A bridge structure monitoring method and device, computer equipment and storage medium

Abstract

The application provides a bridge structure monitoring method and device, computer equipment and a storage medium, and belongs to the field of bridge monitoring. The method comprises the following steps: establishing a parameterized initial digital twin model based on the design parameters and initial state of a bridge structure; obtaining measured structure response data of the bridge structure under actual working conditions; calculating the predicted structure response of the bridge structure under the actual working conditions based on the current digital twin model; calculating the response deviation between the predicted structure response and the measured structure response; iteratively correcting the parameters of the initial digital twin model to reduce the response deviation until the response deviation meets the preset convergence condition, thereby obtaining an updated digital twin model; and monitoring and evaluating the current health state of the bridge structure based on the updated digital twin model. Thus, the accuracy and real-time performance of the bridge health state evaluation are improved, and a strong guarantee is provided for the long-term safe service of the bridge.

Description

Technical Field

[0001] This invention belongs to the field of bridge monitoring, and specifically relates to a bridge structure monitoring method, device, computer equipment, and storage medium. Background Technology

[0002] As a crucial transportation infrastructure, bridges are subject to changes in structural performance over long-term service due to factors such as vehicle loads, environmental effects, and material degradation, leading to increased structural safety risks. To ensure bridge operational safety, structural health monitoring technology is commonly used in engineering practice to conduct long-term observations of the bridge's stress state and structural response.

[0003] Existing methods for monitoring the health of bridge structures mainly include sensor-based strain monitoring, vibration monitoring, and structural analysis methods combined with finite element models. While these methods can obtain response information of bridge structures under specific working conditions, they still have the following shortcomings during long-term operation:

[0004] The model is prone to deviating from the actual structural state. In existing methods, finite element models are mostly established based on design parameters or initial calibration parameters, and model parameter updates usually rely on manual correction or offline analysis, making it difficult to continuously reflect the performance changes of bridge structures during service.

[0005] There is a lack of a mechanism for continuous model evolution. Most existing technologies focus on using monitoring data for state analysis, but fail to form a closed-loop mechanism driven by measured data for continuous updates, which causes existing models to gradually become distorted over long-term operation.

[0006] Therefore, existing methods that use finite element models to reflect the performance changes of bridges during service are prone to distortion and cannot effectively reflect the true situation of bridges during service in the long term. Summary of the Invention

[0007] To address the aforementioned problems, this invention provides a bridge structure monitoring method, apparatus, computer equipment, and storage medium.

[0008] To achieve the above objectives, the present invention provides the following technical solution: A method for monitoring bridge structures, the method comprising: Based on the design parameters and initial state of the bridge structure, a parameterized initial digital twin model is established; during the service of the bridge, the measured structural response data of the bridge structure under actual working conditions are obtained. Obtain the working conditions corresponding to the measured structural response data, and calculate the predicted structural response of the bridge structure under these working conditions based on the current digital twin model; Multi-domain feature extraction is performed on the measured structural response data and the predicted structural response, respectively. Structural response features are extracted from at least two domains, namely the time domain, frequency domain and wavelet domain, to obtain the corresponding measured multi-domain feature quantities and predicted multi-domain feature quantities. The predicted multi-domain feature quantities are compared and analyzed with the measured multi-domain feature quantities to construct a multi-domain fusion response deviation. The multi-domain fusion response deviation is used to quantify the difference between the digital twin model and the actual bridge structure state from multiple physical dimensions. With the goal of reducing the multi-domain fusion response bias, the parameters of the initial digital twin model are adaptively and iteratively corrected using the Bayesian inference method. During the parameter update process, the uncertainty quantification results of the model parameters are output synchronously, and the predicted structural response is recalculated after each correction until the preset convergence condition is met, thereby obtaining the updated digital twin model. Based on the updated digital twin model, the current health status of the bridge structure is monitored and evaluated.

[0009] Optionally, the measured structural response data includes one or more of the following: strain data, displacement data, and acceleration response data.

[0010] Optionally, the constructed multi-domain fusion response bias includes: Calculate the intra-domain deviations between the measured multi-domain feature quantities and the predicted multi-domain feature quantities respectively; The intra-domain deviations of each domain are weighted and fused to obtain the multi-domain fused response deviation; wherein, the weight of each domain is dynamically adjusted according to at least one of the current service conditions of the bridge structure, the damage sensitivity calibration results, or the signal-to-noise ratio evaluation results.

[0011] Optionally, before calculating the response deviation, the measured structural response data is preprocessed, including denoising, filtering, and normalization.

[0012] Optionally, the parameters updated in the initial digital twin model include one or more of the following: equivalent stiffness parameters of structural members, equivalent damping parameters, equivalent constraint parameters of connection parts, and equivalent parameters of boundary conditions.

[0013] Optionally, a Bayesian inference method is used to adaptively and iteratively correct the parameters of the initial digital twin model. During the parameter update process, the uncertainty quantification results of the model parameters are output synchronously, and the predicted structural response is recalculated after each correction until the preset convergence conditions are met, including: The prior probability distribution of the updatable parameters in the initial digital twin model is combined with the likelihood function constructed based on the multi-domain fusion response bias to calculate the posterior probability distribution of the updatable parameters. The parameter update value for the current round is obtained by sampling from the posterior probability distribution, and the uncertainty quantification result of the updatable parameter is output synchronously according to the statistical characteristics of the posterior probability distribution; the uncertainty quantification result includes at least one of the parameter's posterior variance, confidence interval, or probability density function. Based on the parameter update value, the corresponding parameters of the digital twin model are corrected, and the predicted structural response and the corresponding multi-domain fusion response deviation are recalculated after correction. The likelihood function is updated using the new multi-domain fusion response deviation, and the next round of Bayesian inference iteration is entered until the preset convergence condition is met.

[0014] Optionally, the monitoring and assessment of the current health status of the bridge structure based on the updated digital twin model includes: The updated model parameters or key structural response indicators output by the model are compared with the historical state or the initial state. When the model parameters change continuously or the key structural response indicators exceed the preset change range, it is determined that the bridge structure state has changed and is output as a health status monitoring result.

[0015] A bridge structure monitoring device, the device comprising: The acquisition module is used to establish a parameterized initial digital twin model based on the design parameters and initial state of the bridge structure; and to acquire measured structural response data of the bridge structure under actual working conditions during the bridge's service life. The prediction module is used to obtain the working conditions corresponding to the measured structural response data, and calculate the predicted structural response of the bridge structure under the working conditions based on the current digital twin model. The calculation module is used to compare and analyze the predicted structural response with the measured structural response data, and calculate the response deviation between the two. The response deviation is used to quantify the difference between the digital twin model and the actual bridge structural state. The update module is used to adaptively and iteratively correct the parameters of the initial digital twin model with the goal of reducing the response deviation, and recalculate the predicted structural response after each correction until the response deviation meets the preset convergence condition, thereby obtaining the updated digital twin model. The monitoring module is used to monitor and assess the current health status of the bridge structure based on the updated digital twin model.

[0016] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned bridge structure monitoring method.

[0017] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned bridge structure monitoring method.

[0018] The bridge structure monitoring method provided by this invention has the following beneficial effects: This invention extracts and fuses structural response features from at least two domains—time, frequency, and wavelet—abandoning the crude approach of relying solely on single-domain time-domain differences or frequency-domain modal comparisons. This allows model bias to be finely characterized and quantified from multiple physical dimensions. This multi-dimensional analysis method can keenly capture early, subtle evolutionary information such as local damage degradation and relaxed boundary constraints, which are easily overlooked in traditional single-domain bias analysis. This ensures that subtle deviations between the model and the actual state are not missed, thus significantly improving the relevance and comprehensiveness of model calibration. Furthermore, a Bayesian inference method is used to replace conventional deterministic optimization. Model parameters are expressed in the form of probability distributions, and the posterior variance or confidence interval of the parameters is output synchronously after each correction. This ensures that model parameter updates are always under the rational constraints of physical probability, avoiding mathematically convergent but physically unreasonable parameter distortion. The resulting digital twin model can dynamically track the actual performance degradation trajectory of bridges during service, truly establishing a long-term closed-loop evolution capability driven by measured data. This lays a solid and reliable foundation for accurate health assessment and safety early warning throughout the entire life cycle of bridges. Attached Figure Description

[0019] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. 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.

[0020] Figure 1 This is a flowchart illustrating a bridge structure monitoring method according to an exemplary embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of a bridge structure provided by the present invention according to an exemplary embodiment.

[0022] Figure 3 This is a schematic diagram of the front structure of a bridge according to an exemplary embodiment of the present invention.

[0023] Figure 4 This is a schematic diagram of the front structure of a bridge according to an exemplary embodiment of the present invention.

[0024] Figure 5 This is a schematic diagram of a controller structure provided by the present invention according to an exemplary embodiment.

[0025] Figure 6 This is a schematic diagram of the front structure of a controller according to an exemplary embodiment of the present invention.

[0026] Figure 7 This is a diagram illustrating a signal processing method provided by the present invention according to an exemplary embodiment.

[0027] Figure 8 This invention provides a damage development trend curve and fatigue accumulation curve according to an exemplary embodiment.

[0028] Figure 9 This is a host computer page design diagram provided by the present invention according to an exemplary embodiment.

[0029] Figure 10 This is a block diagram of a bridge structure monitoring device provided by the present invention according to an exemplary embodiment.

[0030] Figure 11 This is a block diagram of another bridge structure monitoring device provided by the present invention according to an exemplary embodiment. Figure label: 101-Strain gauge, 102-Acceleration sensor, 103-Displacement sensor, 104-Temperature sensor, 201-Controller reserved slot, 401-Sensor interface, 402-Nut port, 501-Wireless module interface, 502-Wired communication interface. Detailed Implementation

[0031] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0032] The technical solutions provided by the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0033] First, this invention provides a method for monitoring bridge structures, specifically as follows: Figure 1 As shown, it includes the following steps: S101. Based on the design parameters and initial state of the bridge structure, establish a parameterized initial digital twin model; obtain the measured structural response data of the bridge structure under actual working conditions during the bridge's service life.

[0034] In this step, a three-dimensional finite element analysis model is preferred for the digital twin model. Based on the bridge structure's design parameters (such as span, cross-sectional shape, material properties, connection method, boundary conditions, and typical load conditions), a finite element model corresponding to the actual bridge is established to simulate the bridge's structural response characteristics under different loads and environmental conditions, serving as a theoretical benchmark for subsequent "virtual-real comparison" and "parameter updates".

[0035] The overall dynamic equation of the system modeled by the finite element method can be expressed as: ; in, These are the mass matrix, damping matrix, and stiffness matrix, respectively. The structural response vector, The above dynamic equations describe the dynamic response behavior of a bridge structure under external loads, and the specific solution method does not constitute a limitation of this invention.

[0036] In the initial digital twin model, at least one type of updatable model parameters are pre-defined to characterize the structural characteristics of the bridge structure that may change during service. Preferably, the updatable model parameters include, but are not limited to, equivalent stiffness parameters of structural members, equivalent damping parameters of members, equivalent constraint parameters of supports or connections, and equivalent parameters of boundary conditions. Through parameterization, the digital twin model acquires the ability to be adaptively updated based on measured data.

[0037] See Figures 2-6 A variety of sensors are strategically deployed at key points of the bridge structure to construct a multi-source sensing network system covering the entire bridge. These sensors include, but are not limited to, strain gauges, acceleration sensors, displacement sensors, and temperature sensors. The placement of the sensors can be selected based on the bridge structure type, stress characteristics, and vulnerable parts.

[0038] During the service life of the bridge, the aforementioned sensors are used to collect real-time measured structural response data of the bridge structure. This measured structural response data includes at least one or more of the following: strain data, displacement data, acceleration response data, or vibration response data; temperature data can be used as auxiliary information for condition identification or temperature effect compensation.

[0039] The collected measured structural response data is transmitted in real time to a data processing center or host computer system via wired or wireless communication, enabling continuous recording of the bridge structure's operational status. The wireless communication method can employ low-power wireless networking (such as ZigBee), but this invention is not limited to any specific communication protocol.

[0040] S102. Obtain the working conditions corresponding to the measured structural response data, and calculate the predicted structural response of the bridge structure under the working conditions based on the current digital twin model; perform multi-domain feature extraction on the measured structural response data and the predicted structural response respectively to obtain the corresponding measured multi-domain feature quantities and predicted multi-domain feature quantities, and construct the multi-domain fusion response deviation.

[0041] Among them, multi-domain feature extraction involves extracting structural response features from at least two of the time domain, frequency domain, and wavelet domain to obtain the corresponding measured multi-domain feature quantities and predicted multi-domain feature quantities. This response deviation is used to quantify the difference between the digital twin model and the actual bridge structural state.

[0042] At the data processing center, based on the current digital twin model, the predicted structural response of the bridge structure is calculated under the working conditions corresponding to the measured structural response data. This predicted structural response is consistent with the measured structural response in terms of dimensions, measurement point locations, or characteristic dimensions, such as the strain, displacement, and acceleration time histories of the corresponding measurement points, or frequency domain characteristic parameters calculated from the time histories.

[0043] In the process of multi-domain fusion response deviation calculation, the predicted structural response and the measured structural response are first aligned on the time axis or working conditions. Then, the two are compared point by point or at the feature level, and their difference, mean square error or frequency difference is calculated as the response deviation, which is used to quantify the difference between the prediction results of the digital twin model and the actual bridge structural state.

[0044] When constructing the multi-domain fusion response bias, the intra-domain bias between the measured multi-domain feature quantities and the predicted multi-domain feature quantities is calculated separately; the intra-domain biases of each domain are weighted and fused to obtain the multi-domain fusion response bias; wherein, the weight of each domain is dynamically adjusted according to at least one of the current service conditions of the bridge structure, the damage sensitivity calibration results, or the signal-to-noise ratio evaluation results.

[0045] See Figure 7 To improve the stability and comparability of the virtual-real comparison, the measured structural response data is preprocessed and feature extracted before calculating the multi-domain fusion response deviation. This preprocessing includes denoising, filtering, and normalization, while the feature extraction includes time-domain analysis, frequency-domain analysis, or time-frequency analysis. The above signal processing steps enhance the robustness of the multi-domain fusion response deviation calculation and represent a preferred embodiment, but do not constitute a limitation on the core steps of this invention.

[0046] S103. With the goal of reducing the deviation of the multi-domain fusion response, the parameters of the initial digital twin model are adaptively and iteratively corrected using the Bayesian inference method. During the parameter update process, the uncertainty quantification results of the model parameters are output synchronously, and the predicted structural response is recalculated after each correction until the preset convergence condition is met, thereby obtaining the updated digital twin model.

[0047] Using the multi-domain fusion response deviation obtained in the aforementioned steps as the basis for model calibration, the pre-set updatable model parameters are adaptively corrected so that the predicted structural response of the digital twin model gradually approaches the measured structural response, thereby obtaining the updated digital twin model.

[0048] During the parameter update process, the updatable model parameters are iteratively adjusted with the goal of reducing response bias. Specifically, in each round of updates, the predicted structural response is recalculated based on the current parameter combination to obtain a new response bias; when the response bias decreases, the current parameter update result is retained; when the response bias does not decrease, the parameter adjustment magnitude or direction is corrected, and the next round of calculation begins.

[0049] For example, the prior probability distribution of the updatable parameter in the initial digital twin model is combined with the likelihood function constructed based on the multi-domain fusion response bias to calculate the posterior probability distribution of the updatable parameter; the parameter update value for the current round is obtained by sampling from the posterior probability distribution, and the uncertainty quantification result of the updatable parameter is output synchronously according to the statistical characteristics of the posterior probability distribution; the uncertainty quantification result includes at least one of the parameter's posterior variance, confidence interval, or probability density function; the corresponding parameter of the digital twin model is corrected based on the parameter update value, and the predicted structural response and the corresponding multi-domain fusion response bias are recalculated after correction. The likelihood function is updated using the new multi-domain fusion response bias, and the next round of Bayesian inference iteration is entered until the preset convergence condition is met.

[0050] The parameter update process terminates when preset conditions are met. These preset conditions may include: the response deviation is less than a preset threshold, the change in model parameters is less than a preset limit, or the improvement in response deviation in multiple consecutive updates is less than a set value.

[0051] During parameter updates, a physically reasonable range can be set for the updatable parameters to avoid parameter results that do not conform to engineering realities. Parameter updates can be implemented using optimization search or probabilistic updates, but this invention is not limited to any specific algorithm.

[0052] S104. Based on the updated digital twin model, monitor and assess the current health status of the bridge structure.

[0053] After completing the aforementioned steps, the health status of the bridge structure is monitored based on the updated digital twin model. During health monitoring, the updated model parameters or key structural response indicators output by the model are compared with the historical or initial states. When the model parameters show continuous changes or the key structural response indicators exceed the preset range of change, it is determined that the bridge structure status has changed, and this is output as the health status monitoring result.

[0054] Specifically, such as Figure 8 As shown, when the equivalent stiffness parameters, connection parameters, or damping parameters of the components change continuously, or when the key response indicators output by the model under the same working conditions exceed the preset range of change, it can be determined that the bridge structure has changed and output as a health status monitoring result.

[0055] like Figure 9 The diagram of the host computer interface shows that the monitoring results can be displayed graphically, including the comparison results of measured data and predicted data, the trend of response deviation changes, and the update status of model parameters, so that maintenance personnel can intuitively grasp the operating status of the bridge structure.

[0056] Furthermore, to implement the above method, this embodiment can adopt a modular system architecture, such as... Figure 10 As shown, the system includes an acquisition module for obtaining sensor data and design parameters of the measured structural response, a prediction module for calculating and predicting the structural response using a digital twin model, a calculation module for determining the deviation between the measured and predicted structural responses, an update module for iteratively correcting the digital twin model in the prediction module, and a monitoring module for real-time health monitoring using the updated digital twin model. These modules work together to complete the adaptive updating of the digital twin model and the health monitoring of the bridge structure.

[0057] Based on the completion of the core steps described above, the monitoring results can optionally be further analyzed and applied. For example, trend analysis can be performed based on long-term monitoring data, or the monitoring results can be displayed in a hierarchical manner to assist in operation and maintenance management. The above-mentioned extended analysis methods are one form of application of monitoring results and do not constitute a limitation on the core technical solution of this invention.

[0058] Compared with existing technologies, this invention drives the continuous updating of the digital twin model through measured structural response data, enabling the digital twin model to dynamically reflect the real state changes of the bridge structure, avoiding the gradual distortion of the model during long-term service, thereby improving the reliability and consistency of bridge structural health monitoring results.

[0059] The present invention provides a bridge structural health monitoring method based on adaptive updating of digital twin models, which is applicable to the operational status monitoring and structural health management of various types of bridge structures, including but not limited to highway bridges, railway bridges, and municipal bridges.

[0060] In practical applications, structural response monitoring devices are deployed at key locations of the bridge structure to collect measured structural response data during the bridge's service life. This data is then transmitted to a data processing system. The data processing system continuously updates the digital twin model of the bridge structure based on the measured structural response data and monitors the health status of the bridge structure based on the updated digital twin model.

[0061] The method of this invention can adapt to the application needs of bridges under different operating conditions and environmental conditions, such as during the flood season, heavy traffic, high temperature or low temperature, and can continuously monitor changes in the structural state of bridges. It is suitable for status tracking and operation management during the long-term service of bridges.

[0062] Based on the application of this invention, the adaptive updating of the digital twin model can be driven by measured structural response data, enabling the digital twin model to continuously reflect the actual state changes of the bridge structure and preventing the model from gradually becoming distorted over time. Establishing bridge structural health monitoring based on the updated digital twin model improves the stability and consistency of state judgments based on model output results. This method does not rely on specific communication protocols or hardware implementations, and can be flexibly deployed according to different bridge structural forms and site conditions, making it suitable for various bridge types and complex operating environments. The method has a clear flow, and the model parameter updating and monitoring process can be modularly implemented, facilitating integration with existing bridge monitoring systems and demonstrating good engineering feasibility. By continuously updating the digital twin model, long-term tracking of bridge structural state changes can be achieved, meeting the health status monitoring needs throughout the entire service life of bridges.

[0063] Secondly, the present invention also provides a bridge structure monitoring device, such as... Figure 11 As shown, it includes: The acquisition module 201 is used to establish a parameterized initial digital twin model based on the design parameters and initial state of the bridge structure; and to acquire the measured structural response data of the bridge structure under actual working conditions during the bridge's service life.

[0064] The prediction module 202 is used to obtain the working conditions corresponding to the measured structural response data, and calculate the predicted structural response of the bridge structure under the working conditions based on the current digital twin model.

[0065] The calculation module 203 is used to perform multi-domain feature extraction on the measured structural response data and the predicted structural response, respectively, extracting structural response features from at least two domains of time domain, frequency domain and wavelet domain, to obtain the corresponding measured multi-domain feature quantities and predicted multi-domain feature quantities; comparing and analyzing the predicted multi-domain feature quantities and the measured multi-domain feature quantities to construct a multi-domain fusion response deviation, which is used to quantify the difference between the digital twin model and the actual bridge structural state from multiple physical dimensions.

[0066] The update module 205 is used to adaptively and iteratively correct the parameters of the initial digital twin model using a Bayesian inference method with the goal of reducing the multi-domain fusion response deviation. During the parameter update process, the uncertainty quantification result of the model parameters is output synchronously, and the predicted structural response is recalculated after each correction until the preset convergence condition is met, thereby obtaining the updated digital twin model.

[0067] The monitoring module 206 is used to monitor and evaluate the current health status of the bridge structure based on the updated digital twin model.

[0068] The present invention also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The steps of the provided bridge structure monitoring method.

[0069] This invention also provides a computer device. At the hardware level, the computer device includes a processor, an internal bus, a network interface, memory, and non-volatile memory, and may also include other hardware required for various operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it to achieve the above-mentioned functions. Figure 1 The steps of the provided bridge structure monitoring method.

[0070] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0072] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0074] It should be noted that the specific embodiments described above enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the patent of the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for monitoring bridge structures, characterized in that, The method includes: Based on the design parameters and initial state of the bridge structure, a parameterized initial digital twin model is established; during the service of the bridge, the measured structural response data of the bridge structure under actual working conditions are obtained. Obtain the working conditions corresponding to the measured structural response data, and calculate the predicted structural response of the bridge structure under these working conditions based on the current digital twin model; Multi-domain feature extraction is performed on the measured structural response data and the predicted structural response, respectively. Structural response features are extracted from at least two domains, namely the time domain, frequency domain and wavelet domain, to obtain the corresponding measured multi-domain feature quantities and predicted multi-domain feature quantities. The predicted multi-domain feature quantities are compared and analyzed with the measured multi-domain feature quantities to construct a multi-domain fusion response deviation. The multi-domain fusion response deviation is used to quantify the difference between the digital twin model and the actual bridge structure state from multiple physical dimensions. With the goal of reducing the multi-domain fusion response bias, the parameters of the initial digital twin model are adaptively and iteratively corrected using the Bayesian inference method. During the parameter update process, the uncertainty quantification results of the model parameters are output synchronously, and the predicted structural response is recalculated after each correction until the preset convergence condition is met, thereby obtaining the updated digital twin model. Based on the updated digital twin model, the current health status of the bridge structure is monitored and evaluated.

2. The method according to claim 1, characterized in that, The measured structural response data includes one or more of the following: strain data, displacement data, and acceleration response data.

3. The method according to claim 1, characterized in that, The constructed multi-domain fusion response bias includes: Calculate the intra-domain deviations between the measured multi-domain feature quantities and the predicted multi-domain feature quantities respectively; The intra-domain deviations of each domain are weighted and fused to obtain the multi-domain fused response deviation; wherein, the weight of each domain is dynamically adjusted according to at least one of the current service conditions of the bridge structure, the damage sensitivity calibration results, or the signal-to-noise ratio evaluation results.

4. The method according to claim 3, characterized in that, Before calculating the response deviation, the measured structural response data is preprocessed, including denoising, filtering, and normalization.

5. The method according to claim 1, characterized in that, The parameters updated in the initial digital twin model include one or more of the following: equivalent stiffness parameters of structural members, equivalent damping parameters, equivalent constraint parameters of connection parts, and equivalent parameters of boundary conditions.

6. The method according to claim 1, characterized in that, The method of adaptively iteratively correcting the parameters of the initial digital twin model using Bayesian inference, synchronously outputting the uncertainty quantification results of the model parameters during the parameter update process, and recalculating the predicted structural response after each correction until the preset convergence condition is met includes: The prior probability distribution of the updatable parameters in the initial digital twin model is combined with the likelihood function constructed based on the multi-domain fusion response bias to calculate the posterior probability distribution of the updatable parameters. The parameter update value for the current round is obtained by sampling from the posterior probability distribution, and the uncertainty quantification result of the updatable parameter is output synchronously according to the statistical characteristics of the posterior probability distribution; the uncertainty quantification result includes at least one of the parameter's posterior variance, confidence interval, or probability density function. Based on the parameter update value, the corresponding parameters of the digital twin model are corrected, and the predicted structural response and the corresponding multi-domain fusion response deviation are recalculated after correction. The likelihood function is updated using the new multi-domain fusion response deviation, and the next round of Bayesian inference iteration is entered until the preset convergence condition is met.

7. The method according to claim 1, characterized in that, The monitoring and assessment of the current health status of the bridge structure based on the updated digital twin model includes: The updated model parameters or key structural response indicators output by the model are compared with the historical state or the initial state. When the model parameters change continuously or the key structural response indicators exceed the preset change range, it is determined that the bridge structure state has changed and is output as a health status monitoring result.

8. A bridge structure monitoring device, characterized in that, The device includes: The acquisition module is used to establish a parameterized initial digital twin model based on the design parameters and initial state of the bridge structure; and to acquire measured structural response data of the bridge structure under actual working conditions during the bridge's service life. The prediction module is used to obtain the working conditions corresponding to the measured structural response data, and calculate the predicted structural response of the bridge structure under the working conditions based on the current digital twin model. The calculation module is used to perform multi-domain feature extraction on the measured structural response data and the predicted structural response, respectively, extracting structural response features from at least two domains including the time domain, frequency domain, and wavelet domain, to obtain the corresponding measured multi-domain feature quantities and predicted multi-domain feature quantities; comparing and analyzing the predicted multi-domain feature quantities with the measured multi-domain feature quantities to construct a multi-domain fusion response deviation, which is used to quantify the difference between the digital twin model and the actual bridge structural state from multiple physical dimensions. The update module is used to adaptively and iteratively correct the parameters of the initial digital twin model with the goal of reducing the multi-domain fusion response deviation. During the parameter update process, the uncertainty quantification results of the model parameters are output synchronously, and the predicted structural response is recalculated after each correction until the preset convergence condition is met, thereby obtaining the updated digital twin model. The monitoring module is used to monitor and assess the current health status of the bridge structure based on the updated digital twin model.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 7.

10. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any one of claims 1 to 7.

Images