Bridge deformation monitoring device based on digital twin technology

Abstract

The invention discloses a bridge deformation monitoring device based on a digital twinborn technology, and the device can carry out the real-time correction of collected data through employing a data optimization algorithm, and eliminates an error caused by an environment factor. The algorithms can automatically adjust the measurement result based on the difference between the theoretical model and the actual sensor data, so that the measurement result is more accurate, and additional hardware investment is not needed. The sensor data is compensated and corrected through an optimization algorithm, the precision and stability of the monitoring system can be effectively improved, it is ensured that the collected data truly reflects the actual deformation state of the bridge, and therefore a more reliable basis is provided for safety monitoring and decision making of the bridge.

Description

Technical Field

[0001] The present invention belongs to the field of bridge deformation monitoring. Specifically, it relates to a bridge deformation monitoring device based on digital twin technology. Background Art

[0002] With the acceleration of the urbanization process, bridges, as important transportation infrastructure, their structural safety and stability are crucial for traffic safety, social economy, and the safety of people's lives and property. Bridges are long-term affected by various external factors such as vehicle loads, temperature changes, wind, and earthquakes. As the service life increases, the structure of the bridge gradually ages, which may lead to problems such as deformation, cracks, and corrosion. Therefore, the health monitoring and maintenance management of bridges are particularly important.

[0003] Traditional bridge deformation usually relies on regular manual inspections or static measurements using traditional sensors. These methods have some limitations:

[0004] To overcome the above problems, an intelligent bridge monitoring system based on the Internet of Things technology has emerged. By installing various sensors (such as laser displacement sensors, tilt sensors, etc.) at key monitoring points of the bridge, real-time data collection can be achieved, providing comprehensive health monitoring data of the bridge. However, even with various sensors and real-time data collection, the sensor data is easily affected by environmental factors, resulting in data deviation, and effective error correction and optimization are required. Moreover, during the bridge monitoring process, external factors such as vehicles passing by, wind, and earthquakes may cause the sensors to be instantaneously vibrated, and these vibrations will disturb the measured values, especially in a highly dynamic environment. For example, when a vehicle passes by, the vibration on the bridge surface may cause instantaneous fluctuations in the displacement value measured by the sensor, affecting the accuracy of the data. Wind may also cause misreading of the tilt sensor. Especially when the wind speed is high, the sensor may produce unstable measurement results due to external disturbances.

[0005] In view of this, the present invention is specifically proposed. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a bridge deformation monitoring device based on digital twin technology, which solves the problems raised in the above background art.

[0007] To solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0008] A bridge deformation monitoring device based on digital twin technology, comprising: an Internet of Things sensor module, which includes a laser displacement sensor and an inclination sensor, installed at key monitoring points of the bridge for collecting real-time deformation data of the bridge; the laser displacement sensor is a device for measuring the displacement between the measured object and the sensor [1] . Similar to the total station ranging method, it emits laser in a fixed direction to the measured object at a certain frequency according to its own laser emitter, and obtains the distance by calculating the round-trip time difference. Set a certain interval to collect multiple distance data, and the obtained difference is the displacement information of the object during this period. Laser displacement sensors are now widely used in the field of Internet of Things measurement [2]

[0009] The inclination sensor is a device for measuring the inclination angle of an object relative to the ground plane or a reference axis [2] , which has been applied in the fields of architecture, automation equipment and geological survey for many years, and provided accurate inclination angle information in many projects. Its safety and high efficiency are well-known. There are many types of sensors, each working based on different principles, including technologies such as accelerometers and rotary gyroscopes [3] .

[0010] References:

[0011] [1] Liu Zhongnan, Wang Zhongqing. Research on the rail settlement monitoring system based on laser displacement sensors [J]. Computers & Telecommunications, 2022(3): 55-59.

[0012] [2] Fan Feng, Zhang Xin. Comparative analysis of static load tests and various deflection measurement methods for long-span suspension bridges [J]. Guangdong Highway Communications, 2021(5): 40-45.

[0013] [3] Du Lanshun. Application analysis of deflection measurement technology in bridge monitoring [J]. Transport World, 2022(36): 152-154.

[0014] A digital twin modeling and synchronization module, which is used to construct and update the virtual digital twin model of the bridge according to the real-time collected sensor data, and the model reflects the deformation state of the bridge in real time;

[0015] A data processing and analysis module, which is used to optimize the deformation data collected by the Internet of Things sensor module by the least squares algorithm, correct errors and obtain accurate monitoring results;

[0016] A danger warning module, which is used to automatically trigger an alarm when the bridge deformation reaches the set threshold, reminding the bridge management personnel to conduct inspections and maintenance;

[0017] Data transmission and remote monitoring module. The data transmission and remote monitoring module is used to upload the data collected by the sensors to the cloud platform in real time and view the real-time deformation data of the bridge through a remote monitoring device.

[0018] Optionally, the steps of constructing and updating the virtual digital twin model of the bridge based on the sensor data collected in real time, where the model reflects the deformation state of the bridge in real time are as follows:

[0019] Based on the design drawings, structural characteristics and historical monitoring data of the bridge, construct a preliminary digital twin model. Among them, the digital twin model includes the geometric shape of the bridge, structural parameters (such as span, material, load capacity, etc.) and its stress analysis data, forming an ideal state model of the bridge;

[0020] Connect the sensor data collected in real time with the digital twin model to update the virtual model of the bridge. Whenever the sensor data changes, the system will adjust the deformation state in the virtual model according to the real-time data, so that the virtual model is synchronized with the actual monitoring situation and accurately reflects the deformation process of the bridge.

[0021] Optionally, the steps of optimizing the deformation data collected by the IoT sensor module using the least squares algorithm, correcting errors and obtaining accurate monitoring results are as follows:

[0022] Based on the physical model of the bridge structure, construct an error equation system to describe the difference between the sensor data and the theoretical model, and consider possible sensor errors, environmental interference and other factors;

[0023] Use the least squares algorithm to optimize the error model and obtain the correction coefficient by minimizing the sum of the squared errors between the sensor data and the theoretical values. Among them, the theoretical values represent the deformation state that the bridge should reach under ideal conditions and are used as the reference benchmark for the sensor measurement values. The specific deformation state can be obtained through finite element analysis of existing technology simulation.

[0024] According to the correction coefficient optimized by the least squares method, correct the errors of the data collected by the sensors, eliminate the systematic errors, and obtain more accurate bridge deformation data. Then, verify the accuracy of the corrected monitoring results by cross-validation or comparison with known reliable data sources to ensure that the corrected data is valid and has high precision;

[0025] Then, use the corrected data as the final accurate monitoring result to update the bridge deformation state in the digital twin model.

[0026] Optionally, since the laser displacement sensor is affected by temperature changes, the steps for adjusting the error of the laser displacement sensor using the least squares algorithm are as follows:

[0027] Collect displacement data of the bridge from the laser displacement sensor (such as the deflection and deformation of the bridge), and ensure that the measurement time of each data point and the reading value of the sensor are recorded;

[0028] Assume that the error between the sensor data and environmental factors (such as temperature) is a linear relationship, then the objective function for error correction is expressed as: where, y measured (i) is the original measurement value of the sensor, y actual (i) is the actual deformation value of the bridge, T(i) is the temperature value at the time of measurement, and α is the coefficient to be optimized, representing the influence of temperature change on the measurement error; among them, the actual deformation value of the bridge is obtained by actual measurement using on-site measurement equipment, and the on-site measurement equipment includes but is not limited to on-site total stations.

[0029] By minimizing the objective function J(α), the optimal correction coefficient is obtained. The expression for minimizing the sum of squared errors usually involves taking the derivative and setting it to zero, and its expression is Then through the formula: Calculate the optimal correction coefficient: Solve the objective function to obtain the optimized correction coefficient α * ;

[0030] Use the obtained correction coefficient α * , to correct the measurement data of the sensor, and the corrected sensor data is: y corrected (i) = y measured (i) - α * , finally, input the corrected laser displacement sensor data into the digital twin model of the bridge to update the deformation state in the model.

[0031] Optionally, the vibrations generated when a vehicle passes by or changes in wind speed can cause instantaneous reading errors in the sensor and result in errors. Therefore, the steps for using the least squares algorithm to adjust the errors of the tilt sensor are as follows:

[0032] Collect tilt angle data of the bridge from the tilt sensor (such as tilt degree, angle changes at the bridge support points, etc.), and record the timestamp of each data point. At the same time as collecting the tilt data, it is also necessary to use devices such as vibration sensors or wind speed sensors to record dynamic factors in the environment, such as vibrations (caused by vehicle passing by or other external vibrations) and wind speed (which may affect sensor readings);

[0033] Set an objective function to minimize the sensor error. The objective function expresses the difference between the sensor measurement value and the actual value, while considering the influence of vibrations and wind speed. The objective function J(θ, α, β) can be expressed as: where,

[0034] y measured(i) is the measured value at the i-th time point, y actual (i) is the actual inclination value at the i-th time point, α and β are the correction coefficients to be optimized, representing the influence of vibration and wind speed on the error;

[0035] Using the least squares method, the optimal correction coefficients α * and β * are solved by minimizing the objective function J(θ, α, β) through an optimization algorithm, taking the partial derivatives of the objective function and setting them to zero. These two coefficients represent the influence of vibration and wind speed on the inclination sensor error.

[0036] Using the optimal correction coefficients α * and β * , the measurement data of the inclination sensor is corrected: y corrected (i) = y measured (i) - α * ·vibration i -β * ·wind i , where vibration i and wind i are the vibration and wind speed data at the i-th time point respectively.

[0037] Optionally, after obtaining the corrections of the laser displacement sensor and the inclination sensor, the corrected sensor data needs to be applied to update the digital twin model of the bridge. The steps are as follows:

[0038] Synchronize the corrected sensor data (the displacement and inclination angle data of the laser displacement sensor and the inclination sensor) into the digital twin model. Then, based on the corrected data, calculate the deformation state of the bridge through the formula and update the deformation curve and stress distribution in the digital twin model. Among them, ΔL(x, t) is the deformation amount of the bridge at position x and time t (for example, displacement or deflection), L is the total length of the bridge, representing the span from one end to the other end of the bridge, P(x) is the instantaneous load at position x (including traffic load, wind load, etc.), which can be obtained from the corrected sensor data and environmental data (such as traffic flow, wind speed, etc.), α is the temperature coefficient, considering the influence of temperature change on the thermal expansion or contraction of materials, usually a known constant, T(t) is the temperature value at time t, representing the influence of environmental temperature on the bridge deformation, E is the elastic modulus of the material, describing the stiffness of the material and reflecting the elastic properties of the bridge material, I(x) is the moment of inertia at position x, related to the cross-sectional geometry of the bridge and representing the bending resistance of the structure, dx is the small interval of integration, representing discrete calculation of the entire bridge to obtain local deformation data. Finally, based on the deformation state of the bridge, conduct risk assessment to identify potential dangerous areas or parts with serious deformation of the bridge.

[0039] Optionally, when the deformation of the bridge reaches a set threshold and an alarm is automatically triggered to remind the bridge management personnel to conduct inspections and maintenance, the deformation threshold is set based on the maximum allowable displacement, maximum tilt angle, and stress limit. When the deformation value (such as displacement, tilt angle) of the bridge exceeds the set safety threshold, the early warning mechanism is immediately triggered to generate alarm information, and relevant bridge management personnel are notified by means of e-mail, text message, mobile application, etc. Among them, the setting of the threshold refers to historical monitoring data, standard specifications, engineering experience, etc.

[0040] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all the advantages described below at the same time:

[0041] The present invention can perform real-time correction on the collected data by adopting data optimization algorithms, eliminating the errors caused by environmental factors. These algorithms can automatically adjust the measurement results based on the difference between the theoretical model and the actual sensor data to make them more accurate, and no additional hardware investment is required. By compensating and correcting the sensor data through the optimization algorithm, the accuracy and stability of the monitoring system can be effectively improved, ensuring that the collected data truly reflects the actual deformation state of the bridge, thereby providing a more reliable basis for the safety monitoring and decision-making of the bridge.

[0042] The following further describes in detail the specific implementation manners of the present invention with reference to the accompanying drawings. Description of the Drawings

[0043] The following drawings in the description are only some embodiments. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0044] Figure 1 is the system block diagram of the beam deformation monitoring device;

[0045] Figure 2 is the comparison chart of the recognition rates of the beam deformation monitoring device;

[0046] Figure 3 is the sensor layout diagram of the beam deformation monitoring device.

[0047] It should be noted that these drawings and the textual descriptions are not intended to limit the scope of the concept of the present invention in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. Specific Embodiments

[0048] Now, the present invention will be further described in detail with reference to the accompanying drawings.

[0049] Please refer toFigures 1-3 As shown in the figure, in this embodiment, a bridge deformation monitoring device based on digital twin technology is provided, including an Internet of Things sensor module. The Internet of Things sensor module includes a laser displacement sensor 3 and an inclination sensor 5, which are installed at key monitoring points of the bridge and are used to collect real-time deformation data of the bridge.

[0050] consisting of Figure 3 As shown in the figure, this figure is only one of various installation and measurement methods for the convenience of explanation. The actual installation positions of the sensors are not limited to this. The bridge is composed of a pier 1 and a beam body 2. The laser displacement sensor 3 is located at the edge of the pier 1 at both ends of the bridge by means of adhesive bonding or bolt fastening, and its laser beam points to the bottom surface of the beam body 2 near the mid-span. A reflection target 4 for reflecting the laser beam is arranged at the mid-span position below the beam body 2. The inclination sensor 5 is installed below the mid-span of the beam body 2 by means of adhesive bonding or bolt fastening. Due to the load effect, the maximum deflection deformation occurs at the mid-span position. In order to make the data obtained by the laser displacement sensor 3 more accurate. Therefore, the interval between the reflection target 4 and the inclination sensor 5 should be set to 5 - 50 cm, and the optimal interval is 20 cm. The reflection target 4 is made of an aluminum-based or plastic substrate, and the surface of the substrate is sprayed with a silver coating.

[0051] A digital twin modeling and synchronization module, which is used to construct and update the virtual digital twin model of the bridge according to the real-time collected sensor data, and the model reflects the deformation state of the bridge in real time;

[0052] A data processing and analysis module, which is used to optimize the deformation data collected by the Internet of Things sensor module by using the least squares algorithm, correct the errors and obtain accurate monitoring results;

[0053] A danger warning module, which is used to automatically trigger an alarm when the bridge deformation reaches a set threshold, reminding the bridge management personnel to conduct inspections and maintenance;

[0054] A data transmission and remote monitoring module, which is used to upload the data collected by the sensors to the cloud platform in real time and view the real-time deformation data of the bridge through a remote monitoring device. By adopting a data optimization algorithm, the present invention can correct the collected data in real time and eliminate the errors caused by environmental factors. These algorithms can automatically adjust the measurement results based on the difference between the theoretical model and the actual sensor data to make them more accurate, and no additional hardware investment is required. By compensating and correcting the sensor data through the optimization algorithm, the accuracy and stability of the monitoring system can be effectively improved, ensuring that the collected data truly reflects the actual deformation state of the bridge, thereby providing a more reliable basis for the safety monitoring and decision-making of the bridge.

[0055] In this embodiment, the steps of constructing and updating the virtual digital twin model of the bridge according to the sensor data collected in real time, where the model reflects the deformation state of the bridge in real time are as follows:

[0056] Based on the design drawings, structural characteristics, and historical monitoring data of the bridge, construct a preliminary digital twin model. Among them, the digital twin model includes the geometric shape of the bridge, structural parameters (such as span, material, load capacity, etc.), and its stress analysis data, forming an ideal state model of the bridge;

[0057] Dock the sensor data collected in real time with the digital twin model to update the virtual model of the bridge. Whenever the sensor data changes, the system will adjust the deformation state in the virtual model according to the real-time data, so that the virtual model is synchronized with the actual monitoring situation and accurately reflects the deformation process of the bridge.

[0058] In this embodiment, the steps of optimizing the deformation data collected by the Internet of Things sensor module using the least squares algorithm, correcting errors, and obtaining accurate monitoring results are as follows:

[0059] Based on the physical model of the bridge structure, construct an error equation system to describe the difference between the sensor data and the theoretical model, and consider possible sensor errors, environmental interference, and other factors;

[0060] Use the least squares algorithm to optimize the error model and obtain correction coefficients by minimizing the sum of the squared errors between the sensor data and the theoretical values;

[0061] According to the correction coefficients obtained by the least squares optimization, correct the errors in the data collected by the sensors, eliminate the systematic errors, and obtain more accurate bridge deformation data. Then, verify the accuracy of the corrected monitoring results by cross-validation or comparison with known reliable data sources to ensure that the corrected data is valid and has high precision;

[0062] Then, use the corrected data as the final accurate monitoring result to update the bridge deformation state in the digital twin model.

[0063] In this embodiment, since the laser displacement sensor 3 is affected by temperature changes, the steps for adjusting the error of the laser displacement sensor 3 using the least squares algorithm are as follows:

[0064] Collect the displacement data of the bridge (such as the deflection and deformation of the bridge) from the laser displacement sensor 3, and ensure that the measurement time of each data point and the reading value of the sensor are recorded;

[0065] Assume that the error between the sensor data and environmental factors (such as temperature) is a linear relationship, then the objective function of error correction is expressed as: where, y measured(i) is the original measurement value of the sensor, y actual (i) is the actual bridge deformation value, T(i) is the temperature value at the time of measurement, and α is the coefficient to be optimized, representing the influence of temperature change on the measurement error;

[0066] By minimizing the objective function J(α), the optimal correction coefficient is obtained. The expression for minimizing the sum of squared errors is usually carried out by taking the derivative and setting it to zero, and its expression is Then through the formula: Calculate the optimal correction coefficient: Solve the objective function to obtain the optimized correction coefficient α * ;

[0067] Use the obtained correction coefficient α * , to correct the measurement data of the sensor. The corrected sensor data is: y corrected (i) = y measured (i) - α * , Finally, input the corrected data of the laser displacement sensor 3 into the digital twin model of the bridge to update the deformation state in the model.

[0068] In this embodiment, the vibration or wind force change generated when the vehicle passes by will cause instantaneous reading errors of the sensor and generate errors. Therefore, the steps for adjusting the error of the tilt sensor 5 using the least squares algorithm are as follows:

[0069] Collect the tilt angle data of the bridge from the tilt sensor 5 (such as tilt degree, angle change of the bridge support point, etc.), and record the timestamp of each data point. While collecting the tilt data, it is also necessary to use devices such as vibration sensors or wind speed sensors to record the dynamic factors in the environment, such as vibration (caused by vehicle passing or other external vibrations) and wind speed (which may affect the sensor readings);

[0070] Set an objective function to minimize the sensor error. The objective function expresses the difference between the sensor measurement value and the actual value, while considering the influence of vibration and wind speed. The objective function J(θ, α, β) can be expressed as: Where, y measured (i) is the measurement value at the i-th time point, y actual (i) is the actual tilt value at the i-th time point, and α and β are the correction coefficients to be optimized, representing the influence of vibration and wind speed on the error;

[0071] Use the least squares method to minimize the objective function J(θ, α, β) through an optimization algorithm, take the partial derivatives of the objective function and set them to zero, and solve for the optimal correction coefficients α * and β * , These two coefficients represent the influence of vibration and wind speed on the error of the tilt sensor 5.

[0072] Using the optimal correction coefficients α * and β * , correct the measurement data of the tilt sensor 5: y corrected (i) = y measured (i) - α * ·vibration i - β * ·wind i , where vibration i and wind i are the vibration and wind speed data at the i-th time point respectively.

[0073] In this embodiment, after obtaining the corrections of the laser displacement sensor 3 and the tilt sensor 5, the corrected sensor data needs to be applied to update the digital twin model of the bridge. The steps are as follows:

[0074] Synchronize the corrected sensor data (the displacement and tilt angle data of the laser displacement sensor 3 and the tilt sensor 5) into the digital twin model. Then, based on the corrected data, calculate the deformation state of the bridge through the formula where ΔL(x, t) is the amount of deformation (e.g., displacement or deflection) of the bridge at position x and time t, L is the total length of the bridge, representing the span from one end to the other end of the bridge, P(x) is the instantaneous load at position x (including traffic load, wind load, etc.), which can be obtained from the corrected sensor data and environmental data (such as traffic flow, wind speed, etc.), α is the temperature coefficient, considering the influence of temperature change on the thermal expansion or contraction of materials, usually a known constant, T(t) is the temperature value at time t, representing the influence of environmental temperature on the bridge deformation, E is the elastic modulus of the material, describing the stiffness of the material and reflecting the elastic properties of the bridge material, I(x) is the moment of inertia at position x, related to the cross-sectional geometry of the bridge and representing the flexural resistance of the structure, dx is the small interval of integration, indicating discrete calculation of the entire bridge to obtain local deformation data. Finally, based on the deformation state of the bridge, conduct a risk assessment to identify potential dangerous areas or parts with serious deformation of the bridge.

[0075] In this embodiment, when the bridge deformation reaches the set threshold, an alarm is automatically triggered to remind the bridge management personnel to conduct inspections and maintenance. The deformation threshold is set based on the maximum allowable displacement, maximum tilt angle, and stress limit. When the deformation value (such as displacement, tilt angle) of the bridge exceeds the set safety threshold, the early warning mechanism is immediately triggered to generate an alarm message, and the relevant bridge management personnel are notified by means of email, text message, mobile application, etc. The setting of the threshold refers to historical monitoring data, standard specifications, engineering experience, etc.

[0076] In the field of bridge deformation monitoring, some existing technical solutions use multiple sensors to monitor different types of deformations (such as the combination of a laser displacement sensor 3 and an inclination sensor 5), but these systems usually lack data optimization and error correction mechanisms. For example:

[0077] Combined monitoring with multiple sensors: The system uses multiple sensors to collect data, but no effective error correction is carried out. Data processing may only rely on the original data, lacking the least squares method or other optimization algorithms to remove the influence of noise and environmental factors, resulting in relatively large errors in the measurement results.

[0078] To conduct a comparative experiment fairly, it is necessary to ensure that the two solutions are tested under the same experimental conditions. The following are the equivalent condition settings for the comparative experiment:

[0079] Select a bridge with various deformation phenomena as the experimental object. The structure of the bridge includes important parts such as multiple support points, cross beams, and bridge piers 1. Select at least one continuous week for monitoring to ensure that the deformations of the bridge under different environmental conditions can be captured. Under the same conditions, both solutions use the same number and type of sensors (such as a laser displacement sensor 3 and an inclination sensor 5) arranged at the key monitoring parts of the bridge.

[0080] The existing solution only analyzes the original sensor data, while this solution uses the least squares method algorithm to optimize and correct the data to eliminate environmental interferences such as temperature, humidity, and vibration. Under the same conditions, the data update frequencies of the two solutions are the same, ensuring that the same amount of data is collected within the same time range.

[0081] By comparing the errors between the actual deformation data of the bridge (such as the deformation data measured by other precision equipment) and the sensor data, the deformation accuracy of each solution is evaluated. The time delay from data collection to update is measured to evaluate the performance of the solution in real-time data update. Through the actual deformation situation of the bridge, the accuracy of automatically triggering an alarm when exceeding the limit for each solution is evaluated.

[0082] As Figure 2 shown, when the bridge deformation reaches the set threshold, the error correction of this solution makes the risk assessment more accurate. By comparing the accuracy of risk warnings, the warning trigger situation after error correction is demonstrated. It can be seen that through error correction, this solution significantly improves the accuracy of warnings, reduces the probability of false triggers, and ensures that bridge management personnel can make responses based on correct monitoring data.

[0083] By adopting the least squares algorithm to correct the errors of sensor data, the effect in bridge deformation monitoring is significantly better than the existing solutions. By correcting the errors, this solution shows higher accuracy in terms of deformation accuracy, real-time monitoring, risk assessment, etc. Specifically, the deformation monitoring accuracy after error elimination is greatly improved; the accuracy of the risk warning system after error correction is increased; the real-time performance and accuracy of the overall system are enhanced.

[0084] The present invention is not limited to the above embodiments. Anyone should know that structural changes made under the inspiration of the present invention, as long as they have the same or similar technical solutions as the present invention, fall within the protection scope of the present invention. The technologies, shapes, and structures not described in detail in the present invention are all well-known technologies.

Claims

1. A bridge deformation monitoring device based on digital twin technology, characterized in that: include: IoT sensor module: The IoT sensor module includes laser displacement sensors and tilt sensors, which are installed at key monitoring points of the bridge to collect real-time deformation data of the bridge; A digital twin modeling and synchronization module, which is used to build and update a virtual digital twin model of the bridge based on sensor data collected in real time, wherein the model reflects the deformation state of the bridge in real time; A data processing and analysis module, which is used to optimize the deformation data collected by the IoT sensor module using a least squares algorithm, correct errors and obtain accurate monitoring results; Danger warning module: The danger warning module is used to automatically trigger an alarm when the bridge deformation reaches a set threshold, reminding bridge management personnel to conduct inspections and maintenance; The data transmission and remote monitoring module is used to upload the data collected by the sensor to the cloud platform in real time, and view the real-time deformation data of the bridge through the remote monitoring equipment.

2. According to claim 1, a bridge deformation monitoring device based on digital twin technology is characterized in that: The steps of constructing and updating a virtual digital twin model of the bridge based on the sensor data collected in real time, wherein the model reflects the deformation state of the bridge in real time, are as follows: Based on the design drawings, structural characteristics and historical monitoring data of the bridge, a preliminary digital twin model is constructed. The digital twin model includes the geometric shape, structural parameters and stress analysis data of the bridge to form an ideal state model of the bridge. The sensor data collected in real time is connected to the digital twin model to update the virtual model of the bridge. Whenever the sensor data changes, the system will adjust the deformation state in the virtual model according to the real-time data, so that the virtual model is synchronized with the actual monitoring situation and accurately reflects the deformation process of the bridge.

3. According to claim 1, a bridge deformation monitoring device based on digital twin technology is characterized in that: The steps of optimizing the deformation data collected by the IoT sensor module using the least squares algorithm, correcting errors and obtaining accurate monitoring results are as follows: Based on the physical model of the bridge structure, a set of error equations is constructed to describe the difference between the sensor data and the theoretical model, taking into account potential sensor errors and environmental interference; The least squares algorithm is used to optimize the error model and obtain the correction coefficient by minimizing the sum of square errors between sensor data and theoretical values; According to the correction coefficient obtained by the least squares method optimization, the data collected by the sensor is corrected to eliminate the system error and obtain more accurate bridge deformation data. Then, by comparing with known reliable data sources, the accuracy of the corrected monitoring results is verified to ensure that the corrected data is valid and has high precision. Then, the corrected data is used as the final accurate monitoring result to update the deformation state of the bridge in the digital twin model.

4. According to claim 1, a bridge deformation monitoring device based on digital twin technology is characterized in that: Since the laser displacement sensor 3 is affected by temperature changes, the steps for adjusting the error of the laser displacement sensor using the least squares algorithm are as follows: Collect bridge displacement data from laser displacement sensors and ensure that the measurement time and sensor readings are recorded for each data point; Assuming that the error between sensor data and environmental factors is a linear relationship, the objective function of error correction is expressed as: Among them, y measured (i) is the original measurement value of the sensor, y actual (i) is the actual bridge deformation value, T(i) is the temperature value during measurement, and α is the coefficient to be optimized, which represents the influence of temperature change on the measurement error; By minimizing the objective function J(α), the optimal correction coefficient is obtained. Minimizing the sum of squared errors is usually done by taking the derivative and setting it to zero. Its expression is: Then by the formula: Calculate the best correction coefficient: solve the objective function and get the optimized correction coefficient α * ; Use the correction factor α obtained * , correct the sensor's measurement data, the corrected sensor data is: y corrected (i) = y measured ((i)-α * ,Finally, the corrected laser displacement sensor data is input into the ,digital twin model of the bridge to update the deformation state in the ,model.

5. The bridge deformation monitoring device based on digital twin technology according to claim 1 is characterized in that: The vibration or wind force changes caused by the passing of a vehicle can cause the sensor to read incorrectly and generate errors. Therefore, the steps for adjusting the error of the tilt sensor using the least squares algorithm are as follows: Collect the tilt angle data of the bridge from the tilt sensor and record the timestamp of each data point before collecting the tilt data; The objective function is set to minimize the sensor error. The objective function expresses the difference between the sensor measurement and the actual value, while considering the effects of vibration and wind speed. The objective function j(θ, α, β) can be expressed as: Among them, y measured (i) is the measured value at the i-th time point, y actual (i) is the actual tilt value at the i-th time point, α and β are the correction coefficients to be optimized, representing the influence of vibration and wind speed on the error; Use the least squares method to minimize the objective function J(θ, α, β) through the optimization algorithm, calculate the partial derivative of the objective function and set it to zero, and solve the optimal correction coefficient α * and β * , these two coefficients represent the impact of vibration and wind speed on the tilt sensor error. Use the optimal correction factor α * and β * , correct the measurement data of the tilt sensor: y corrected ((i)=y measured ((i)-α * ·vibration i -β * ·wind i , where vibration i and wind i are the vibration and wind speed data at the i-th time point respectively.

6. The bridge deformation monitoring device based on digital twin technology according to claim 1 is characterized in that: After obtaining the corrections of the laser displacement sensor and tilt sensor, the corrected sensor data needs to be applied to update the digital twin model of the bridge. The steps are as follows: The corrected sensor data is synchronized to the digital twin model. Then, based on the corrected data, the formula Calculate the deformation state of the bridge and update the deformation curve and stress distribution in the digital twin model, where ΔL(x, t) is the deformation of the bridge at position x and time t, L is the total length of the bridge, indicating the span of the bridge from one end to the other, P(x) is the instantaneous load at position x, which can be obtained from the corrected sensor data and environmental data, α is the temperature coefficient, T(t) is the temperature value at time t, indicating the influence of ambient temperature on the deformation of the bridge, E is the elastic modulus of the material, describing the stiffness of the material and reflecting the elastic properties of the bridge material, I(x) is the moment of inertia at position x, which is related to the cross-sectional geometry of the bridge and indicates the bending resistance of the structure, dx is the small interval of integration, indicating discrete calculation of the entire bridge to obtain local deformation data, and finally, based on the deformation state of the bridge, conduct risk assessment to identify potential dangerous areas of the bridge or areas with severe deformation.

7. The bridge deformation monitoring device based on digital twin technology according to claim 1 is characterized in that: When the deformation of the bridge reaches the set threshold, an alarm is automatically triggered to remind bridge managers to conduct inspections and maintenance. The deformation threshold is set based on the maximum allowable displacement, maximum inclination angle, and stress limit. When the deformation value of the bridge exceeds the set safety threshold, the early warning mechanism is immediately triggered, an alarm message is generated, and relevant bridge managers are notified via email, text message, or mobile application.

Images