Road and bridge support hidden danger monitoring and early warning method and system

Abstract

The invention discloses a road and bridge support hidden danger monitoring and early warning method and system, and belongs to the technical field of road and bridge support hidden danger intelligent monitoring. Constructing a theoretical transfer relation model based on the synchronous vehicle load parameters and the synchronous support mechanical response parameters; generating a modified theoretical model based on the synchronous environment temperature parameters and the theoretical transfer relation model; obtaining a response residual error based on the corrected theoretical model, the synchronous vehicle load parameter and the synchronous support mechanical response parameter; acquiring a hidden danger characteristic mode based on the response residual error and the synchronous structure attitude parameter; acquiring a risk probability value based on the hidden danger feature mode; and obtaining graded early warning information based on the risk probability value and the hidden danger characteristic mode. According to the road and bridge support hidden danger monitoring and early warning method and system disclosed by the invention, the problems of false alarm and missing alarm in the prior art can be solved, and the accuracy and reliability of road and bridge support hidden danger monitoring are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology for potential hazards in road and bridge bearings, and in particular to a method and system for monitoring and early warning of potential hazards in road and bridge bearings. Background Technology

[0002] As core force-transfer components in bridge structures, bridge bearings bear the crucial task of safely transferring the enormous loads borne by the superstructure to the substructure piers. They must also be able to adapt to beam displacement and rotation deformation caused by external factors such as temperature changes and vehicle loads. The health of the bearings has a decisive impact on the overall safety and durability of the bridge. Faults such as jamming, dislodgement, or aging damage can lead to unexpected additional stresses within the bridge structure, seriously threatening traffic safety. Therefore, efficient and accurate monitoring of bridge bearings is essential. Currently, monitoring methods for bridge bearings mainly include regular on-site manual inspections and partially automated monitoring. Automated monitoring typically involves installing displacement or stress sensors at key locations on the bearings, acquiring monitoring data in real-time or at set intervals through a data acquisition system. When the monitored data exceeds a pre-set fixed threshold, the system triggers an alarm to alert management personnel. Some solutions also deploy multiple sensors simultaneously to obtain more comprehensive data.

[0003] However, existing technologies have significant technical shortcomings in practical applications. First, alarm methods based on fixed thresholds are too mechanical and cannot effectively distinguish between a large, instantaneous response caused by the normal passage of heavy vehicles and a persistent anomaly caused by structural performance degradation, thus easily generating a large number of invalid alarms. Second, changes in ambient temperature cause thermal expansion and contraction of supports and beams, and the resulting displacement and stress effects are mixed with signals from actual hazards. Existing technologies struggle to effectively isolate this environmental interference, leading to low reliability of monitoring results. Finally, most of these monitoring methods remain at the level of post-event alarms, lacking the ability to analyze and predict the development trend of hazards, and thus failing to provide forward-looking guidance for preventative maintenance. Therefore, there is an urgent need for a method capable of monitoring and providing early warning of hazards in road and bridge supports to solve the technical problems of false alarms and missed alarms in traditional monitoring technologies. Summary of the Invention

[0004] This invention provides a method and system for monitoring and early warning of potential hazards in road and bridge bearings, which can solve the problems of false alarms and missed alarms in the existing technology, and greatly improve the accuracy and reliability of monitoring potential hazards in road and bridge bearings.

[0005] This invention provides a method for monitoring and early warning of potential hazards in road and bridge bearings, comprising:

[0006] Acquire multi-dimensional vehicle passage data, and perform time synchronization processing based on the multi-dimensional vehicle passage data to obtain synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters.

[0007] A theoretical transfer relationship model is constructed based on the synchronous vehicle load parameters and synchronous support mechanical response parameters.

[0008] Based on the synchronous ambient temperature parameters and the theoretical transfer relationship model, dynamic correction is performed to generate a corrected theoretical model;

[0009] The response residuals are obtained based on the modified theoretical model, synchronous vehicle load parameters, and synchronous support mechanical response parameters.

[0010] Based on the response residual and the attitude parameters of the synchronization structure, a coupled discrimination is performed to obtain the hidden danger feature pattern;

[0011] Time series analysis is performed based on the aforementioned hazard characteristic patterns to obtain risk probability values;

[0012] Based on the risk probability value and hidden danger characteristic pattern, graded early warning information is obtained to realize the monitoring and early warning of hidden dangers in road and bridge bearings.

[0013] This invention provides a method for monitoring and early warning of potential hazards in road and bridge bearings. First, the collected multi-dimensional vehicle traffic information is processed in time synchronization to form a synchronized dataset containing synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters. Next, a theoretical transfer relationship model is established based on the synchronized vehicle load parameters and synchronized bearing mechanical response parameters, i.e., a dynamic theoretical model coupled with the environment and load is established. This model is dynamically corrected using synchronized ambient temperature parameters, and then coupled to discriminate the corresponding hazard characteristic patterns, filtering out interference from ambient temperature changes. Furthermore, the response residual is obtained by using the corrected theoretical model and synchronized data to filter out normal operating loads on the bridge, solving the problems of false alarms and missed alarms in traditional monitoring technologies. Time series analysis of the hazard characteristic patterns reveals the degradation trend of bearing performance. Finally, risk warning information is output based on the risk probability value and hazard characteristic patterns, realizing a shift from passive alarm to active prediction, achieving monitoring and early warning of potential hazards in road and bridge bearings, and greatly improving the accuracy and reliability of road and bridge bearing hazard monitoring.

[0014] Furthermore, the acquisition of multi-dimensional vehicle passage data, and the time synchronization processing based on the multi-dimensional vehicle passage data to obtain synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters, includes:

[0015] The multidimensional vehicle data includes vehicle load parameters, bearing mechanical response parameters, structural attitude parameters, and ambient temperature parameters.

[0016] When a vehicle is passing by:

[0017] Collect vehicle axle load dataset and vehicle speed dataset, and obtain the vehicle load parameters based on the vehicle axle load dataset and vehicle speed dataset;

[0018] Collect the vertical pressure set and three-dimensional displacement dataset of the support, and obtain the mechanical response parameters of the support based on the vertical pressure set and three-dimensional displacement dataset;

[0019] Collect a dataset of support tilt angle changes, and obtain the structural attitude parameters based on the dataset of support tilt angle changes;

[0020] Collect several temperature datasets at several designated locations, and obtain the ambient temperature parameters based on the several temperature datasets;

[0021] Based on the vehicle load parameters, bearing mechanical response parameters, structural attitude parameters, and ambient temperature parameters, time synchronization processing is performed to obtain synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters.

[0022] The above scheme collects multi-dimensional data such as vehicle axle load, speed, bearing pressure, three-dimensional displacement, tilt angle change, and ambient temperature when a vehicle passes by, and performs time alignment to generate a synchronized dataset containing synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters. This constructs a multi-dimensional, synchronized data acquisition system, integrating previously discrete and isolated monitoring data points into a complete event dataset with inherent physical correlation. It accurately quantifies uncontrollable random vehicle loads into known input excitations, uses the bearing mechanical response and attitude changes as quantifiable outputs, and uses ambient temperature as a key boundary condition, creating the necessary prerequisites for subsequently establishing accurate load-response models and eliminating non-structural interference. This solves the problem of temporal disorder caused by asynchronous sampling from multiple source sensors in traditional monitoring. For example, misalignment of vehicle load and bearing response data may lead to misjudgments of mechanical transmission relationships. It ensures the spatiotemporal correspondence between ambient temperature changes and mechanical response data, providing an accurate benchmark for subsequent temperature correction. Through precise capture and time synchronization of the dynamic process, it prepares the data foundation for accurately constructing theoretical transmission models.

[0023] Furthermore, the construction of the theoretical transfer relationship model based on the synchronous vehicle load parameters and the synchronous support mechanical response parameters includes:

[0024] The synchronous vehicle load parameters are used as the input excitation signal, and the synchronous support mechanical response parameters are used as the output response signal.

[0025] A theoretical transfer relationship model is constructed based on the input excitation signal, the output response signal, and the preset system identification method.

[0026] In the above scheme, the synchronous vehicle load is used as the input excitation, and the bearing mechanical response is used as the output signal. A theoretical model is established through system identification methods to quantify the mapping relationship between load and response. By establishing this dynamic, causal-based theoretical transmission model, each measurement value is no longer viewed in isolation. A scale for evaluating the rationality of the bearing response is designed, providing the most crucial theoretical foundation for subsequent steps to accurately distinguish between minor anomalies caused by structural performance degradation and severe but harmless responses caused by normal loads. This achieves a fundamental shift from passive data monitoring to proactive performance evaluation.

[0027] Furthermore, the dynamic correction based on the synchronous ambient temperature parameters and the theoretical transfer relationship model to generate a corrected theoretical model includes:

[0028] The real-time temperature value is obtained based on the synchronous ambient temperature parameters;

[0029] The real-time corrected stiffness value is obtained based on the preset temperature-stiffness correlation function and the real-time temperature value;

[0030] Dynamic correction is performed based on the real-time corrected stiffness value and the theoretical transfer relationship model to generate a corrected theoretical model.

[0031] In the above scheme, a preset temperature-stiffness correlation function is used to dynamically adjust the stiffness parameters of the correction theoretical model according to the real-time temperature, thereby generating a corrected theoretical model. Through active temperature compensation, nonlinear changes in material stiffness caused by temperature changes are avoided. This effectively filters out normal fluctuations in support response caused by environmental factors such as day-night temperature differences and seasonal changes, eliminates the interference of temperature on the mechanical response of the support, reduces residual fluctuations caused by environmental factors, and makes the model prediction more applicable to complex and changing real-world scenarios.

[0032] Furthermore, obtaining the response residual based on the modified theoretical model, synchronous vehicle load parameters, and synchronous bearing mechanical response parameters includes:

[0033] The theoretical expected response value is obtained based on the synchronous vehicle load parameters and the modified theoretical model;

[0034] The response residual is obtained based on the mechanical response of the synchronous support and the theoretical expected response value.

[0035] In the above scheme, the predicted response value is obtained by correcting the theoretical model and comparing it with the measured response. The residual reflects the deviation between the measured value and the theoretical prediction, characterizes the degree of anomaly, and effectively distinguishes between normal operating load fluctuations and structural damage. This successfully transforms a complex comparison problem into the analysis of a single, pure anomaly signal. The calculated response residual signal undergoes dual stripping of load and temperature effects, and its information is almost entirely about structural performance degradation or damage. Compared to directly analyzing the original signal in traditional methods, analyzing the response residual can greatly amplify the characteristics of potential hazards. Even very small early damages that are difficult to detect in the original signal will appear as clear, regular non-zero signals in the response residual signal. This provides high-quality, high signal-to-noise ratio input data for subsequent accurate identification of the type and severity of potential hazards.

[0036] Furthermore, the step of coupling and discriminating based on the response residual and the synchronous structure attitude parameters to obtain the hidden danger feature pattern includes:

[0037] Feature extraction is performed based on the response residuals to obtain residual distribution features;

[0038] Feature extraction is performed based on the attitude parameters of the synchronous structure to obtain tilt angle change features;

[0039] Based on the residual distribution characteristics, tilt angle change characteristics, and preset feature pattern database, a coupled discrimination is performed to obtain the hidden danger feature pattern.

[0040] The above scheme fundamentally solves the fuzziness and uncertainty of diagnosis from a single information source by introducing synchronous structural attitude parameters and response residuals for coupled discrimination. It achieves cross-validation of multi-dimensional information, greatly improves the accuracy and reliability of diagnosis, effectively avoids misjudgment and omission, and can output hidden danger characteristic patterns with clear physical meaning, providing unprecedented precise guidance for subsequent risk assessment and maintenance decisions.

[0041] Furthermore, the step of performing time series analysis based on the hazard characteristic pattern to obtain the risk probability value includes:

[0042] The current residual index is obtained based on the aforementioned hidden danger characteristic pattern;

[0043] Obtain historical residual indices, and perform time series analysis based on the current residual indices and historical residual indices to obtain a series of residual indices;

[0044] Based on the residual index series, a trend fit is performed to obtain the performance degradation trend line;

[0045] Extrapolation prediction is performed based on the performance degradation trend line to obtain the risk probability value.

[0046] Furthermore, the step of extrapolating and predicting based on the performance degradation trend line to obtain a risk probability value includes:

[0047] The performance degradation rate is obtained based on the aforementioned performance degradation trend line;

[0048] The remaining safe lifetime is obtained based on the performance degradation rate and the preset failure threshold residual index.

[0049] The risk probability value is obtained based on the preset risk mapping function and the remaining safe lifetime.

[0050] In the above scheme, a time series model is constructed based on the historical residual index. The performance degradation trend line is fitted and extrapolated to predict the risk probability. Time series analysis reveals the deterioration pattern of bearing performance over time. By comparing the performance degradation rate with the failure threshold, the remaining safe life is estimated, which helps in the formulation of subsequent preventive maintenance plans. Combined with the current residual index, the trend line is continuously updated to achieve dynamic risk assessment and accelerate the extrapolation prediction frequency. By outputting quantitative remaining safe life values ​​and risk probability values, unprecedented decision support is provided for bridge management and maintenance. This allows managers to no longer rely on fixed maintenance cycles or passive alarm signals, but instead formulate accurate, state-based preventive maintenance plans based on the scientific and data-driven prediction results provided by the prediction method of this invention. This not only effectively avoids catastrophic accidents caused by sudden bearing failure, but also significantly optimizes maintenance resource allocation and extends the service life of the structure by intervening at the optimal time, thereby minimizing the total life cycle cost while ensuring safety.

[0051] Furthermore, the step of obtaining graded early warning information based on the risk probability value and hidden danger characteristic pattern to realize the monitoring and early warning of road and bridge bearing hidden dangers includes:

[0052] The warning level is obtained based on the risk probability value and the preset risk warning classification threshold;

[0053] Based on the aforementioned warning levels and hazard characteristic patterns, graded warning information is obtained to achieve monitoring and early warning of road and bridge bearing hazards.

[0054] The above solution achieves differentiated early warning through multi-level threshold settings, which facilitates managers in quickly identifying the type and severity of potential hazards and improves the flexibility of early warning strategies. It transforms complex and continuous risk probability values ​​into operational instructions with clear priorities that are easy for managers to understand and execute. It realizes a differentiated early warning mode, enabling managers to rationally allocate maintenance resources according to the urgency of risks, such as continuously tracking low-risk hazards, arranging planned maintenance for medium-risk hazards, and activating emergency response plans only for high-risk hazards.

[0055] This invention provides a method for monitoring and early warning of potential hazards in road and bridge bearings, significantly improving the accuracy and reliability of hazard monitoring. Firstly, the method does not rely on isolated parameter thresholds. Instead, it establishes a dynamic theoretical model coupled with the environment and loads, analyzing the residual between the actual response and theoretical expectations. This effectively filters out interference from normal operating loads and environmental temperature changes, fundamentally solving the false alarm and missed alarm problems inherent in traditional monitoring technologies. Secondly, by conducting long-term time-series analysis of the quantified hazard characteristics, it more accurately reveals the degradation trend of bearing performance and provides a quantified risk probability assessment, achieving a shift from passive alarm to proactive prediction. This provides a scientific basis for managers to implement state-based preventative maintenance strategies, enabling them to take measures before hazards evolve into serious failures, ensuring structural safety. Finally, by coupling the mechanical response residual with structural attitude parameters, this invention accurately identifies different hazard characteristic patterns, such as bearing jamming or detachment, constructing a multi-dimensional cross-validation mechanism. This gives the diagnostic results clear physical meaning, providing precise guidance for subsequent maintenance and reinforcement work and avoiding blind handling. It effectively solves the problems of ineffective fixed threshold alarms and false alarms and missed alarms caused by environmental interference in traditional technologies, and breaks through the limitations of post-event alarms. It realizes quantitative assessment and forward-looking prediction of the performance degradation trend of bearings, and provides reliable dynamic monitoring and early warning support for bridge structural safety.

[0056] This invention also provides a road and bridge bearing hidden danger monitoring and early warning system, used to implement the above-mentioned road and bridge bearing hidden danger monitoring and early warning method, comprising:

[0057] The acquisition and synchronization module is used to acquire multi-dimensional vehicle passage data and perform time synchronization processing based on the multi-dimensional vehicle passage data to acquire synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structural attitude parameters and synchronized ambient temperature parameters.

[0058] The theoretical model construction module is used to construct a theoretical transfer relationship model based on the synchronous vehicle load parameters and synchronous support mechanical response parameters.

[0059] The dynamic model correction module is used to dynamically correct the synchronous ambient temperature parameters and the theoretical transfer relationship model to generate a corrected theoretical model.

[0060] The response residual calculation module is used to obtain the response residual based on the modified theoretical model, synchronous vehicle load parameters, and synchronous support mechanical response parameters.

[0061] The hazard pattern discrimination module is used to perform coupled discrimination based on the response residual and the attitude parameters of the synchronization structure to obtain hazard feature patterns;

[0062] The risk probability prediction module is used to perform time series analysis based on the hazard characteristic pattern to obtain the risk probability value.

[0063] The graded early warning generation module is used to obtain graded early warning information based on the risk probability value and hidden danger characteristic pattern, so as to realize the monitoring and early warning of hidden dangers in road and bridge bearings.

[0064] This invention provides a road and bridge bearing hidden danger monitoring and early warning system. First, a data acquisition and synchronization module performs time synchronization processing on the collected multi-dimensional vehicle passage information, forming a synchronized dataset including synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters. Next, a theoretical model construction module establishes a theoretical transfer relationship model based on the synchronized vehicle load parameters and synchronized bearing mechanical response parameters, i.e., establishing a dynamic theoretical model coupled with the environment and load. A dynamic model correction module dynamically corrects the model using synchronized ambient temperature parameters, and a response residual calculation module calculates the response residual, thereby enabling the system to... The hazard pattern discrimination module is coupled to identify the corresponding hazard characteristic patterns, filtering out interference from changes in ambient temperature. A modified theoretical model and synchronously acquired response residuals are used to filter out normal operational loads on the bridge, solving the problems of false alarms and missed alarms in traditional monitoring technologies. A risk probability prediction module performs time-series analysis on the hazard characteristic patterns to reveal the degradation trend of bearing performance. Finally, a graded early warning generation module calculates the risk probability value and hazard characteristic patterns to output risk warning information, realizing a shift from passive alarm to active prediction. This achieves monitoring and early warning of road and bridge bearing hazards, greatly improving the accuracy and reliability of road and bridge bearing hazard monitoring. Attached Figure Description

[0065] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0066] Figure 1 This is a schematic diagram of a method for monitoring and early warning of potential hazards in road and bridge bearings provided in this embodiment;

[0067] Figure 2 This is a schematic diagram of a road and bridge bearing hidden danger monitoring and early warning system provided in this embodiment. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0069] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0070] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0071] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0072] In the description of the embodiments in this application, the term "and / or" 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, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0073] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0074] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0075] This embodiment provides a method for monitoring and early warning of potential hazards in road and bridge bearings, such as... Figure 1 As shown, it includes:

[0076] S1. Acquire multi-dimensional vehicle passage data, and perform time synchronization processing based on the multi-dimensional vehicle passage data to obtain synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters.

[0077] S2. Construct a theoretical transfer relationship model based on the synchronous vehicle load parameters and synchronous support mechanical response parameters;

[0078] S3. Based on the synchronous ambient temperature parameters and the theoretical transfer relationship model, perform dynamic correction to generate a corrected theoretical model;

[0079] S4. Obtain the response residual based on the modified theoretical model, synchronous vehicle load parameters, and synchronous support mechanical response parameters;

[0080] S5. Based on the response residual and the attitude parameters of the synchronization structure, perform coupled discrimination to obtain the hidden danger feature pattern;

[0081] S6. Perform time series analysis based on the aforementioned hidden danger characteristic pattern to obtain the risk probability value;

[0082] S7. Based on the risk probability value and hidden danger characteristic pattern, obtain graded early warning information to realize the monitoring and early warning of hidden dangers in road and bridge bearings.

[0083] This embodiment provides a method for monitoring and early warning of potential hazards in road and bridge bearings. First, the collected multi-dimensional vehicle transit information is processed in time synchronization to form a synchronized dataset containing synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters. Next, a theoretical transfer relationship model is established based on the synchronized vehicle load parameters and synchronized bearing mechanical response parameters, i.e., a dynamic theoretical model coupled with the environment and load is established. This model is dynamically corrected using synchronized ambient temperature parameters, and then coupled to discriminate the corresponding hazard characteristic patterns, filtering out interference from ambient temperature changes. Furthermore, the response residuals obtained from the corrected theoretical model and synchronized data are used to filter out normal operating loads on the bridge, solving the problems of false alarms and missed alarms in traditional monitoring technologies. Time series analysis of the hazard characteristic patterns is performed to reveal the degradation trend of bearing performance. Finally, the risk probability value and hazard characteristic patterns are calculated, and risk warning information is output, realizing a shift from passive alarm to active prediction, achieving monitoring and early warning of potential hazards in road and bridge bearings, and greatly improving the accuracy and reliability of road and bridge bearing hazard monitoring.

[0084] Optionally, step S1 includes:

[0085] The multidimensional vehicle data includes vehicle load parameters, bearing mechanical response parameters, structural attitude parameters, and ambient temperature parameters.

[0086] When a vehicle is passing by:

[0087] Collect vehicle axle load dataset and vehicle speed dataset, and obtain the vehicle load parameters based on the vehicle axle load dataset and vehicle speed dataset;

[0088] Collect the vertical pressure set and three-dimensional displacement dataset of the support, and obtain the mechanical response parameters of the support based on the vertical pressure set and three-dimensional displacement dataset;

[0089] Collect a dataset of support tilt angle changes, and obtain the structural attitude parameters based on the dataset of support tilt angle changes;

[0090] Collect several temperature datasets at several designated locations, and obtain the ambient temperature parameters based on the several temperature datasets;

[0091] Based on the vehicle load parameters, bearing mechanical response parameters, structural attitude parameters, and ambient temperature parameters, time synchronization processing is performed to obtain synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters.

[0092] In the specific implementation process, this embodiment addresses the following each time a vehicle passes:

[0093] The axle load and speed data of vehicles passing through are collected by a weighing sensor system to construct vehicle axle load dataset and vehicle speed dataset, thereby forming vehicle load parameters. It should be noted that a high-precision dynamic weighing sensor system is pre-embedded under the bridge deck lane near the monitoring support. When a vehicle passes through, the system captures and outputs data in real time, including the total weight of the vehicle, the axle load of each axle, and the corresponding passing speed, forming vehicle load parameters as input excitation for subsequent analysis.

[0094] Vertical pressure and three-dimensional displacement data of the bearing are collected by mechanical sensors to construct vertical pressure sets and three-dimensional displacement sets, forming the bearing mechanical response parameters. It should be noted that a high-sensitivity pressure sensor is installed above or below the core bearing surface of the bearing to continuously measure the vertical pressure changes of the bearing caused by vehicle load and structural self-weight. At the same time, a three-dimensional displacement sensor is installed between the upper and lower bearing plates of the bearing to synchronously monitor the relative displacement of the bearing in the longitudinal, lateral and vertical directions. These two sets of data together constitute the bearing mechanical response parameters that reflect the direct stress and deformation state of the bearing.

[0095] The tilt angle change data of the support is collected by the tilt angle sensor to construct the support tilt angle change dataset, and then the structural attitude parameters are formed. It should be noted that a dual-axis tilt angle sensor is precisely installed on the surface of the upper seat plate of the support to monitor the minute tilt angle changes of the support in real time during the passage of the vehicle. This tilt angle change data is the structural attitude parameters.

[0096] Temperature data at the location of the support is collected by temperature sensors, and several temperature datasets are constructed to form environmental temperature parameters. It should be noted that multiple temperature sensors are deployed in the steel components, polymer sliding plate material and surrounding beam concrete of the support to form temperature field monitoring of the support and its local environment. These multi-point temperature readings (i.e., several temperature datasets) are combined to form environmental temperature parameters.

[0097] A unified timestamp is applied to the vehicle load parameters, the bearing mechanical response parameters, the structural attitude parameters, and the ambient temperature parameters to generate a synchronized multidimensional dataset including synchronized vehicle load parameters, synchronized bearing mechanical response parameters, synchronized structural attitude parameters, and synchronized ambient temperature parameters. It should be noted that all sensing units are timestamped through a high-precision clock synchronization module to ensure that the vehicle load parameters, bearing mechanical response parameters, structural attitude parameters, and ambient temperature parameters collected at any given moment have strict temporal consistency, providing a high-quality data foundation for subsequent causal correlation analysis.

[0098] Optionally, step S2 includes:

[0099] The synchronous vehicle load parameters are used as the input excitation signal, and the synchronous support mechanical response parameters are used as the output response signal.

[0100] A theoretical transfer relationship model is constructed based on the input excitation signal, the output response signal, and the preset system identification method.

[0101] In the specific implementation process, the step of establishing the theoretical transfer relationship model is to systematically analyze the correlation between the synchronous vehicle load parameters and the synchronous bearing mechanical response parameters after obtaining them. This process treats each vehicle passage event as a dynamic loading test on the bearing system. First, the time-varying synchronous vehicle load parameters, namely the effective dynamic load force time history acting on the bearing calculated by combining the vehicle axle load and speed measured by the weighing system with the influence line of the bridge structure, are defined as the system's input excitation signal P(t). At the same time, the vertical displacement and shear displacement of the bearing synchronously collected by the sensors are defined as the system's output response signal D(t).

[0102] It should be noted that the specific process of calculating the effective dynamic load force time history acting on the support by combining the vehicle axle load and speed measured by the weighing system with the influence line of the bridge structure is as follows: 1) Data acquisition and preprocessing: The axle load and corresponding vehicle speed of each axle when the vehicle passes are obtained through a high-precision dynamic weighing sensor system. The collected data are timestamped to ensure that the vehicle passing time and the support response data strictly correspond; 2) Application of the bridge structure influence line: Definition of influence line: The bridge structure influence line is a curve that describes the change of internal force of a specified support or section with the load position when a unit load moves on the bridge; Dynamic load position tracking: According to the vehicle axle load distribution and vehicle speed, the position of each axle on the bridge at each moment is calculated, and the load contribution of this position to the target support is determined by combining the influence line. Assuming that the position of the i-th axle of the vehicle at time t is x_i(t), the corresponding influence line at x_i(t) is x_i(t). The value at _i(t) is I_i(t), where I_i(t) is the influence line value of the i-th axle of the vehicle at time t. The dynamic load contribution of this axle to the target support is: F_i(t) = axle load _i × I_i(t), where F_i(t) is the dynamic load of the i-th axle of the vehicle at time t on the target support. The contributions of all axles are superimposed to obtain the total dynamic load: F_total(t) = ΣF_i(t), where F_total(t) is the total dynamic load at time t; 3) Time history curve generation: The dynamic load F_total(t) at each time t of the entire process of the vehicle is arranged in chronological order to form a dynamic load force time history curve that varies with time; 4) Input excitation signal definition: The time-varying dynamic load force time history F_total(t) calculated above is used as the system input excitation signal. The model input is shown in the following formula:

[0103] F_total(t)=[f(t1),f(t2),...,f(tn)]

[0104] Where t1 to tn represent time series points, and f(t1), f(t2), ..., f(tn) represent the dynamic loads of F_total(t) at discrete time series points t1, t2, ..., tn, respectively.

[0105] It should also be noted that, in the case of road and bridge bearings, the shear displacement specifically refers to the relative displacement between the upper and lower bearing plates in the horizontal direction, that is, in the direction perpendicular to the central axis of the bearing, when the bearing is subjected to vehicle load. The lateral and longitudinal displacement data reflect the shear displacement of the bearing.

[0106] Next, the inherent correlation between the input excitation signal and the output response signal is analyzed by the system identification method, and a load-response correlation model is constructed to obtain the theoretical transmission relationship model.

[0107] It should be noted that system identification is a method of establishing a dynamic mathematical model of the support system by analyzing the correlation between the input excitation signal and the output response signal. The specific steps are as follows: 1) System simplification and dynamic modeling: The support and its surrounding structure are simplified into a single-degree-of-freedom or multi-degree-of-freedom mechanical vibration system, whose dynamic behavior can be described by the following second-order ordinary differential equation: Where D(t) represents the displacement response of the support, i.e. the output response signal, P(t) represents the equivalent load under the action of the vehicle, i.e. the input excitation signal, and M, C, and K represent the equivalent mass, equivalent damping, and equivalent stiffness of the system, respectively.

[0108] 2) Input-output data alignment: Ensure strict alignment of the timestamps of vehicle load parameters and support displacement parameters to form a synchronized multidimensional dataset; 3) Parameter estimation method: Use the least squares method to solve for the M, C, and K values ​​in the equation. The corresponding formula for the least squares method is:

[0109] 4) Theoretical transfer relationship model output: The optimal combination of physical parameters M, C, and K constitutes the theoretical transfer relationship model of the support.

[0110] Optionally, step S3 includes:

[0111] The real-time temperature value is obtained based on the synchronous ambient temperature parameters;

[0112] The real-time corrected stiffness value is obtained based on the preset temperature-stiffness correlation function and the real-time temperature value;

[0113] Dynamic correction is performed based on the real-time corrected stiffness value and the theoretical transfer relationship model to generate a corrected theoretical model.

[0114] In the specific implementation process, the ambient temperature parameters synchronously collected by the multi-dimensional sensing unit group are extracted. By averaging the temperature data from multiple points on the support body and surrounding structure, an effective temperature value T representing the current working state of the support is obtained. To achieve dynamic correction, this embodiment calls a pre-established temperature-stiffness correlation function, namely: K(T)=K_ref×(1+α×(T-T_ref)), where K(T) represents the corrected stiffness value of the support at the effective temperature value T in the current working state, K_ref represents the equivalent stiffness of the support calibrated at a reference temperature T_ref, which is preset during the system initialization stage, and α represents the stiffness temperature correction coefficient of the support, which is preset based on experimental data of the material's physical properties. Substituting the real-time acquired effective temperature value T into the above formula, the corrected stiffness value K(T) at the current temperature is calculated. Finally, the corrected stiffness value is applied to the stiffness parameters in the theoretical transfer relationship model to generate the corrected theoretical model.

[0115] It should be noted that by replacing the equivalent support stiffness K_ref in the original theoretical transmission relationship model with the corrected stiffness value K(T), a corrected theoretical model adapted to the current ambient temperature is generated. This effectively filters out normal fluctuations in support response caused by environmental factors such as diurnal temperature differences and seasonal changes. These fluctuations are often misjudged as structural anomalies in traditional monitoring methods, which is the main reason for the high false alarm rate.

[0116] In a specific embodiment of the present invention, the typical value of the stiffness temperature correction coefficient α needs to be pre-set based on experimental data of the physical properties of the key materials of the support. Its value has a clear physical basis: for supports mainly composed of polymer materials, experiments show that their elastic modulus decreases approximately linearly with increasing temperature, and a typical α value can be taken as -0.002 to -0.003 / ℃; for metal components, due to the low temperature sensitivity of the elastic modulus and the weak linear expansion effect, α is usually taken as a very small value close to 0; for steel-rubber composite supports, the contributions of the rubber layer and the metal layer need to be weighted according to volume fraction, and the comprehensive α value is approximately -0.002 to -0.003 / ℃. This coefficient is determined by fitting the temperature-mechanical property curve obtained from standard material experiments, ensuring that the model correction conforms to the material constitutive relationship and meets engineering accuracy requirements.

[0117] Optionally, step S4 includes:

[0118] The theoretical expected response value is obtained based on the synchronous vehicle load parameters and the modified theoretical model;

[0119] The response residual is obtained based on the mechanical response of the synchronous support and the theoretical expected response value.

[0120] In the specific implementation process, calculating the response residual is a crucial step in the diagnostic process, aiming to quantify the deviation between the actual behavior of the bearing and its theoretical healthy behavior. First, the measured mechanical response parameters of the bearing, acquired synchronously with the vehicle load parameters, are obtained. This represents the displacement or pressure time history signal of the bearing's true state, denoted as D_measured(t). Simultaneously, the generated modified theoretical model is invoked, using the synchronous vehicle load parameter P(t) corresponding to the measured data as input. This drives the modified theoretical model to perform a forward calculation, thereby solving for the theoretical response that a fully healthy bearing should produce under specific load and temperature conditions. This result is the theoretical expected value, denoted as D_theoretical(t). The difference between the measured bearing mechanical response parameters and the theoretical expected response value is then calculated to obtain the response residual. It should be noted that in practical applications, the measured mechanical response parameters of the support on the same time axis are compared point by point with the theoretical expected values, and the difference between the two is calculated: R(t) = D_measured(t) - D_theoretical(t), where R(t) represents the response residual. The magnitude of the response residual R(t) directly reflects the degree to which the actual performance of the support deviates from the healthy benchmark.

[0121] Optionally, the step of coupling discrimination based on the response residual and the attitude parameters of the synchronization structure to obtain the hidden danger feature pattern includes:

[0122] Feature extraction is performed based on the response residuals to obtain residual distribution features;

[0123] Feature extraction is performed based on the attitude parameters of the synchronous structure to obtain tilt angle change features;

[0124] Based on the residual distribution characteristics, tilt angle change characteristics, and preset feature pattern database, a coupled discrimination is performed to obtain the hidden danger feature pattern.

[0125] In the specific implementation process, the specific process of coupling the discrimination and outputting the hidden danger feature pattern is as follows: 1) Feature extraction of response residuals: First, the response residuals are subjected to detailed feature extraction, which is clearly decomposed into vertical pressure residual components and shear displacement residual components. Then, for these two components, their statistical features in a single vehicle passage event are obtained. These statistical features include, but are not limited to, the mean and peak values, and finally form a residual feature vector that comprehensively describes the residual characteristics. 2) Feature extraction of synchronous structural attitude parameters: From the synchronously acquired structural attitude parameters, the tilt angle change data is specifically extracted to determine its maximum amplitude. 3) Coupled discrimination of residual distribution characteristics and tilt angle change characteristics: 31) Start discrimination logic: After obtaining the residual feature vector and tilt angle change characteristics, the coupled discrimination logic is started immediately; 32) Apply expert rule base: The discrimination logic is executed through a preset expert rule base (preset feature pattern database). The preset feature pattern database stores the precise mapping relationship between different hidden danger feature patterns and residual features and attitude features; 33) Identify hidden danger feature patterns: 331) Support detachment judgment: When the discrimination logic detects that the residual feature vector shows a significant negative deviation in the vertical pressure residual component, while the shear displacement residual component has no obvious pattern, the system will initially judge that there may be a support detachment; 332) Support jamming judgment: If the discrimination logic further detects that the shear displacement residual component shows an obvious lag phenomenon, that is, the measured displacement is much smaller than the theoretical expected value, and this phenomenon shows an abnormal, synchronous positive correlation peak with the tilt angle change data in the structural attitude parameters, the system will highly confidently judge that the support jamming has occurred. 4) Output hidden danger feature patterns: Based on the results of coupling discrimination, the system identifies and outputs specific hidden danger feature patterns, providing important reference for subsequent maintenance and repair work.

[0126] Optionally, the step of performing time series analysis based on the hazard characteristic pattern to obtain the risk probability value includes:

[0127] The current residual index is obtained based on the aforementioned hidden danger characteristic pattern;

[0128] Obtain historical residual indices, and perform time series analysis based on the current residual indices and historical residual indices to obtain a series of residual indices;

[0129] Based on the residual index series, a trend fit is performed to obtain the performance degradation trend line;

[0130] Extrapolation prediction is performed based on the performance degradation trend line to obtain the risk probability value.

[0131] In the specific implementation process, the hazard characteristic patterns generated by the coupled discrimination step after each vehicle passage event are first systematically recorded. To quantify these qualitative diagnostic results, a comprehensive quantitative index, namely the residual index, is extracted from the response residuals that generate the patterns. The residual index can be defined as the energy integral of the response residual signal over one event period, I = ∫[R(t)]²dt, where I represents the residual index of a single event, the magnitude of which directly reflects the severity of the deviation of the support behavior from the healthy baseline in that event, and R(t) is the response residual calculated by the previous steps. Time series analysis is performed on the historical residual index and the current residual index to obtain a residual index series. The residual indices of multiple events are then accumulated in chronological order to form a residual index sequence. Trend fitting is then performed on the residual index sequence to establish a performance degradation trend line.

[0132] It should be noted that, over time, the system continuously records the occurrence time and corresponding residual exponent of each event, forming a discrete sequence containing multiple data points. Subsequently, the system employs trend fitting technology to perform linear regression fitting on this sequence data, thereby obtaining a trend line that describes the long-term evolution of the residual exponent. It should also be further explained that the specific process of performing linear regression fitting includes: 1) Data preparation: continuously recording the occurrence time t′ of each vehicle passage event. j and the corresponding residual exponent I j This forms a discrete sequence containing multiple data points, where j represents the vehicle passage event number, j = 1, 2, ..., m; 2) Linear regression model specification: The basic form of the linear regression model is I = a × t′ + b, where I represents the residual exponent, t′ represents time, a represents the slope, and b represents the intercept; 3) Parameter estimation: Linear regression fitting usually uses the least squares method to estimate the model parameters a and b. The goal of the least squares method is to minimize the sum of squared errors between the model predictions and the actual observations. The calculation process is as follows: Calculate the mean of time t′ and the residual exponent I. and Calculate the estimated value of the slope 'a': Calculate the estimated value of the intercept b: 4) Substitute the estimated slope a and intercept b into the linear regression model I=a×t′+b to obtain the equation of the performance degradation trend line. Plot the trend line on the time-residual exponent plane so as to intuitively observe the trend of the residual exponent over time.

[0133] Optionally, the step of extrapolating and predicting based on the performance degradation trend line to obtain the risk probability value includes:

[0134] The performance degradation rate is obtained based on the aforementioned performance degradation trend line;

[0135] The remaining safe lifetime is obtained based on the performance degradation rate and the preset failure threshold residual index.

[0136] The risk probability value is obtained based on the preset risk mapping function and the remaining safe lifetime.

[0137] In the specific implementation process, it is first necessary to define a failure threshold residual index based on the structural properties of the support, namely the preset failure threshold residual index. It should be noted that the failure threshold residual index is a critical residual index derived from the support's design specifications, material fatigue test data, or historical failure case statistics.

[0138] Next, during the prediction process, the remaining safe lifetime is calculated by combining the performance degradation rate and the failure threshold. It should be noted that the specific formula for calculating the remaining safe lifetime is: RSL = (I_fail - I_current) / k, where RSL represents the calculated remaining safe lifetime value, I_fail represents the preset failure threshold residual index, I_current represents the latest residual index value, and k represents the slope of the residual index time series change, i.e., the performance degradation rate. This formula can predict how long it will take for the support to reach a failure state at the current degradation rate, i.e., the remaining safe lifetime.

[0139] Finally, the remaining safe lifetime is converted into the risk probability value using a preset risk mapping function. It should be noted that the remaining safe lifetime is compared with the remaining safe lifetime intervals corresponding to each risk probability value stored in the database. If the remaining safe lifetime falls within the remaining safe lifetime interval corresponding to a certain risk probability value, then that risk probability value is used as the risk probability value converted from the remaining safe lifetime.

[0140] Optionally, the step of obtaining graded early warning information based on the risk probability value and hidden danger characteristic pattern to realize the monitoring and early warning of road and bridge bearing hidden dangers includes:

[0141] The warning level is obtained based on the risk probability value and the preset risk warning classification threshold;

[0142] Based on the aforementioned warning levels and hazard characteristic patterns, graded warning information is obtained to achieve monitoring and early warning of road and bridge bearing hazards.

[0143] In practical implementation, generating tiered early warning information is the final output of the entire monitoring and early warning process, aiming to transform complex prediction results into clear and actionable management instructions. This process begins with multiple risk probability thresholds pre-set in the system backend. These thresholds are not arbitrarily set but are scientifically divided into multiple levels based on bridge design specifications, maintenance manuals, and the management's risk tolerance, forming the preset risk early warning tiered thresholds. For example, there are observation-level thresholds, early warning-level thresholds, and alarm-level thresholds. When the system calculates the latest risk probability value, it immediately compares it logically with these preset risk probability thresholds. If the risk probability value exceeds the observation-level threshold but is lower than the early warning-level threshold, the system will trigger a blue observation-level early warning instruction; if the risk probability value further exceeds the early warning-level threshold but is lower than the alarm-level threshold, a yellow early warning-level early warning instruction will be triggered; once the risk probability value exceeds the highest alarm-level threshold, the system immediately generates a red alarm-level early warning instruction. These early warning instructions are not merely simple alarm signals, but rather structured information packages containing bridge numbers, specific support locations, identified hazard patterns, current risk probability values, and corresponding recommended remedial measures. This transforms complex, continuous risk probability values ​​into easily understandable and prioritized operational instructions for managers. This differentiated early warning model allows managers to allocate maintenance resources rationally based on the urgency of the risks, continuously monitor low-risk hazards, schedule planned maintenance for medium-risk hazards, and activate emergency response plans only for high-risk hazards.

[0144] This embodiment also provides a road and bridge bearing hidden danger monitoring and early warning system to implement the above-mentioned road and bridge bearing hidden danger monitoring and early warning method, including:

[0145] The acquisition and synchronization module is used to acquire multi-dimensional vehicle passage data and perform time synchronization processing based on the multi-dimensional vehicle passage data to acquire synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structural attitude parameters and synchronized ambient temperature parameters.

[0146] The theoretical model construction module is used to construct a theoretical transfer relationship model based on the synchronous vehicle load parameters and synchronous support mechanical response parameters.

[0147] The dynamic model correction module is used to dynamically correct the synchronous ambient temperature parameters and the theoretical transfer relationship model to generate a corrected theoretical model.

[0148] The response residual calculation module is used to obtain the response residual based on the modified theoretical model, synchronous vehicle load parameters, and synchronous support mechanical response parameters.

[0149] The hazard pattern discrimination module is used to perform coupled discrimination based on the response residual and the attitude parameters of the synchronization structure to obtain hazard feature patterns;

[0150] The risk probability prediction module is used to perform time series analysis based on the hazard characteristic pattern to obtain the risk probability value.

[0151] The graded early warning generation module is used to obtain graded early warning information based on the risk probability value and hidden danger characteristic pattern, so as to realize the monitoring and early warning of hidden dangers in road and bridge bearings;

[0152] Optionally, this embodiment also includes a database for storing the remaining safe life intervals corresponding to each risk probability value, and is connected to the risk probability prediction module; the acquisition synchronization module includes a weighing sensing system, a mechanical sensor, an tilt sensor, and a temperature sensor for acquiring multi-dimensional vehicle passage data;

[0153] Specifically, the parameter synchronization acquisition module is connected to the theoretical model construction module, both of which are connected to the dynamic model correction module, both of which are connected to the response residual calculation module, both of which are connected to the hazard mode identification module, the hazard mode identification module is connected to the risk probability prediction module, the risk probability prediction module is connected to the graded early warning generation module, and the risk probability prediction module is connected to the database.

[0154] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for monitoring and early warning of hidden dangers of a road bridge support, characterized in that, The method comprises the following steps: acquiring multi-dimensional vehicle passing data and performing time synchronization processing based on the multi-dimensional vehicle passing data to obtain synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structure posture parameters and synchronized environmental temperature parameters; constructing a theoretical transfer relationship model based on the synchronized vehicle load parameters and the synchronized support mechanical response parameters; performing dynamic correction based on the synchronized environmental temperature parameters and the theoretical transfer relationship model to generate a corrected theoretical model; acquiring response residuals based on the corrected theoretical model, the synchronized vehicle load parameters and the synchronized support mechanical response parameters; performing coupling discrimination based on the response residuals and the synchronized structure posture parameters to obtain a hidden danger feature mode; performing time series analysis based on the hidden danger feature mode to obtain a risk probability value; obtaining grading early warning information based on the risk probability value and the hidden danger feature mode to realize monitoring and early warning of road bridge support hidden dangers.

2. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The method comprises the following steps: The multi-dimensional vehicle passing data comprises vehicle load parameters, support mechanical response parameters, structure posture parameters and environmental temperature parameters. When a vehicle passes: vehicle axle load data sets and vehicle speed data sets are collected, and the vehicle load parameters are obtained based on the vehicle axle load data sets and the vehicle speed data sets; support vertical pressure sets and three-dimensional displacement data sets are collected, and the support mechanical response parameters are obtained based on the vertical pressure sets and the three-dimensional displacement data sets; support inclination change data sets are collected, and the structure posture parameters are obtained based on the support inclination change data sets; a plurality of temperature data sets at a plurality of specified positions are collected, and the environmental temperature parameters are obtained based on the plurality of temperature data sets; time synchronization processing is performed based on the vehicle load parameters, the support mechanical response parameters, the structure posture parameters and the environmental temperature parameters to obtain synchronized vehicle load parameters, synchronized support mechanical response parameters, synchronized structure posture parameters and synchronized environmental temperature parameters.

3. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The method comprises the following steps: The synchronized vehicle load parameters are taken as input excitation signals, and the synchronized support mechanical response parameters are taken as output response signals. A theoretical transfer relationship model is constructed based on the input excitation signals, the output response signals and a preset system identification method.

4. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The method comprises the following steps: Real-time temperature values are obtained based on the synchronized environmental temperature parameters. Real-time correction stiffness values are obtained based on a preset temperature-stiffness correlation function and the real-time temperature values. Dynamic correction is performed based on the real-time correction stiffness values and the theoretical transfer relationship model to generate a corrected theoretical model.

5. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The method comprises the following steps: Theoretical expected response values are obtained based on the synchronized vehicle load parameters and the corrected theoretical model. Obtaining a response residual based on the synchronous support mechanical response and a theoretically expected response value.

6. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The coupling discrimination based on the response residual and the synchronous structure attitude parameter obtains a hidden danger characteristic mode, including: Feature extraction based on the response residual obtains a residual distribution characteristic; Feature extraction based on the synchronous structure attitude parameter obtains a inclination angle change characteristic; Coupling discrimination based on the residual distribution characteristic, the inclination angle change characteristic and a preset characteristic mode database obtains a hidden danger characteristic mode.

7. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The time series analysis based on the hidden danger characteristic mode obtains a risk probability value, including: Obtaining a current residual index based on the hidden danger characteristic mode; Obtaining a historical residual index, and performing time series analysis based on the current residual index and the historical residual index to obtain a residual index series; Trend fitting based on the residual index series obtains a performance degradation trend line; Extrapolation prediction based on the performance degradation trend line obtains a risk probability value.

8. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 7, characterized in that, The time series analysis based on the hidden danger characteristic mode obtains a risk probability value, including: Obtaining a performance degradation rate based on the performance degradation trend line; Obtaining a remaining safe life based on the performance degradation rate and a preset failure threshold residual index; Obtaining a risk probability value based on a preset risk mapping function and the remaining safe life.

9. The method for monitoring and early warning of hidden dangers of a road and bridge support according to claim 1, characterized in that, The risk probability value and the hidden danger characteristic mode obtain a graded early warning information, realizing the monitoring and early warning of the road bridge support hidden danger, including: Obtaining a warning level based on the risk probability value and a preset risk warning grading threshold; Obtaining a graded early warning information based on the warning level and the hidden danger characteristic mode, realizing the monitoring and early warning of the road bridge support hidden danger.

10. A hidden danger monitoring and early warning system for a road-bridge support, characterized in that, A road bridge support hidden danger monitoring and early warning method for realizing any one of claims 1-9, including: A synchronous module for obtaining multi-dimensional vehicle passing data, and performing time synchronization processing based on the multi-dimensional vehicle passing data to obtain synchronous vehicle load parameters, synchronous support mechanical response parameters, synchronous structure attitude parameters and synchronous environmental temperature parameters; A theoretical model construction module for constructing a theoretical transfer relationship model based on the synchronous vehicle load parameters and the synchronous support mechanical response parameters; A dynamic model correction module for dynamic correction based on the synchronous environmental temperature parameters and the theoretical transfer relationship model to generate a corrected theoretical model; A response residual calculation module for obtaining a response residual based on the corrected theoretical model, the synchronous vehicle load parameters and the synchronous support mechanical response parameters; A hidden danger mode discrimination module for coupling discrimination based on the response residual and the synchronous structure attitude parameter to obtain a hidden danger characteristic mode; A risk probability prediction module for time series analysis based on the hidden danger characteristic mode to obtain a risk probability value; A graded early warning generation module for obtaining a graded early warning information based on the risk probability value and the hidden danger characteristic mode to realize the monitoring and early warning of the road bridge support hidden danger.

Images