones to collect high-definition images of the bridge structure surface, and use wireless transmission technology to transmit image data in real time to the central processing system. The image data includes but is not limited to image files, GPS location information, shooting time, etc.

[0082] Drones can quickly cover large areas, greatly improving inspection efficiency compared to traditional manual inspection methods. They reduce the labor and time costs required for manual inspections, and also reduce the time that roads are closed due to inspections. GPS location information and shooting time can be used to help establish a historical record of disease development, which is very useful for tracking disease trends.

[0083] In a feasible solution of this embodiment, the specific method in step S5 in which the central processing system processes the collected image data and identifies the disease includes:

[0084] The received image data is preprocessed in the central monitoring system, including denoising and grayscale conversion.

[0085] Use image enhancement techniques (such as histogram equalization, contrast stretching, etc.) to improve image quality and increase the accuracy of subsequent disease identification.

[0086] Computer vision algorithms are used to automatically identify and extract defects in images. For example, convolutional neural networks (CNNs) in deep learning can be used for training and detection to identify the type, location, size, shape, etc. of defects.

[0087] The identified defect information is matched with the BIM model, and the specific location of the defect in the BIM model is marked through the image recognition results. By combining the image recognition results with the BIM model, it helps to integrate multiple data sources and form a unified data view.

[0088] In a feasible solution of this embodiment, the specific method of using the GIS system to draw a disease distribution map and perform risk assessment in step S6 includes:

[0089] Import the structural information and defect identification results in the BIM model into the GIS system.

[0090] Integrate GPS location information collected by drones and coordinate information in the BIM model.

[0091] In the GIS system, the disease distribution map is drawn based on the location information of the disease.

[0092] Analyze the three-dimensional spatial distribution of defects and their changing trends over time, evaluate the impact of defects on the overall safety of the bridge, consider the type, location, size, and shape of the defects, and evaluate the potential impact on the bridge structure.

[0093] It can be understood that by drawing a disease distribution map based on the location information of the disease in the GIS system, a clear visual display is provided to managers to help them understand the overall distribution of the disease.

[0094] In a feasible solution of this embodiment, the disease monitoring method further includes:

[0095] A climbing robot is used to regularly monitor the bridge cables. The sensors on the climbing robot collect the structural response data of the cables under different working conditions, including displacement, strain, and vibration. The high-definition camera on the climbing robot is used to capture all-round images of the cables and record their appearance, cracks, and rust.

[0096] In a feasible solution of this embodiment, the disease monitoring method further includes:

[0097] According to the risk assessment results of the GIS system, the maintenance team is arranged to conduct on-site inspections to confirm the damage situation. According to the severity and development trend of the damage, a corresponding maintenance plan is formulated and maintenance work is carried out according to the maintenance plan to ensure the safe operation of the bridge.

[0098] In a feasible solution of this embodiment, the disease monitoring method further includes:

[0099] A prediction model is established using machine learning algorithms to predict the location and severity of bridge damage in the future so that preventive measures can be taken in advance, including:

[0100] Collect historical monitoring data, environmental data and maintenance records of the bridge over the past period of time, including sensor data, drone image data, manual inspection records, weather conditions, humidity and temperature.

[0101] Data preprocessing includes data cleaning (removing invalid data, handling missing values ​​and outliers), feature engineering (selecting or constructing useful feature variables), and data integration (integrating different types of data into a unified data set).

[0102] In the feature selection stage, correlation analysis and feature importance assessment are used to determine which features are most correlated with the disease and which features are most valuable for prediction. Then, a suitable machine learning model is selected, such as logistic regression, support vector machine (SVM), neural network, random forest, etc., and the selected model is trained using the training data set. In order to improve the stability and accuracy of the model, the hyperparameters of the model need to be adjusted through methods such as grid search or random search, and the use of ensemble learning methods should be considered.

[0103] After the model training is completed, it is necessary to evaluate the model, select appropriate evaluation indicators (such as accuracy, precision, recall, F1 score, etc.), and evaluate the performance of the model on an independent test data set; in addition, it is also necessary to pay attention to the interpretability of the model and provide confidence intervals or probability distributions for the prediction results to help decision makers understand the uncertainty of the prediction; based on the prediction results, preventive maintenance plans can be formulated to optimize resource allocation and reduce future maintenance costs.

[0104] Over time, the model may become obsolete, so it is necessary to retrain the model and update the dataset regularly; in addition, it is also important to establish a feedback mechanism to collect emerging disease data to continuously improve the model.

[0105] The present invention uses a machine learning algorithm to establish a prediction model to predict the location and severity of possible bridge defects in the future. It can effectively use machine learning technology to predict possible bridge defects in the future and take preventive measures in advance, thereby improving the safety and service life of the bridge.

[0106] In a feasible solution of this embodiment, the disease monitoring method further includes:

[0107] The deep reinforcement learning algorithm is used to train the drone so that it can adjust its flight path and operation mode according to environmental changes. When the drone regularly inspects bridges, it can adjust the flight altitude and angle according to actual conditions to obtain image data from the best perspective. The specific method is as follows:

[0108] Define mission objectives: Identify the type of mission the drone needs to complete, such as inspections of large concrete structures on bridges; set mission completion criteria, such as completion time, flight path length, energy consumption, and other key indicators.

[0109] Build a simulation environment: Create a virtual environment that simulates real-world conditions, including bridge shape, terrain, weather, obstacles, etc.; it is worth noting that the simulation environment should be realistic enough to ensure that the trained policy can also be effectively applied in reality.

[0110] Design state space: define the state variables of the drone, including position, speed, altitude, remaining battery, etc. These variables will be used to describe the environmental state of the drone at every moment.

[0111] Set action space: Specifies the set of actions that the drone can take, such as ascending, descending, moving forward, backward, moving left and right, accelerating, decelerating, turning, etc. The action space determines how the drone interacts with the environment.

[0112] Establish a reward function: Establish an evaluation system to evaluate the impact of each action on the completion of the task. The reward function should encourage the drone to complete the task efficiently and safely while minimizing energy consumption and risk.

[0113] Data collection and preprocessing: Generate a large amount of flight data in a simulated environment, covering different environmental conditions and mission requirements, and preprocess the collected data to facilitate the subsequent training process.

[0114] Training deep reinforcement learning models: Use deep neural networks (such as convolutional neural networks (CNNs)) to process state information and use deep Q-learning (DQN), policy gradient methods, or other reinforcement learning algorithms to train the agent.

[0115] Testing and verification: Test the trained model in a simulated environment to ensure that it can complete the task under various conditions and verify whether the drone can correctly respond to various emergencies, such as obstacle avoidance and emergency landing.

[0116] Actual deployment and iteration: Deploy the trained model to the drone for testing and collect data feedback from actual flight to further optimize model performance.

[0117] The second aspect of an embodiment of the present invention proposes a large-span suspension bridge defect monitoring system, which corresponds to a large-span suspension bridge defect monitoring method provided by the above-mentioned embodiment of the present invention. Since the large-span suspension bridge defect monitoring system provided by the embodiment of the present invention corresponds to the large-span suspension bridge defect monitoring method provided by the above-mentioned embodiment of the present invention, the implementation method of the aforementioned large-span suspension bridge defect monitoring method is also applicable to the large-span suspension bridge defect monitoring system provided by this embodiment.

[0118] Specifically, Figure 2 As shown, in this embodiment, a long-span suspension bridge disease monitoring system includes:

[0119] BIM model building module, used to build the BIM model of the bridge.

[0120] The segmentation module is used to segment the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body.

[0121] The bridge health status detection module is used to monitor the bridge health status in real time through a number of sensors deployed at key structural parts of the bridge.

[0122] The drone inspection module is used to regularly inspect the bridge via drones and collect image data to transmit to the central processing system module.

[0123] The central processing system module is used to process the collected image data and identify diseases.

[0124] The disease assessment module is used to draw disease distribution maps and conduct risk assessment using the GIS system.

[0125] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for monitoring long-span suspension bridge defects, characterized in that: The following steps are involved: Constructing a BIM model of the bridge; Segment the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body; Deploy several sensors at key structural parts of the bridge to monitor the health status of the bridge in real time; Regularly inspect the bridge concrete body through drones and collect image data to transmit to the central processing system; The central processing system processes the collected image data and identifies diseases; Use GIS system to draw disease distribution map and conduct risk assessment.

2. A method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: Specific methods for constructing a BIM model of a bridge include: According to the design drawings and actual construction records of the bridge, a 3D model of each component of the bridge is established, including the bridge tower, main cable, anchorage, and key structures of the bridge deck; Add detailed information of each bridge structure into the BIM model, including geometric dimensions, material properties, construction date, and maintenance records; The accuracy of the BIM model was verified by comparing it with the actual bridge structure.

3. A long-span suspension bridge disease monitoring method according to claim 1, characterized in that: The specific methods for segmenting the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body include: Export the BIM model to a format compatible with Rhino software, open the model in Rhino, select the key structural parts that need to be monitored for defects, and use Rhino's "Divide" command to divide the selected structure based on a predetermined distance or structural feature. Through model segmentation, the large concrete body can be subdivided into multiple small areas to facilitate subsequent defect location and analysis.

4. A method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: The specific methods of deploying several sensors at key structural parts of the bridge to monitor the health status of the bridge in real time include: According to the structural characteristics of the bridge, a number of sensors are deployed at key parts of the bridge, and the sensors include at least one or more of stress / strain sensors, vibration sensors, displacement sensors, temperature and humidity sensors, and accelerometers; The sensors continuously collect real-time data of the bridge and send it to the cloud server for storage via wireless network; According to the bridge design specifications and empirical data, the normal range of monitoring indicators is set, and when the data collected by the sensor exceeds the normal range, an alarm is triggered; Big data analysis and machine learning techniques are used to process and analyze the data collected by sensors to assess the health of the bridge and predict future performance changes.

5. The method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: The specific methods of regularly inspecting the bridge concrete body by drones and collecting image data to transmit to the central processing system include: Equip drones with high-precision positioning systems and high-definition cameras, formulate drone flight plans, including take-off points, flight altitudes, speeds, and set flight routes to ensure coverage of all key structural parts, and consider wind speed and weather conditions to ensure safe flight. Use drones to collect high-definition images of the bridge structure surface, and use wireless transmission technology to transmit image data in real time to the central processing system. Image data includes image files, GPS location information, and shooting time.

6. A method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: The specific methods for the central processing system to process the collected image data and identify diseases include: Preprocessing the received image data in the central monitoring system, including denoising and grayscale conversion; Use image enhancement technology to improve image quality and increase the accuracy of subsequent disease identification; Use computer vision algorithms to automatically identify defects in images and identify the type, location, size, and shape of the defects; The identified defect information is matched with the BIM model, and the specific location of the defect in the BIM model is marked through the image recognition results.

7. A method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: Specific methods for using GIS system to draw disease distribution map and conduct risk assessment include: Import structural information and defect identification results from the BIM model into the GIS system; Integrate GPS location information collected by drones with coordinate information in the BIM model; In the GIS system, the disease distribution map is drawn based on the location information of the disease; Analyze the three-dimensional spatial distribution of defects and their changing trends over time, evaluate the impact of defects on the overall safety of the bridge, consider the type, location, size, and shape of the defects, and evaluate the potential impact on the bridge structure.

8. The method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: The disease monitoring method also includes: A climbing robot is used to regularly monitor the bridge cables. The sensors on the climbing robot collect the structural response data of the cables under different working conditions, including displacement, strain, and vibration. The high-definition camera on the climbing robot is used to capture all-round images of the cables and record their appearance, cracks, and rust.

9. The method for monitoring defects of a long-span suspension bridge according to claim 1, characterized in that: The disease monitoring method also includes: According to the risk assessment results of the GIS system, the maintenance team is arranged to conduct on-site inspections to confirm the damage situation. According to the severity and development trend of the damage, a corresponding maintenance plan is formulated and maintenance work is carried out according to the maintenance plan to ensure the safe operation of the bridge.

10. A long-span suspension bridge disease monitoring system, characterized in that: include: BIM model building module, used to build the BIM model of the bridge; The segmentation module is used to segment the key structures in the BIM model to simulate and analyze the complex positioning problems of the key structural parts of the bridge concrete body; The bridge health status detection module is used to monitor the bridge health status in real time through a number of sensors deployed at key structural parts of the bridge; The drone inspection module is used to regularly inspect the bridge using drones and collect image data to transmit to the central processing system module; The central processing system module is used to process the collected image data and identify diseases; The disease assessment module is used to draw disease distribution maps and conduct risk assessment using the GIS system.

Citation Information

Patent Citations

  • Bridge monitoring method

    CN108645360A

  • Bridge management and maintenance system based on BIM-GIS

    CN110287604A

  • Bridge safety monitoring platform based on GIS and BIM technologies

    CN113432657A

  • BIM (Building Information Modeling) analysis method for deducing basement partition construction scheme

    CN117763693A

  • Digital twin technology-based containment twin system and construction method therefor

    WO2023168947A1

Cited By

  • Building material quality detection method and system

    CN119395237A

  • Bridge disease two-stage analysis and risk assessment method and system

    CN119475107A

  • Quantitative analysis method for influence of bridge diseases on structural performance

    CN119783195A

  • Bridge and tunnel intelligent monitoring method and system

    CN120609407A

  • Intelligent health maintenance prediction method and system for bridge inspection

    CN121505477A