A bridge health prediction device and monitoring analysis method based on a Beidou system

Abstract

The application discloses a bridge health prediction device and a monitoring and analyzing method based on a Beidou system, and relates to the field of bridge health monitoring.The method comprises the following steps: S1, monitoring points are arranged at key structure nodes of a bridge, and three-dimensional position information and multi-source data are collected by using a Beidou system and multiple types of sensors; S2, a time-varying displacement field and a continuous deformation tensor are constructed, a structure fatigue factor is constructed by fusing stress and strain, and dynamic correction of the fatigue factor is realized by introducing environmental disturbance; S3, a health state function is constructed based on stress response, displacement gradient and deformation tensor, a damage mapping function is constructed by combining cumulative deformation and historical threshold values, and a damage heat map is generated; and S4, finally, bridge risks are evaluated by fusing fatigue, health and damage indexes, and dynamic early warning is performed.Through modeling by fusing mechanical tensor characteristics and environmental disturbance, a multi-index linkage fatigue and damage evaluation mechanism is constructed, and the precision, robustness and global perception ability of bridge health monitoring are improved.

Description

Technical Field

[0001] This invention relates to the field of bridge health monitoring, specifically to a bridge health prediction device and monitoring and analysis method based on the BeiDou system. Background Technology

[0002] With the continuous expansion of modern transportation infrastructure, bridges, as key components, play a vital role in urban roads, highways, and railway systems. During long-term service, bridge structures are susceptible to multiple factors, including vehicle loads, environmental climate, seismic disturbances, and structural aging, leading to problems such as material fatigue, loose connections, component deformation, and localized damage. In severe cases, this can even cause structural instability or complete collapse. Therefore, conducting research on real-time health monitoring and early warning of bridge structures has become an important research direction in the fields of civil engineering and structural safety.

[0003] Traditional bridge health monitoring methods mainly rely on manual inspections or single-point data collection using fixed equipment such as strain gauges, accelerometers, and fiber optic sensors. These methods typically suffer from limited coverage, low resolution, poor real-time data processing, and an inability to capture the overall structural response. Furthermore, monitoring systems and data platforms are often deployed independently, lacking a unified spatiotemporal reference, making it difficult to achieve efficient fusion and analysis of multi-source data.

[0004] In recent years, with the development of global navigation satellite system technology, especially the widespread application of China's independently developed BeiDou Navigation Satellite System, new technological pathways have been provided for bridge monitoring. The BeiDou system possesses all-weather, high-precision, and long-distance three-dimensional displacement measurement capabilities, and in particular, through differential positioning and three-frequency signal processing technology, it can achieve millimeter-level dynamic monitoring. However, the application of the BeiDou system in the field of bridge structural health is still in its early stages. Systematic solutions are still lacking for issues such as how to efficiently integrate it with traditional sensor networks, how to construct a high-precision integrated space-time-mechanical monitoring model, and how to achieve intelligent early warning and risk assessment driven by multiple factors.

[0005] Furthermore, fatigue damage identification and early warning methods in structural health assessment also face numerous challenges. Current research attempts to incorporate machine learning algorithms or finite element inversion analysis, but these methods are often limited by data dimensionality, physical interpretability, and real-time response capabilities, making it difficult to meet the dynamic adaptation requirements of engineering sites. Therefore, there is an urgent need to develop a novel bridge health monitoring and analysis method that integrates high-precision displacement information, multi-source sensor data, environmental disturbance factors, and evolutionary law analysis to improve the accuracy, response speed, and early warning reliability of structural anomaly identification, thereby ensuring the long-term service safety of bridge structures. Summary of the Invention

[0006] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a bridge health prediction device and monitoring and analysis method based on the Beidou system to solve the above-mentioned technical problems.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a bridge health monitoring and analysis method based on the BeiDou system, comprising:

[0008] S1: Deploy monitoring points at key structural nodes of the bridge, use the BeiDou system to collect real-time three-dimensional location information of the monitoring points, and simultaneously collect data from multiple types of sensors to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset;

[0009] S2: Construct a time-varying three-dimensional displacement field and a continuous deformation tensor of the structure using the three-dimensional coordinate sequence of Beidou positioning, construct a structural fatigue factor that integrates stress, strain, the time-varying three-dimensional displacement field and the continuous deformation tensor, and introduce environmental disturbance parameters to construct an environmental factor. Use the environmental factor to achieve adaptive correction of the structural fatigue factor and obtain the structural fatigue coefficient.

[0010] S3: Based on the stress response, displacement gradient and continuous deformation tensor of each monitoring point, construct the structural health state function; based on the comparison between the cumulative displacement deformation of the monitoring points and the preset historical threshold, construct the structural damage mapping function and output the damage heat map.

[0011] S4: Based on the structural fatigue coefficient, structural health state function, and damage factor, bridge risk assessment is conducted to obtain a comprehensive risk index. Dynamic early warning and level judgment are then performed based on the comprehensive risk index and the set risk threshold.

[0012] The present invention is further configured such that S1 includes:

[0013] Millimeter-level three-dimensional displacement monitoring is performed using BeiDou tri-frequency signals. Atmospheric errors are eliminated by differential positioning between the reference point and the monitoring point, and three-dimensional coordinate data of key structural parts of the bridge are collected.

[0014] Strain gauges, force sensors, temperature sensors, air humidity sensors, ultrasonic anemometers, and fiber optic vibrators are deployed at bridge structural points to form a sensor network, collect multi-source sensor data, and achieve full-area monitoring coverage.

[0015] By utilizing BeiDou's precise single-point timing technology, the timestamp accuracy of multi-source data is ensured to reach the nanosecond level, forming a unified time-based synchronized data set. The data set includes: BeiDou positioning three-dimensional coordinate sequence and multi-source sensor dataset.

[0016] The present invention is further configured such that S2 includes:

[0017] Based on the BeiDou positioning three-dimensional coordinate sequence, a time-varying three-dimensional displacement field of the structure is constructed by differential processing of coordinate data at adjacent time points;

[0018] Displacement gradient field data is extracted based on the three-dimensional coordinate sequence of Beidou positioning. The symmetric linear strain components are combined with the nonlinear displacement coupling effect to eliminate rigid body motion interference and then a continuous deformation tensor is constructed.

[0019] The present invention is further configured to construct an energy dissipation term based on the product between stress response and axial strain, characterize the motion intensity term with the Euclidean norm of the time-varying three-dimensional displacement field, extract the local volume deformation response through the determinant of the deformation tensor, and nonlinearly combine the three terms to form fatigue energy density.

[0020] A weighted fusion strategy based on node weights is applied to the fatigue energy density at each monitoring point of the bridge structure to construct a structural fatigue factor for global fatigue evolution characterization.

[0021] The present invention is further configured to construct environmental factors by introducing normalized environmental disturbance parameters and performing nonlinear weighted combination. The environmental disturbance parameters include: temperature, humidity and wind speed.

[0022] An environmental disturbance adjustment coefficient and a mutation penalty coefficient are introduced. The environmental disturbance adjustment coefficient is used to achieve linear reduction compensation of steady-state environmental disturbances, and the penalty coefficient is used to perform nonlinear amplification compensation of the first derivative of time. Finally, the fatigue coefficient is obtained by dynamically correcting the structural fatigue factor through a two-level compensation mechanism.

[0023] The present invention is further configured such that S3 includes:

[0024] Based on the time-varying stress response, three-dimensional displacement field gradient modulus and the squared trace of the nonlinear continuous deformation tensor at the monitoring point, a weighted fusion is performed to construct the health state function of the monitoring point.

[0025] Based on the importance weight of each monitoring point, the health status function of each monitoring point is hierarchically controlled, and the sensitivity to extreme value changes is enhanced by a nonlinear power function to generate the health status function of the bridge.

[0026] The present invention is further configured to calculate the cumulative deformation of each monitoring point and compare it with the historical deformation threshold to obtain the difference value. The difference between the cumulative deformation of the monitoring point and its historical threshold indicates the degree of damage of the monitoring point. A damage heat map is constructed by integrating the degree of damage of each monitoring point.

[0027] The present invention is further configured such that, in step S4, the final comprehensive risk index is obtained by weighted summation of the assessment indicators of the bridge's health status, fatigue level, and damage status.

[0028] When the overall risk index exceeds the set risk threshold, an early warning will be automatically triggered.

[0029] When the comprehensive risk index is greater than the risk threshold but less than or equal to the first risk threshold, it is judged as a yellow warning;

[0030] When the comprehensive risk index is greater than the first risk threshold and less than or equal to the second risk threshold, it is judged as an orange alert;

[0031] If the comprehensive risk index exceeds the second risk threshold, it is judged as a red alert.

[0032] The present invention is further configured such that the method also includes a visualization interaction and collaborative management method, which uploads bridge monitoring data to a cloud management platform in real time via a wireless network. After the platform processes and analyzes the data, it obtains the bridge's status information, which includes: Beidou positioning three-dimensional coordinate sequence, multi-source sensor dataset, structural fatigue coefficient, bridge health status, damage heat map, and risk indicators.

[0033] Bridge status information is integrated to construct a bridge status information set, which is then transmitted to the visualization interaction module to generate a visualization interface for managers to view in real time.

[0034] The present invention also provides a bridge health prediction device based on the BeiDou system, the device comprising:

[0035] Data acquisition and processing module: Monitoring points are deployed at key structural nodes of the bridge. The BeiDou system is used to collect real-time three-dimensional location information of the monitoring points and simultaneously collect data from multiple types of sensors to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset.

[0036] Feature extraction and establishment module: Construct a time-varying three-dimensional displacement field and a continuous deformation tensor of the structure using the three-dimensional coordinate sequence of Beidou positioning, construct a structural fatigue factor that integrates stress, strain, the time-varying three-dimensional displacement field and the continuous deformation tensor, and introduce environmental disturbance parameters to construct an environmental factor. Use the environmental factor to achieve adaptive correction of the structural fatigue factor and obtain the structural fatigue coefficient.

[0037] Structural health assessment and damage mapping module: Based on the stress response, displacement gradient and continuous deformation tensor of each monitoring point, a structural health state function is constructed. Based on the comparison of the cumulative displacement deformation of the monitoring points with the preset historical threshold, a structural damage mapping function is constructed, and a damage heat map is output.

[0038] Risk estimation and level determination module: Based on structural fatigue coefficient, structural health state function and damage factor, bridge risk assessment is carried out to obtain comprehensive risk index. Dynamic early warning and level determination are carried out based on comprehensive risk index and set risk threshold.

[0039] This invention provides a bridge health prediction device and monitoring and analysis method based on the BeiDou system. The method comprises: S1: Deploying monitoring points at key structural nodes of the bridge, collecting real-time three-dimensional position information of the monitoring points using the BeiDou system, and simultaneously collecting data from multiple types of sensors to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset; S2: Constructing a time-varying three-dimensional displacement field and a continuous deformation tensor of the structure using the BeiDou positioning three-dimensional coordinate sequence, constructing a structural fatigue factor that integrates stress, strain, the time-varying three-dimensional displacement field, and the continuous deformation tensor, and introducing environmental disturbance parameters to construct an environmental factor, using the environmental factor to achieve adaptive correction of the structural fatigue factor, and obtaining the structural fatigue coefficient; S3: Constructing a structural health state function based on the stress response, displacement gradient, and continuous deformation tensor of each monitoring point, comparing the cumulative displacement deformation of the monitoring points with a preset historical threshold, constructing a structural damage mapping function, and outputting a damage heatmap;

[0040] S4: Bridge risk assessment is conducted based on structural fatigue coefficient, structural health state function, and damage factor to obtain a comprehensive risk index. Dynamic early warning and risk level determination are then performed based on the comprehensive risk index and a set risk threshold. The beneficial effects include:

[0041] Integrating continuous deformation tensor and stress response to characterize structural fatigue evolution: A structural fatigue factor integrating physical indices such as displacement field gradient, stress-strain product, and tensor determinant was constructed. It can characterize the fatigue evolution process from both mechanical energy dissipation and deformation intensity, and has good physical interpretability and evolution sensitivity.

[0042] Environmental disturbance modeling enables dynamic correction of fatigue factors: By introducing environmental disturbance parameters such as temperature, humidity, and wind speed as independent factors, and using disturbance adjustment coefficients and mutation penalty mechanisms, nonlinear dynamic correction of fatigue factors is performed, effectively eliminating the interference of external environment on structural health assessment and improving the robustness and adaptability of prediction models.

[0043] Construct a multi-indicator joint bridge health status and damage mapping function: integrate stress response, displacement gradient modulus and deformation tensor characteristics into a unified structural health function, and extract damage information through cumulative displacement difference to output structural damage heat map, which has stronger local sensitivity and overall structural perception capabilities.

[0044] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0046] Figure 1 A flowchart illustrating a bridge health monitoring and analysis method based on the BeiDou system is shown as an exemplary embodiment of the present invention.

[0047] Figure 2 This is a schematic diagram of a bridge health prediction device based on the BeiDou system, which is an exemplary embodiment of the present invention. Detailed Implementation

[0048] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0049] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0050] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0051] Example 1

[0052] A bridge health monitoring and analysis method based on the BeiDou system, such as Figure 1 As shown, it includes:

[0053] S1: Deploy monitoring points at key structural nodes of the bridge, use the BeiDou system to collect real-time three-dimensional location information of the monitoring points, and simultaneously collect data from multiple types of sensors to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset;

[0054] S2: Construct a time-varying three-dimensional displacement field and a continuous deformation tensor of the structure using the three-dimensional coordinate sequence of Beidou positioning, construct a structural fatigue factor that integrates stress, strain, the time-varying three-dimensional displacement field and the continuous deformation tensor, and introduce environmental disturbance parameters to construct an environmental factor. Use the environmental factor to achieve adaptive correction of the structural fatigue factor and obtain the structural fatigue coefficient.

[0055] S3: Based on the stress response, displacement gradient and continuous deformation tensor of each monitoring point, construct the structural health state function; based on the comparison between the cumulative displacement deformation of the monitoring points and the preset historical threshold, construct the structural damage mapping function and output the damage heat map.

[0056] S4: Based on the structural fatigue coefficient, structural health state function, and damage factor, bridge risk assessment is conducted to obtain a comprehensive risk index. Dynamic early warning and level judgment are then performed based on the comprehensive risk index and the set risk threshold.

[0057] The present invention is further configured such that S1 includes:

[0058] Millimeter-level three-dimensional displacement monitoring is performed using BeiDou tri-frequency signals. Atmospheric errors are eliminated by differential positioning between the reference point and the monitoring point, and three-dimensional coordinate data of key structural parts of the bridge are collected.

[0059] Strain gauges, force sensors, temperature sensors, air humidity sensors, ultrasonic anemometers, and fiber optic vibrators are deployed at bridge structural points to form a sensor network, collect multi-source sensor data, and achieve full-area monitoring coverage.

[0060] Utilizing BeiDou's precise single-point time synchronization technology, the timestamp accuracy of multi-source data is ensured to reach the nanosecond level, forming a synchronized data set with a unified time base. This data set includes: BeiDou positioning 3D coordinate sequences and multi-source sensor datasets. Specifically, real-time acquisition of 3D coordinate sequences through the BeiDou system is existing technology and will not be elaborated upon here. Monitoring points are deployed at various points along the bridge structure, including at least piers, towers, main beams, hangers, cables, and tower-beam connection points. The more monitoring points deployed, the higher the prediction accuracy. Time synchronization is also existing technology and will not be elaborated upon here. BeiDou positioning 3D coordinate sequence P i (t)=[x i (t),y i (t),z i [(t)], where P i (t) represents the three-dimensional coordinate sequence of BeiDou positioning, x i (t), y i (t), z i (t) represents the east-west, north-south, and vertical coordinates of the critical structural part i at time stamp t. Multi-source sensor dataset S i (t)={εi (t),σ i (t),T i (t),H i (t),v i (t),a i (t)}, where ε i (t) represents the axial strain, used to reflect the local deformation response of the structure under external forces, and is acquired by a strain gauge; σ i (t) represents the stress response, used to reflect the stress state of the bridge, and is collected by a force-sensitive sensor; T i (t) represents temperature, used to capture the effect of thermal expansion and contraction on the thermal stress of the bridge, and is collected by a temperature sensor; H i (t) represents humidity, which, along with temperature, influences the rate of steel corrosion and crack propagation; it is collected by an air humidity sensor. i (t) represents wind speed, used to provide the background of dynamic environmental load, and is collected by an ultrasonic anemometer; a i (t) represents the vibration acceleration, used for early identification of risks such as component loosening, connection fatigue, and structural resonance, and is collected by a fiber optic vibration machine.

[0061] The present invention is further configured such that S2 includes:

[0062] Based on the BeiDou positioning three-dimensional coordinate sequence, a time-varying three-dimensional displacement field of the structure is constructed by differential processing of coordinate data at adjacent time points;

[0063] Displacement gradient field data is extracted based on the three-dimensional coordinate sequence of BeiDou positioning. The symmetric linear strain components are combined with the nonlinear displacement coupling effect to eliminate rigid body motion interference and comprehensively construct a continuous deformation tensor. Specifically, the time-varying three-dimensional displacement field reflects the absolute displacement changes of key structural components over a period of time, calculated through the position difference over the time series. The specific calculation formula is: Δu i (t)=P i (t)-P i (t-δt), where Δu i (t) represents the time-varying three-dimensional displacement field of the structure, which will be referred to as the displacement field for simplicity; P i (t) represents the three-dimensional coordinates of the i-th monitoring point at time t; δt is the time step, i.e., the time interval between two data acquisitions. The specific time step is set by experts based on multiple factors, including the bridge's health status, its commissioning time, and recommended maintenance intervals. Continuous deformation tensor E i(t) consists of linear and nonlinear terms of the displacement gradient. The linear part corresponds to the normal strain and shear strain under the small deformation assumption, while the nonlinear term characterizes the geometric nonlinear effect caused by large deformation. Its determinant reflects the local volume change rate and is used to evaluate the material compression or expansion characteristics. The construction of the continuous deformation tensor is an existing technology and will not be elaborated here.

[0064] The present invention is further configured to construct an energy dissipation term based on the product between stress response and axial strain, characterize the motion intensity term with the Euclidean norm of the time-varying three-dimensional displacement field, extract the local volume deformation response through the determinant of the deformation tensor, and nonlinearly combine the three terms to form fatigue energy density.

[0065] A weighted fusion strategy based on node weights is applied to the fatigue energy density at each monitoring point of the bridge structure to construct a structural fatigue factor for global fatigue evolution characterization. Specifically, the fatigue factor reflects the comprehensive fatigue response intensity of the bridge structure under working conditions at time t. It is calculated by accumulating the fatigue energy density at each monitoring point in the bridge, thus constructing the structural fatigue factor. This more realistically reflects the "cumulative effect of structural fatigue" of the bridge structure under long-term loads and environmental influences. The fatigue energy density calculation logic is: F... i (t)=(σ i (t)·ε i (t)) α ·||Δu i (t)|| β ·[det(E i (t))] γ , of which F i (t) represents the fatigue energy density; σ i (t) represents the stress response; ε i (t) represents the axial strain; Δu i (t) represents the displacement field; E i (t) is the continuous deformation tensor; (σ) i (t)·ε i (t) is the energy dissipation term, which is the stress-strain product and represents the energy stored per unit volume of the material under stress; ||Δu i (t)|| represents the motion intensity term, which is the magnitude of the three-dimensional coordinate increment of the i-th point at the current moment compared to the previous sampling period. It reflects the instantaneous deformation intensity of the local structure. If the changes are frequent but the stress is not strong, it indicates that there may be a fatigue risk; det(E i (t) represents the local volumetric deformation response, which is the continuous deformation tensor E. iThe determinant of (t) represents the degree of nonlinear transformation of the volume of the micro-element in the monitoring point area. An increase in volume indicates tension, while a decrease in volume indicates compression. A significant deviation from 1 indicates large deformation, local buckling, or shear distortion. α, β, and γ are weighting parameters. α is the stress-strain energy weight, used to reflect the material's sensitivity to "internal accumulation," with a suggested value between 1 and 3. For high-strength steel, a value >1.5 is recommended. The specific value is determined by experts based on statistical analysis of monitoring data. β is the displacement change weight, used to control the penalty degree of the actual deformation amplitude, with a suggested value between 0.5 and 2. If bridge vibration is frequent, a value >1.0 is recommended, with the specific value determined by experts based on statistical analysis of monitoring data. γ is the nonlinear tensor weight, with a suggested value between 0.5 and 1.5. Higher values ​​are recommended for areas with high risk of nonlinear buckling or crushing, such as cable towers and bridge deck ends, with the specific value determined by experts based on statistical analysis of monitoring data. Structural fatigue factor calculation logic: Among them, F fatigue (t) represents the structural fatigue factor; N represents the total number of monitoring points in the bridge participating in the evaluation; P ref The coordinates of the reference point are denoted as τ; τ is the spatial attenuation coefficient, used to reflect the spatial propagation range of fatigue damage. The spatial attenuation coefficient ranges from 5 to 200. A larger spatial attenuation coefficient is more suitable for long-span bridges, while a smaller spatial attenuation coefficient is more suitable for monitoring local damage in bridges. The structural fatigue factor integrates three physical sources: structural mechanics, kinematics, and geometric nonlinearity. By adjusting the parameters, it adapts to different bridge types to complete fatigue monitoring.

[0066] The present invention is further configured to construct environmental factors by introducing normalized environmental disturbance parameters and performing nonlinear weighted combination. The environmental disturbance parameters include: temperature, humidity and wind speed.

[0067] An environmental disturbance adjustment coefficient and a mutation penalty coefficient are introduced. The environmental disturbance adjustment coefficient achieves linear reduction compensation for steady-state environmental disturbances, while the penalty coefficient performs nonlinear amplification compensation on the first derivative over time. Finally, the fatigue factor is obtained by dynamically correcting the structural fatigue factor through a two-stage compensation mechanism. Specifically, the fatigue factor of a bridge is a physical phenomenon controlled by stress-strain-deformation. However, in actual daily use, the decay rate and critical threshold are significantly adjusted by the environment. Therefore, when designing the structural fatigue factor, an environmental factor is used to modify the original structural fatigue factor, making the fatigue factor environmentally sensitive and more closely reflecting the actual operating conditions of the bridge. Environmental factor calculation logic: Where ψ(t) represents the environmental factor; m represents the number of environmental disturbance parameters, which are specifically collected through a sensor network and include temperature, humidity, and wind speed; f j (t) represents the measured value of the j-th environmental disturbance parameter at the current time; ηj θ represents the coupling weight of the environmental disturbance parameter, indicating the degree of influence of this environmental disturbance parameter on the fatigue factor. Its value ranges from 0.01 to 1.0 and can be obtained by fitting historical data through correlation coefficient analysis or Bayesian regression. A larger value indicates a greater influence on the fatigue factor. j This represents the nonlinear sensitivity, indicating the degree of nonlinear influence of fatigue on environmental factors. A value between 1 and 3 is recommended, with the specific value obtained through fitting based on the application scenario. The basic fatigue factor is corrected using environmental factors; the calculation logic for fatigue factor correction is as follows: in, κ is the corrected fatigue factor, which will be referred to as the fatigue coefficient for ease of distinction; κ is the environmental disturbance adjustment coefficient, used to control the weight of the overall environmental disturbance on the fatigue factor, with a value ranging from 0.1 to 10. The larger the value, the more sensitive the structure is to environmental influences in the current operating stage; ξ is the mutation penalty coefficient, used to enhance the model's sensitivity to transient changes in environmental parameters and avoid sudden disturbances being masked by the steady-state correction term, with a value ranging from 0.1 to 1. The specific parameters should be adaptively modified according to the application scenario. The differential term is the first derivative of the environmental disturbance factor ψ(t) with respect to time, which characterizes the instantaneous rate of change of the environmental disturbance. The instantaneous rate of change of the environmental disturbance is calculated using the central difference method. As a denominator correction term, it suppresses the steady-state environmental impact of the bridge's fatigue factor through environmental disturbance factors, and is a first-order compensation. The differential penalty term captures instantaneous changes in environmental parameters, enhances the sensitivity of the fatigue coefficient to sudden events, and is a secondary compensation. By combining the two levels of compensation, the influence of environmental factors on bridge fatigue is corrected.

[0068] The present invention is further configured such that S3 includes:

[0069] Based on the time-varying stress response, three-dimensional displacement field gradient modulus and the squared trace of the nonlinear continuous deformation tensor at the monitoring point, a weighted fusion is performed to construct the health state function of the monitoring point.

[0070] Based on the importance weights of each monitoring point, the sub-items in the health state function of the monitoring points are hierarchically controlled. A nonlinear power function is used to enhance the sensitivity to extreme value changes, generating the bridge's health state function. Specifically, the bridge health state function reflects the health state level of different monitoring nodes of the bridge structure at time t by nonlinearly weighting and combining three types of physical indicators: stress intensity, displacement gradient intensity, and nonlinear deformation intensity. A global health evaluation index H(t) is constructed by accumulating and weighting these indicators. The health function calculation logic is as follows: Where H(t) represents the health status; N represents the total number of monitoring points in the bridge participating in the assessment; σ represents the importance weight of node i in the structure, with a value ranging from 0.1 to 2; i (t)| p is the stress intensity term, used to reflect the load level of the material at monitoring point i; p is the exponential term, with a value between 1 and 3, used to control the amplification of the response at high stress points; the absolute value |·| is used to ensure a unified evaluation of tension and compression for both positive and negative stresses. This is the displacement gradient norm term, representing the degree of non-uniformity in structural deformation. tr(E) represents the displacement gradient, specifically the partial derivative matrix of the displacement field in spatial coordinates, reflecting the deformation gradient within the neighborhood of monitoring point i. It is calculated using finite difference or shape function interpolation. q is an exponential term used to reflect the sensitivity to local deformation, with a value ranging from 1 to 2. i (t) 2 ) r For nonlinear deformation energy terms, tr(E) i (t) 2 λ is the second-order trace of the continuous strain tensor, used to represent the local energy during large deformation. r is the exponential term, used to represent the deformation excitation factor; a higher value highlights the large deformation region, and its value ranges from 0.5 to 2. λ1, λ2, and λ3 are weighting factors used to adjust the relative influence of different physical factors. λ1 emphasizes stress response, λ2 emphasizes deformation gradient, and λ3 emphasizes nonlinearity. The values ​​of the three weighting factors are all between 0 and 1, but they must add up to 1. Finally, the overall health status of the bridge is obtained by summing the health status of all monitoring points.

[0071] The invention further involves calculating the cumulative deformation at each monitoring point and comparing it with historical deformation thresholds to obtain a difference value. The difference between the cumulative deformation at a monitoring point and its historical threshold indicates the degree of damage at that monitoring point. A damage heatmap is constructed by integrating the damage levels of each monitoring point. Specifically, the goal of probabilistic damage mapping is to track and quantitatively describe the damage evolution of bridges during long-term use, providing data support for developing reasonable maintenance strategies and optimizing designs. The specific construction method involves real-time tracking and analysis of the bridge's structural deformation, comparing it with historical thresholds to quantify changes in structural damage, and finally drawing a damage heatmap of the structure. The damage factor calculation formula is as follows: Among them, D damage (t) is the damage factor; ΔL i (t) represents the cumulative displacement of the structure, indicating the cumulative displacement of the current monitoring point from the initial state to the current state. It is calculated using Euclidean distance and reflects the overall degree of drift; L threshold,iThe historical threshold represents the maximum allowable deformation range of the monitoring point under set operating conditions or historical data. The specific value is set based on the allowable displacement value in the design drawings and the measured limits. If the cumulative displacement of the structure exceeds the historical threshold, it indicates the presence of permanent deformation or structural relaxation, requiring close monitoring and vigilance. i For structural importance weights, and structural importance weights Similarly, both represent the importance of monitoring points within the structure. However, the structural importance weighting has a higher safety importance for critical parts of bridge structures, such as cantilever ends or beam end supports, and its value ranges from 0.1 to 5. ρ is the anomaly amplification power exponent, used for nonlinear methods to control displacement deviation. It is usually set between 1 and 3; the larger the value, the more sensitive it is to abnormally increasing deformation, and the easier it is to trigger an alarm. The specific value is adaptively modified according to the actual application scenario. By summarizing the damage factor values ​​of all structural monitoring points at time t and combining them with their coordinate positions in the structural geometric space, spatial interpolation algorithms, such as Gaussian kernel density estimation, inverse distance weighting, or bilinear interpolation, are used to make the damage intensity distribution of discrete points continuous. Then, a color mapping method, such as pseudo-color mapping, is used to generate a two-dimensional image, thus obtaining a damage heatmap of the structure, which intuitively reflects the damage intensity distribution of different regions of the structure. Heatmap generation is an existing technology and will not be elaborated on here.

[0072] The present invention is further configured such that, in step S4, the final comprehensive risk index is obtained by weighted summation of the assessment indicators of the bridge's health status, fatigue level, and damage status.

[0073] When the overall risk index exceeds the set risk threshold, an early warning will be automatically triggered.

[0074] When the comprehensive risk index is greater than the risk threshold but less than or equal to the first risk threshold, it is judged as a yellow warning;

[0075] When the comprehensive risk index is greater than the first risk threshold and less than or equal to the second risk threshold, it is judged as an orange alert;

[0076] If the comprehensive risk index exceeds the second risk threshold, a red alert is issued. Specifically, the comprehensive risk index combines the bridge's health status, fatigue level, and damage condition to generate a unified risk assessment index. This index quantifies the overall risk level of the bridge structure and enables dynamic monitoring and early warning decisions. The comprehensive risk index is a weighted combination of three components: health status, structural fatigue factor, and damage coefficient. Weighting coefficients adjust the proportions of different components to ultimately construct a comprehensive risk index R(t) that reflects the overall condition of the bridge. If the system detects that the comprehensive risk index R(t) exceeds the preset risk threshold R... criticalThe system will trigger an automatic warning and simultaneously record the trigger timestamp and all bridge status information at the current time. Based on the bridge status information, a multi-channel long short-term memory network is used to extract the long-term evolution and short-term disturbance characteristics of the bridge status, and to dynamically predict the future structural fatigue, displacement, and health status of the bridge. To prevent minor anomalies from causing serious alarms, a multi-level risk system is set, with three levels for judging the risk level after triggering the automatic warning: yellow, orange, and red. Yellow represents a low-risk level, where the comprehensive risk index R(t) is greater than the risk threshold R. critical And less than or equal to the first risk threshold A yellow risk level indicates a risk that needs to be recorded and regular inspections and maintenance arranged by maintenance personnel. An orange level indicates a higher risk level, where the comprehensive risk index R(t) exceeds the first risk threshold. Less than or equal to the second risk threshold An orange alert is issued, requiring experts and maintenance personnel to be dispatched to the site for in-depth inspection and handling, and the frequency of testing to be increased; a red alert indicates extremely high risk, when the comprehensive risk index R(t) exceeds the second risk threshold. If the bridge is deemed to be under a red alert, it must be immediately shut down and the road section closed. Vehicles and unauthorized personnel must be prohibited from entering the bridge area. At the same time, a structural assessment and emergency repairs must be carried out.

[0077] The present invention is further configured such that the method also includes a visualization interaction and collaborative management method, which uploads bridge monitoring data to a cloud management platform in real time via a wireless network. After the platform processes and analyzes the data, it obtains the bridge's status information, which includes: Beidou positioning three-dimensional coordinate sequence, multi-source sensor dataset, structural fatigue coefficient, bridge health status, damage heat map, and comprehensive risk index.

[0078] Bridge status information is integrated to construct a bridge status information set, which is then transmitted to the visualization and interaction module to generate a visual interface for real-time viewing by management personnel. Specifically, for the data transmission part: 4G / 5G cellular networks, LoRa / NB-IoT low-power wide area networks, or satellite communication are used as the main transmission channels for the collected or processed data, supporting breakpoint resumption and multi-link redundancy switching to ensure continuous data upload in extreme environments. Data is then encrypted using TLS / SSL protocols, combined with device authentication and access control to prevent data tampering or unauthorized intrusion. The data processing and analysis part has been explained previously and will not be elaborated upon here. For the visualization and interaction part: the processed bridge status information set is added to the bridge status display database. Different display interfaces utilize the corresponding bridge status information set in the database to achieve visualization and interaction of the bridge status.

[0079] Example 2

[0080] Please see Figure 2 This exemplary bridge health prediction device based on the BeiDou system includes:

[0081] Data acquisition and processing module: Monitoring points are deployed at key structural nodes of the bridge. The BeiDou system is used to collect real-time three-dimensional location information of the monitoring points and simultaneously collect data from multiple types of sensors to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset.

[0082] Feature extraction and establishment module: Construct a time-varying three-dimensional displacement field and a continuous deformation tensor of the structure using the three-dimensional coordinate sequence of Beidou positioning, construct a structural fatigue factor that integrates stress, strain, the time-varying three-dimensional displacement field and the continuous deformation tensor, and introduce environmental disturbance parameters to construct an environmental factor. Use the environmental factor to achieve adaptive correction of the structural fatigue factor and obtain the structural fatigue coefficient.

[0083] Structural health assessment and damage mapping module: Based on the stress response, displacement gradient and continuous deformation tensor of each monitoring point, a structural health state function is constructed. Based on the comparison of the cumulative displacement deformation of the monitoring points with the preset historical threshold, a structural damage mapping function is constructed, and a damage heat map is output.

[0084] Risk estimation and level determination module: Based on structural fatigue coefficient, structural health state function and damage factor, bridge risk assessment is carried out to obtain comprehensive risk index. Dynamic early warning and level determination are carried out based on comprehensive risk index and set risk threshold.

[0085] It should be noted that the bridge health prediction device based on the BeiDou system provided in the above embodiments and the bridge health monitoring and analysis method based on the BeiDou system provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the bridge health prediction device based on the BeiDou system provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0086] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0087] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0088] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0089] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0090] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0091] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0095] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0096] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A bridge health monitoring and analysis method based on the BeiDou system, characterized in that, include: S1: Monitoring points are deployed at key structural nodes of the bridge. The BeiDou system is used to collect real-time three-dimensional location information of the monitoring points, and data from multiple types of sensors are collected simultaneously to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset. This includes: using BeiDou tri-frequency signals for millimeter-level three-dimensional displacement monitoring; using differential positioning between the reference point and the monitoring point to eliminate atmospheric errors; and collecting three-dimensional coordinate data of key structural parts of the bridge. Strain gauges, force sensors, temperature sensors, air humidity sensors, ultrasonic anemometers, and fiber optic vibration meters are deployed at the bridge structural points to form a sensor network, collect multi-source sensor data, and achieve full-area monitoring coverage. BeiDou precise single-point time synchronization technology is used to ensure that the timestamp accuracy of multi-source data reaches the nanosecond level, forming a synchronized data set with a unified time base. The data set includes: the BeiDou positioning three-dimensional coordinate sequence and the multi-source sensor dataset. S2: A time-varying three-dimensional displacement field and a continuous deformation tensor of the structure are constructed using the BeiDou positioning three-dimensional coordinate sequence. A structural fatigue factor is constructed by integrating stress, strain, the time-varying three-dimensional displacement field, and the continuous deformation tensor. An environmental factor is constructed by introducing environmental disturbance parameters. The environmental factor is used to achieve adaptive correction of the structural fatigue factor and obtain the structural fatigue coefficient. This includes: constructing a time-varying three-dimensional displacement field of the structure by performing differential processing on the coordinate data of adjacent time points based on the BeiDou positioning three-dimensional coordinate sequence; extracting displacement gradient field data based on the BeiDou positioning three-dimensional coordinate sequence, combining the symmetric linear strain components with the nonlinear displacement coupling effect, and comprehensively constructing a continuous deformation tensor after eliminating rigid body motion interference. S3: Based on the stress response, displacement gradient, and continuous deformation tensor of each monitoring point, a structural health state function is constructed. Based on the comparison of the cumulative displacement deformation of the monitoring points with a preset historical threshold, a structural damage mapping function is constructed, and a damage heatmap is output. This includes: constructing a monitoring point health state function by weighted fusion of the time-varying stress response, three-dimensional displacement field gradient modulus, and square trace of the nonlinear continuous deformation tensor at the monitoring point; and performing hierarchical regulation of each sub-item in the monitoring point health state function based on the importance weight of each monitoring point, and enhancing the sensitivity to extreme value changes through a nonlinear power function to generate the bridge's health state function. S4: Based on the structural fatigue coefficient, structural health state function, and damage factor, bridge risk assessment is conducted to obtain a comprehensive risk index. Dynamic early warning and level judgment are then performed based on the comprehensive risk index and the set risk threshold.

2. The bridge health monitoring and analysis method based on the BeiDou system according to claim 1, characterized in that, S2 includes: The energy dissipation term is constructed based on the product between stress response and axial strain. The motion intensity term is characterized by the Euclidean norm of the time-varying three-dimensional displacement field. The local volumetric deformation response is extracted by the determinant of the deformation tensor. The three terms are nonlinearly combined to form the fatigue energy density. A weighted fusion strategy based on node weights is applied to the fatigue energy density of each monitoring point on the bridge structure to construct a structural fatigue factor for global fatigue evolution characterization.

3. The bridge health monitoring and analysis method based on the BeiDou system according to claim 2, characterized in that, S2 further includes: Environmental factors are constructed by nonlinear weighted combination of normalized environmental disturbance parameters, including temperature, humidity, and wind speed. An environmental disturbance adjustment coefficient and a mutation penalty coefficient are introduced. The environmental disturbance adjustment coefficient is used to achieve linear reduction compensation of steady-state environmental disturbances, and the penalty coefficient is used to perform nonlinear amplification compensation of the first derivative of time. Finally, the fatigue coefficient is obtained by dynamically correcting the structural fatigue factor through a two-level compensation mechanism.

4. The bridge health monitoring and analysis method based on the BeiDou system according to claim 1, characterized in that, S3 includes: The cumulative deformation of each monitoring point is calculated and compared with the historical deformation threshold to obtain the difference value. The difference between the cumulative deformation of the monitoring point and its historical threshold indicates the degree of damage of the monitoring point. A damage heat map is constructed by integrating the damage degree of each monitoring point.

5. The bridge health monitoring and analysis method based on the BeiDou system according to claim 1, characterized in that, S4 includes: The final comprehensive risk index is obtained by weighting and summing the assessment indicators of the bridge's health status, fatigue level, and damage condition. When the overall risk index exceeds the set risk threshold, an early warning will be automatically triggered. When the comprehensive risk index is greater than the risk threshold but less than or equal to the first risk threshold, it is judged as a yellow warning; When the comprehensive risk index is greater than the first risk threshold and less than or equal to the second risk threshold, it is judged as an orange alert; If the comprehensive risk index exceeds the second risk threshold, it is judged as a red alert.

6. The bridge health monitoring and analysis method based on the BeiDou system according to claim 1, characterized in that, This method also includes a visualization, interaction and collaborative management method, which uploads bridge monitoring data to the cloud management platform in real time via wireless network. After processing and analyzing the data, the platform obtains the bridge's status information, which includes: Beidou positioning three-dimensional coordinate sequence, multi-source sensor dataset, structural fatigue coefficient, bridge health status, damage heat map, and risk indicators. Bridge status information is integrated to construct a bridge status information set, which is then transmitted to the visualization interaction module to generate a visualization interface for managers to view in real time.

7. A bridge health prediction device based on the BeiDou system, used to implement the bridge health monitoring and analysis method based on the BeiDou system as described in any one of claims 1-6, characterized in that, include: Data acquisition and processing module: Monitoring points are deployed at key structural nodes of the bridge. The BeiDou system is used to collect real-time three-dimensional location information of the monitoring points and simultaneously collect data from multiple types of sensors to construct a BeiDou positioning three-dimensional coordinate sequence and a multi-source sensor dataset. Feature extraction and establishment module: Construct a time-varying three-dimensional displacement field and a continuous deformation tensor of the structure using the three-dimensional coordinate sequence of Beidou positioning, construct a structural fatigue factor that integrates stress, strain, the time-varying three-dimensional displacement field and the continuous deformation tensor, and introduce environmental disturbance parameters to construct an environmental factor. Use the environmental factor to achieve adaptive correction of the structural fatigue factor and obtain the structural fatigue coefficient. Structural health assessment and damage mapping module: Based on the stress response, displacement gradient and continuous deformation tensor of each monitoring point, a structural health state function is constructed. Based on the comparison of the cumulative displacement deformation of the monitoring points with the preset historical threshold, a structural damage mapping function is constructed, and a damage heat map is output. Risk estimation and level determination module: Based on structural fatigue coefficient, structural health state function and damage factor, bridge risk assessment is carried out to obtain comprehensive risk index. Dynamic early warning and level determination are carried out based on comprehensive risk index and set risk threshold.

Images