A bridge detection method and system based on digital twin technology

Abstract

The application discloses a bridge detection method and system based on digital twin technology, and relates to the field of bridge structure health monitoring.The method comprises the following steps: collecting strain distribution values, vibration frequency spectrum values and environmental load spectrum values in real time through a sensor network deployed on a physical bridge, generating a structure response data set and synchronizing the structure response data set to a digital twin; calculating damage index values and cumulative damage amount values based on the structure response data set; inputting the damage index values and the cumulative damage amount values into a preset safety criterion, calculating safety margin coefficient values and failure risk level values; calculating residual life prediction values based on the safety margin coefficient values and the environmental load spectrum values, and synchronously correcting degradation rate values of the digital twin; generating priority maintenance instructions according to the failure risk level values, the residual life prediction values and the safety margin coefficient values, and feeding back maintenance effect data to the digital twin for updating after execution.The application significantly improves the bridge operation and maintenance efficiency and safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge structure health monitoring, and in particular to a bridge detection method and system based on digital twin technology. BACKGROUND

[0002] Current bridge structure health monitoring mainly relies on periodic manual inspection and offline sensor data analysis, which has significant limitations.

[0003] Manual inspection is highly subjective and has a long cycle, making it difficult to capture sudden damage; traditional vibration detection methods are easily disturbed by environmental noise and have insufficient accuracy in identifying early damage such as micro-cracks; visual detection technology cannot quantify the degree of internal structural degradation.

[0004] Existing digital twin applications are mostly focused on the design stage, and there are three major defects in the operation and maintenance link: first, multi-source data is processed in isolation, lacking dynamic correlation analysis; second, the degradation model relies on static empirical formulas and does not combine real-time state correction parameters; third, maintenance decisions are disconnected from the twin model, forming a "monitoring-evaluation-maintenance" closed loop fracture. This leads to problems such as delayed bridge safety hazard early warning, large life prediction deviation, and unreasonable allocation of maintenance resources, and an intelligent detection system that integrates real-time data-driven, model self-optimization, and decision feedback is urgently needed. SUMMARY

[0005] The present application proposes a bridge detection method based on digital twin technology, comprising:

[0006] Real-time acquisition of strain distribution values, vibration frequency spectrum values, and environmental load spectrum values through a sensor network deployed on the physical bridge, generation of structure response data sets, and synchronization to the digital twin body;

[0007] Based on the structure response data set of the digital twin body, calculate the damage index value and the cumulative damage amount value;

[0008] Input the damage index value and the cumulative damage amount value into the preset safety criterion, calculate the safety margin coefficient value and the failure risk level value;

[0009] Based on the safety margin coefficient value and the environmental load spectrum value, calculate the remaining life prediction value, and synchronize the degradation rate value of the digital twin body;

[0010] Generate a priority maintenance instruction according to the failure risk level value, the remaining life prediction value, and the safety margin coefficient value, and after execution, feedback the maintenance effect data to the digital twin body for updating.

[0011] The bridge detection method based on the digital twin technology, wherein the strain distribution value, the vibration frequency spectrum value and the environmental load spectrum value are collected in real time by the sensor network deployed on the physical bridge, a structure response dataset is generated and synchronized to the digital twin, and the method comprises the following sub-steps:

[0012] The three-dimensional strain distribution values of the main girder web plate, the pier cap and the cable tower anchorage zone are collected by a high-density optical fiber strain sensor array, and a stress field cloud map is constructed.

[0013] The structure vibration response is monitored in real time by using a distributed accelerometer network, and the vibration frequency spectrum characteristic values such as the fundamental frequency and the damping ratio are extracted by using fast Fourier transform.

[0014] The monitoring data of the integrated temperature and humidity sensor, the anemometer and the dynamic weighing system are collected, and a multi-dimensional environmental load spectrum value including the temperature gradient, the wind load spectrum and the traffic load time history is generated.

[0015] The spatio-temporal data registration is performed by using an edge computing gateway, a structure response dataset with a spatio-temporal label is formed, and the structure response dataset is synchronized to the digital twin.

[0016] The bridge detection method based on the digital twin technology, wherein the damage index value and the cumulative damage value are calculated based on the structure response dataset of the digital twin, and the method comprises the following sub-steps:

[0017] The local micro-strain field model is established according to the strain distribution value, the fatigue damage index value of the key component is calculated by combining the material S-N curve and the Miner linear cumulative damage criterion, and the cumulative damage value of the structure stiffness degradation is quantified by using a frequency domain decomposition algorithm.

[0018] The cumulative damage value of the structure stiffness degradation is quantified by using a frequency domain decomposition algorithm.

[0019] The historical detection data and the real-time response are associated, the cumulative damage value is dynamically updated by using a time series prediction model, and a full life cycle degradation curve is generated.

[0020] The bridge detection method based on the digital twin technology, wherein the historical detection data and the real-time response are associated, the cumulative damage value is dynamically updated by using a time series prediction model, and a full life cycle degradation curve is generated, and the method comprises the following sub-steps:

[0021] The strain distribution peak value sequence and the vibration fundamental frequency attenuation data stored in the digital twin over the years are extracted.

[0022] The cumulative damage value considering the material aging effect is reconstructed by using a long short-term memory network to fuse the real-time monitoring value and the historical database.

[0023] The statistical significance of the cumulative damage value is verified based on a Bayesian updating mechanism, and the exponential degradation parameter in the fatigue damage model is dynamically calibrated.

[0024] The bridge detection method based on the digital twin technology as described above, wherein the damage index value and the cumulative damage value are input into a preset safety criterion, and a safety margin coefficient value and a failure risk level value are calculated, including the following sub-steps:

[0025] According to the spatial distribution of the damage index value, the safety margin coefficient value of each region is calculated by matching the preset material strength threshold matrix.

[0026] Combined with the spatio-temporal evolution characteristics of the cumulative damage value, a fuzzy comprehensive evaluation model is used to generate a five-level failure risk level value from low to high.

[0027] The coverage completeness of the risk level determination logic is verified by Monte Carlo simulation to exclude the risk of missed judgment.

[0028] The bridge detection method based on the digital twin technology as described above, wherein, based on the safety margin coefficient value and the environmental load spectrum value, the remaining life prediction value is calculated, and the degradation rate value of the digital twin is simultaneously corrected, including the following sub-steps:

[0029] Coupling the extreme working condition distribution of the environmental load spectrum value and the safety margin coefficient decay curve, the Paris crack propagation law is used to predict the remaining life prediction value.

[0030] According to the remaining life prediction result, the time-varying degradation rate value of the digital twin is optimized in reverse, and a material performance degradation adaptive calibration mechanism is established.

[0031] Through cross verification of the twin and the physical entity, the prediction accuracy of the degradation model is ensured to be controlled within a ±5% error band.

[0032] The bridge detection method based on the digital twin technology as described above, wherein, according to the failure risk level value, the remaining life prediction value and the safety margin coefficient value, a priority maintenance instruction is generated, and after execution, the maintenance effect data is fed back to the digital twin for updating, including the following sub-steps:

[0033] Based on the spatial thermal map of the failure risk level value, high-risk areas requiring emergency treatment and observation monitoring areas are divided.

[0034] Combined with the critical value of the remaining life prediction, an intelligent maintenance instruction set containing construction timing and resource allocation is generated.

[0035] Through the Internet of Things terminal, the change data of the structural dynamic characteristics after maintenance is collected and fed back to the digital twin to verify the effectiveness of the damage model correction.

[0036] The application further provides a bridge detection system based on the digital twin technology, comprising:

[0037] A data acquisition and synchronization module: a sensor network deployed on the physical bridge is used to acquire strain distribution values, vibration frequency spectrum values and environmental load spectrum values in real time, generate a structure response data set and synchronize the structure response data set to the digital twin;

[0038] A structure health assessment module: based on the structure response data set of the digital twin, damage index values and cumulative damage amount values are calculated;

[0039] A life prediction and state calibration module: the damage index values and the cumulative damage amount values are input into a preset safety criterion, a safety margin coefficient value and a failure risk level value are calculated, based on the safety margin coefficient value and the environmental load spectrum value, a residual life prediction value is calculated, and the degradation rate value of the digital twin is corrected synchronously;

[0040] A maintenance decision and closed-loop feedback module: a priority maintenance instruction is generated according to the failure risk level value, the residual life prediction value and the safety margin coefficient value, and after the execution, maintenance effect data is fed back to the digital twin for updating.

[0041] The application further provides a computer storage medium, comprising: at least one memory and at least one processor;

[0042] The memory is used to store one or more program instructions;

[0043] The processor is used to run the one or more program instructions to execute the bridge detection method based on the digital twin technology.

[0044] The application has the following beneficial effects:

[0045] The strain distribution values, the vibration frequency spectrum values and the environmental load spectrum values acquired in real time are used to construct a high-fidelity digital twin, which significantly improves the structure state perception accuracy; the damage index values and the cumulative damage amount values are calculated based on the multi-source data cooperation, which accurately identifies hidden damages such as microscopic crack propagation and stiffness degradation; the safety margin coefficient value and the failure risk level value are dynamically generated in combination with the preset safety criterion, which realizes the transition from passive detection to active warning; the residual life is predicted through the coupling analysis of the environmental load spectrum value and the safety margin, and the degradation model of the digital twin is corrected in real time, which greatly improves the life evaluation reliability; the priority maintenance instruction generated according to the risk level, the life prediction and the safety margin is used to optimize the resource allocation and verify the maintenance effect, forming a "monitoring-evaluation-decision-verification" closed loop, effectively prolonging the service life of the bridge, reducing the risk of sudden accidents, and providing core support for intelligent management and maintenance of infrastructure. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0047] Figure 1 is a bridge detection method flowchart based on digital twin technology provided by the embodiment of the present application.

[0048] Figure 2 is a bridge detection system schematic diagram based on digital twin technology provided by the embodiment of the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0050] Embodiment one

[0051] As shown in Figure 1 , the bridge detection method based on digital twin technology provided by the embodiment of the present application comprises:

[0052] Step S1, real-time collection of strain distribution values, vibration frequency spectrum values and environmental load spectrum values through a sensor network deployed on a physical bridge, generation of structure response data set and synchronization to a digital twin;

[0053] Specifically, real-time acquisition of three-dimensional deformation data of key parts of the bridge by using a high-density optical fiber sensing array to generate a dynamic stress field cloud map; capture of structure vibration signals by a deployed acceleration sensor network, analysis of fundamental frequency and damping characteristics through frequency spectrum analysis; synchronous fusion of temperature gradient, wind load and traffic load time series data obtained by an environmental monitoring device; realization of spatio-temporal calibration of multi-source information by means of an edge computing node, construction of a structure response set with unified spatio-temporal markers and real-time updating of the digital twin, specifically comprising the following sub-steps:

[0054] Step S11, collection of three-dimensional strain distribution values of the main girder web plate, pier cap and cable tower anchorage zone of the bridge by a high-density optical fiber strain sensor array, construction of a stress field cloud map;

[0055] High-density fiber optic strain sensor arrays are deployed in the key stress areas of the bridge. The array continuously collects three-dimensional strain components on the surface or inside the structure with a preset spatial resolution. The original optical signals collected are converted into digital strain data by the demodulation device, and a refined stress field distribution cloud map covering the monitoring area is generated using spatial interpolation algorithms, which intuitively reflects the stress level and gradient changes of the structure under load.

[0056] Step S12, real-time monitoring of structural vibration response by distributed accelerometer network, extracting fundamental frequency, damping ratio and other vibration spectrum characteristic values by fast Fourier transform;

[0057] A distributed accelerometer network is arranged at the sensitive positions of each key mode of the bridge structure. The accelerometers record the vibration acceleration time history data of the structure under environmental excitation or traffic load at a high sampling rate. After preprocessing the original acceleration signals, the fast Fourier transform algorithm is applied to convert them to the frequency domain, and the main vibration fundamental frequency, high-order harmonic frequency, and modal damping ratio calculated based on the half-power bandwidth method or random subspace identification method are accurately analyzed to evaluate the overall dynamic characteristics and health status of the structure.

[0058] Step S13, integrating the monitoring data of temperature and humidity sensors, anemometers and dynamic weighing systems to generate multi-dimensional environmental load spectrum values including temperature gradient, wind load spectrum and traffic load time history;

[0059] Multiple types of environmental and load sensors are integrated at key locations on and around the bridge. A network of temperature and humidity sensors is arranged at different cross-sections of the bridge structure to measure the temperature gradient distribution and environmental humidity inside the structure. The temperature gradient field is calculated using the following formula:

[0060] where, represents the influence of the mass properties of the material itself on temperature changes during heat transfer; represents the specific heat capacity at constant pressure; represents the partial derivative of temperature with respect to time; represents the heat conduction term, represents the gradient operator; represents the temperature gradient; represents the thermal conductivity, reflecting the ability of the material to conduct heat; represents the solar radiation flux; represents the convective heat transfer coefficient; represents the temperature of the object under study; represents the far-field temperature of the environment; represents the emissivity, which describes the ability of the object's surface to emit radiant energy, with a value between 0 and 1, reflecting the degree to which the object approaches black body radiation; It is used to calculate the heat transfer of thermal radiation and is a key constant in the blackbody radiation law; represents the effective radiation temperature of the sky;

[0061] Anemometers are installed at unobstructed locations above the bridge deck and on the tops of cable towers to capture the wind speed, direction, and spectrum characteristics acting on the structure in real time. The wind load spectrum is expressed using the following formula:

[0062]

[0063] in, represents the power spectrum density of fluctuating wind; Indicates frequency; It represents an empirical constant, which is related to factors such as site and topography and is used to fit the actual wind spectrum characteristics; represents the friction speed; represents the characteristic frequency; represents the coefficient related to the wind profile characteristics; Indicates height Average wind speed at Indicates the height of the calculated wind load position relative to the ground; represents the experience correction coefficient; represents the phase perturbation function.

[0064] The dynamic weighing system is embedded in a specific lane of the bridge deck pavement layer to record the axle weight, wheelbase, speed and traffic density of passing vehicles, generating accurate traffic load time history data. The following formula is used to represent the random process of traffic load:

[0065]

[0066] in, Represents the traffic load random process at time Response; Indicates the deadline Total number of arriving load events; Indicates the sequence number of the load event; Indicates the The amplitude of each load event; Indicates the The arrival time of each load event; Indicates: Velocity parameters associated with each load event; Indicates the Other characteristic parameters of each load event; Indicates the The time history function of each load event.

[0067] After the above monitoring data is synchronously collected, a multi-dimensional environmental load spectrum value data set containing a spatial temperature field, a wind load time-frequency characteristic and a traffic load time history is integrated.

[0068] In step S14, the edge computing gateway is used for spatio-temporal data registration, a structure response data set with a spatio-temporal label is formed, and the structure response data set is synchronized to the digital twin;

[0069] The original data stream from the above various sensors is received, a high-precision timing module is used to realize strict time synchronization of all data channels, and the time consistency of the data is ensured. At the same time, according to the accurate spatial coordinates of the sensors on the physical bridge, each data point is given a corresponding spatial position label. The built-in preprocessing module of the gateway performs preliminary checking, format unification and invalid data elimination on the original data. After spatio-temporal registration, the multi-source heterogeneous data is packaged to form a structure response data set with a spatio-temporal label. The data set is transmitted in real time or quasi-real time through a high-speed communication link and is synchronized to the digital twin platform located in the remote server.

[0070] In step S2, based on the structure response data set of the digital twin, damage index values and cumulative damage values are calculated.

[0071] Specifically, the real-time damage index of the core component is calculated based on the local deformation field model combined with the material fatigue characteristics; the structural stiffness degradation is analyzed by using the frequency characteristic offset, and the cumulative damage value is quantified by using the frequency domain algorithm; the dynamic damage accumulation under the material aging effect is reconstructed by synchronously fusing the historical detection data and relying on the time series prediction model; finally, the statistical reliability of the damage value is checked by using the Bayesian mechanism, the fatigue degradation parameters are optimized in real time, and the performance evolution curve in the whole life cycle is generated, which includes the following sub-steps:

[0072] In step S21, a local micro-strain field model is established according to the strain distribution value, the fatigue damage index value of the key component is calculated by combining the material S-N curve and the Miner linear cumulative damage criterion;

[0073] The measurement value of the high-density strain sensor of the specified key component is extracted from the structure response data set updated in real time by the digital twin. Based on the spatial interpolation algorithm, a local micro-strain field distribution map reflecting the surface or internal key path of the component is constructed. According to the standardized S-N fatigue characteristic curve of the component material, the fatigue life cycle number corresponding to different stress amplitudes is determined, the stress time history data obtained in real time and processed by the rainflow counting method is decomposed into stress cycle blocks of different amplitudes. The damage ratio caused by each stress cycle block is calculated by using the formula:

[0074] Multi-axial stress correction formula:

[0075]

[0076] in, The average stress and stress gradient are corrected. The equivalent stress amplitude of each stress state; represents the stress amplitude; represents the mean stress; Indicates ultimate tensile strength; represents the multiaxial correction index; represents the gradient sensitivity coefficient; Represents the Frobenius norm of the strain gradient tensor, which is used to measure the magnitude of the strain gradient;

[0077] Nonlinear SN curve equation:

[0078]

[0079] in, Indicates the Fatigue life under a stress state; represents the Basquin parameter, represents the fatigue strength coefficient; represents the fatigue strength index; Indicates the equivalent stress amplitude; represents the fatigue limit; represents the curvature correction parameter; represents the Laplacian norm of the strain gradient tensor; Indicates the reference strain value.

[0080] Damage ratio calculation formula:

[0081]

[0082] in, Indicates the The damage ratio corresponding to each stress cycle block; Indicates the number of cycles of this stress cycle block; Indicates the fatigue life under the corresponding stress state; represents the strain gradient tensor The Frobenius norm of Represents the strain gradient tensor, the elements contain strain components Coordinates ; represents the damage activation function; Indicates the equivalent stress amplitude; represents the fatigue limit;

[0083] The real-time fatigue damage index value of the key component in the current monitoring period is obtained by accumulating block by block.

[0084] Step S22, based on the modal parameter offset of the vibration spectrum value, the cumulative damage value of the structure stiffness degradation is quantified by the frequency domain decomposition algorithm;

[0085] The high-precision frequency domain decomposition algorithm is used for modal parameter identification of the vibration signal to obtain the main modal frequency, damping ratio and mode shape of the structure in the current state. The identified current modal frequency value is compared with the corresponding modal frequency value stored in the digital twin benchmark model, and the relative offset is calculated. Combined with the analysis of the mechanical properties of the structure, a quantitative mapping relationship between the modal frequency offset and the overall or local structure stiffness degradation is established. The identified multi-order modal frequency offset is comprehensively converted into the cumulative damage value reflecting the overall or key subsystem stiffness degradation of the structure.

[0086] Step S23, associate historical detection data with real-time response, use time series prediction model to dynamically update cumulative damage value and generate full life cycle degradation curve;

[0087] Step S231, extract the strain distribution peak value sequence and vibration fundamental frequency attenuation data stored in the digital twin for many years;

[0088] From the long-term historical database integrated by the digital twin, the typical strain distribution peak data sequence of the specified key component in the important detection or specific event record of each year is extracted in time sequence. At the same time, the vibration fundamental frequency measurement value sequence of the first order or main order of the overall structure at the corresponding time node is extracted to form the attenuation data chain reflecting the change of the fundamental frequency with time.

[0089] Step S232, fuse real-time monitoring value and historical database through long short-term memory network to reconstruct the cumulative damage value considering material aging effect;

[0090] The obtained current real-time key component damage index value and current structure cumulative damage value are spatio-temporally aligned and fused with the corresponding historical data sequence. A damage evolution analysis mechanism that integrates historical trends and real-time state information is established by applying a time series analysis algorithm with long-term dependence relationship capture capability. Through algorithm processing, the cumulative damage prediction value of the key component and the overall structure under the material aging background is dynamically reconstructed and updated, which is more consistent with the actual long-term evolution law.

[0091] Step S233, verify the statistical significance of the cumulative damage value based on the Bayesian updating mechanism, and dynamically calibrate the exponential degradation parameters in the fatigue damage model;

[0092] The cumulative damage prediction value of the fusion aging effect is compared with the prediction results of the physical-based fatigue damage model and the stiffness degradation model using the Bayesian statistical inference framework. The previous fusion prediction value is taken as new observation evidence, and the Bayesian updating mechanism is used to calculate the posterior probability distribution of the model prediction, to evaluate the statistical significance and uncertainty level of the current model prediction result. According to the posterior analysis result, the key time-varying parameters in the fatigue damage model and the stiffness degradation model are dynamically calibrated and optimized. The calibrated parameters are fed back to the core calculation model of the digital twin in real time, ensuring that the model continuously reflects the true degradation state of the structure. Finally, based on the continuously updated model and the fusion data, the key performance evolution curve reflecting the bridge structure from construction to the future is generated and output.

[0093] Step S3, input the damage index value and the cumulative damage value into the preset safety criterion to calculate the safety margin coefficient value and the failure risk level value;

[0094] Specifically, the cutting resistance deviation is calculated by real-time analyzing the frequency spectrum characteristics of the acoustic wave signal and the strain mutation point, and the kinetic energy compensation value is derived according to the preset mapping relationship, and then the driving torque and the feed rate are dynamically adjusted, which specifically includes the following sub-steps:

[0095] Step S31, according to the spatial distribution of the damage index value, match the preset material strength threshold matrix to calculate the safety margin coefficient value of each region;

[0096] The system generates a distribution map of the damage index value in the three-dimensional space of the bridge structure based on the sensor network collected data, and aligns and compares it with the pre-defined material strength threshold matrix. The spatial interpolation algorithm is used to map the discrete damage index to the continuous threshold matrix grid. For each evaluation unit, the safety margin coefficient value reflecting the remaining degree of the structure's carrying capacity in the region is calculated by using the ratio of the damage index value to the corresponding position material strength threshold, combined with the weighted algorithm considering the local stress concentration effect and damage coupling effect. The final calculation of the safety margin coefficient is represented by the following formula:

[0097]

[0098] Wherein, represents the final safety margin coefficient to be calculated; represents the fatigue limit of ; represents the damage related function; represents the numerical stability term; represents a certain correction or regulation function related to ; represents the minimum stress reference value; denotes a scale parameter for defining a stress difference range; denotes a term in exponential function form for considering the influence of damage gradient on safety margin.

[0099] Step S32, combined with the spatio-temporal evolution characteristics of the cumulative damage value, a fuzzy comprehensive evaluation model is used to generate a five-level failure risk grade value from low to high;

[0100] Based on these spatio-temporal evolution characteristics, the system applies a fuzzy logic evaluation system, taking the cumulative damage value and its change rate, spatial distribution width and other key indicators as input variables. Through the fuzzy reasoning process, the contribution weight of each input variable to the overall failure probability is comprehensively considered. The system de-fuzzifies the fuzzy output result, and finally maps it to five discrete grade values from "extremely low risk" to "extremely high risk", which intuitively quantifies the potential failure probability of the bridge key component or the overall structure under the expected service condition.

[0101] Step S33, verify the coverage completeness of the risk grade determination logic by Monte Carlo simulation to exclude the risk of missing judgment;

[0102] A parameterized probability model is constructed, which covers the randomness of material performance, the uncertainty of load action, the error of detection data and the variability of boundary conditions. According to this model, within the framework of risk grade determination logic, large-scale random sampling simulation calculation is carried out to simulate the response of the bridge under various possible working condition combinations and the corresponding risk grade output. Through statistical analysis of a large number of simulation results, the system focuses on whether the high-risk scenarios such as critical damage state and rare load events can be accurately identified and classified into the corresponding high-risk grade, especially the ability of the determination logic to distinguish the potential "gray area" or complex coupled damage mode.

[0103] Step S4, based on the safety margin coefficient value and the environmental load spectrum value, calculate the remaining life prediction value, and simultaneously correct the degradation rate value of the digital twin;

[0104] Specifically, based on the safety margin coefficient value and the environmental load spectrum value, the remaining life prediction value is calculated, and the degradation rate value of the digital twin is corrected simultaneously. Specifically: coupling the extreme working condition of the environmental load spectrum and the safety margin attenuation curve, the remaining life is calculated based on the Paris law; the twin material degradation rate parameters are optimized in the reverse direction according to the prediction value deviation; and the prediction accuracy is controlled within ± 5% through cross verification of the twin prediction and the entity monitoring data, and the calibration is triggered if it exceeds, which includes the following sub-steps:

[0105] Step S41, coupling the extreme working condition distribution of the environmental load spectrum value and the safety margin coefficient attenuation curve, predicting the remaining life prediction value based on the Paris crack propagation law;

[0106] The load distribution characteristics representing extreme service conditions in the environmental load spectrum are identified, and they are coupled with the decay curve of the safety margin coefficient of the structure key position obtained in real time monitoring. According to the structure damage evolution law described by the Paris crack propagation theory, the current crack size, material fracture toughness, and the coupled load-resistance interaction characteristics are comprehensively considered to construct the residual life prediction equation, which is expressed by the following formula:

[0107]

[0108] wherein, represents the residual life; represents the initial crack length; represents the critical crack length; represents the small increment of crack propagation; represents the material constant; represents the effective stress intensity factor range; represents the geometric factor for correcting the stress intensity factor; represents the crack propagation rate sensitivity index of the material; represents the coefficient related to the material and the environment; represents the rate quantity varying with the crack length, such as the sliding displacement rate, in the crack propagation process; represents the time representation of the residual life; represents the equivalent cyclic frequency; represents the time period for calculating the statistical or equivalent cyclic frequency, which is a time interval for integral calculation; represents the quantity related to the load history; represents the rate of change thereof over time.

[0109] By solving the equation, the residual service life prediction value of the structure key position under the expected service environment is calculated.

[0110] Step S42, the time-varying degradation rate value of the digital twin is optimized reversely according to the residual life prediction result, and a material performance degradation adaptive calibration mechanism is established;

[0111] The calculated residual life prediction value is compared and analyzed with the current simulation predicted residual life value of the digital twin. Based on the prediction deviation, the possible error of the time-varying rate parameter of the simulated material performance degradation in the digital twin is deduced reversely. Using the deviation information, a correction factor for the material performance degradation rate parameter in the digital twin is dynamically generated. By applying the correction factor to the degradation rate parameter of the digital twin, the online and adaptive calibration of the material performance degradation process in the digital twin is realized, and it is ensured that the degradation trajectory simulated by the digital twin is consistent with the degradation trend revealed by the actual monitoring.

[0112] Step S43, cross-validation of the twin and the physical entity ensures that the degradation model prediction accuracy is controlled within a ±5% error band;

[0113] A normalization cross-validation mechanism is established between the digital twin prediction data and the physical bridge entity measured data. The key response or derived indicators simulated by the twin based on the current degradation model and load input are compared quantitatively with the actual sensor monitoring data at the corresponding position and time. Statistical process control method is used to continuously monitor the relative error between the predicted value and the measured value. Once the error exceeds the preset ±5% allowable error band, the degradation rate reverse optimization calibration process in step S42 is automatically triggered to iteratively correct the twin parameters. Through this closed-loop feedback mechanism, the prediction accuracy of the digital twin for the bridge structure material performance degradation process simulation is continuously improved and maintained within the engineering acceptable range.

[0114] Step S5, generate priority maintenance instructions according to the failure risk level value, residual life prediction value and safety margin coefficient value, and feedback the maintenance effect data to the digital twin for updating after execution;

[0115] Specifically, based on the failure risk thermal map, high-risk and monitoring areas are divided; maintenance instruction set is generated by combining risk level, residual life and safety margin; dynamic parameters are collected through Internet of Things after maintenance, and feedback to digital twin to verify the effect and update the state, including the following sub-steps:

[0116] Step S51, based on the spatial thermal map of failure risk level value, divide the high-risk area that needs emergency disposal and the observation monitoring area;

[0117] According to the spatial distribution thermal map of bridge structure failure risk level generated by the digital twin, identify the continuous color block area and its spatial boundary representing the extremely high risk level in the thermal map. By analyzing the color gradient change of the thermal map, set the risk level threshold, automatically delineate the area beyond the threshold as the high-risk area, and mark it as the priority area that needs immediate reinforcement or repair engineering intervention measures. At the same time, identify the area with medium risk level and relatively discrete spatial distribution, and mark it as the observation monitoring area, which needs to strengthen regular inspection and monitoring frequency, but does not need immediate engineering intervention. The division result is superimposed on the bridge digital twin model in the form of a visual layer.

[0118] Step S52, generate intelligent maintenance instruction set containing construction sequence and resource allocation in combination with residual life prediction critical value;

[0119] For the high-risk area divided out, the corresponding residual life prediction value is extracted. The safety threshold of residual life is set, and the components or parts with residual life prediction value lower than the threshold in the high-risk area are determined as emergency treatment items. According to the failure risk grade value, the residual life prediction value and the safety margin coefficient value, a comprehensive sequence is generated, and a maintenance priority sequence is automatically generated. Based on the sequence, combined with the availability of engineering resources, construction process requirements and traffic influence factors, an optimization algorithm is used to generate a detailed construction timing plan and resource allocation scheme, and finally a structured and executable intelligent maintenance instruction set is output to guide the on-site maintenance operation.

[0120] Step S53, collect the structural dynamic characteristic change data after maintenance through the Internet of Things terminal, and feed back to the digital twin to verify the correction effectiveness of the damage model;

[0121] After the execution of the maintenance instruction set is completed, the structural dynamic response data of the bridge under the action of the operating load is collected in real time through the Internet of Things sensor network deployed at the key parts of the bridge. The natural frequency, modal shape, damping ratio and other core dynamic characteristic parameters of the structure after maintenance are collected and calculated. The collected dynamic characteristic data set after maintenance is transmitted to the digital twin platform through a safe communication link. The measured data received is compared and analyzed with the historical baseline data stored in the twin before maintenance. If the measured dynamic characteristic parameters meet or are better than the theoretical improvement model based on the maintenance measures, it is determined that the maintenance measures are effective, and the correction logic and prediction accuracy of the damage identification and evolution model built in the digital twin after the maintenance intervention are verified.

[0122] Embodiment two

[0123] As shown in Figure 2 Embodiment two of the present application provides a bridge detection system based on digital twin technology, comprising:

[0124] The data acquisition and synchronization module 21 acquires strain distribution values, vibration frequency spectrum values and environmental load spectrum values in real time through the sensor network deployed on the physical bridge, generates a structural response data set and synchronizes it to the digital twin; including the following sub-modules:

[0125] The strain field acquisition sub-module 211 acquires three-dimensional strain distribution values of the bridge girder web, pier pile cap and cable tower anchorage zone through a high-density optical fiber strain sensor array, and constructs a stress field cloud map;

[0126] The vibration frequency spectrum monitoring sub-module 212 uses a distributed accelerometer network to monitor the structural vibration response in real time, and extracts the fundamental frequency, damping ratio and other vibration frequency spectrum characteristic values through fast Fourier transform;

[0127] Environmental load integration submodule 213: Integrate the monitoring data of temperature and humidity sensors, anemometers, and dynamic weighing systems to generate a multi-dimensional environmental load spectrum containing temperature gradient, wind load spectrum, and traffic load time history;

[0128] Edge synchronization gateway submodule 214: Use edge computing gateway for spatiotemporal data registration to form a structure response dataset with spatiotemporal labels and synchronize to the digital twin;

[0129] Structure health assessment module 22: Calculate damage index value and cumulative damage value based on the structure response dataset of the digital twin, including the following submodules:

[0130] Fatigue damage index calculation submodule 221: Establish a local micro-strain field model based on strain distribution value, and calculate the fatigue damage index value of key components by combining material S-N curve and Miner linear cumulative damage criterion;

[0131] Stiffness degradation identification submodule 222: Quantify the cumulative damage value of structural stiffness degradation through frequency domain decomposition algorithm based on modal parameter offset of vibration frequency spectrum value;

[0132] Full life cycle prediction submodule 223: Correlate historical detection data with real-time response, and dynamically update the cumulative damage value and generate the full life cycle degradation curve using time series prediction model;

[0133] Life prediction and state calibration module 23: Input damage index value and cumulative damage value into preset safety criteria to calculate safety margin coefficient value and failure risk level value; based on safety margin coefficient value and environmental load spectrum value, calculate residual life prediction value, and synchronize to correct the degradation rate value of the digital twin; including the following submodules:

[0134] Safety margin field calculation submodule 231: Calculate regional safety margin coefficient value by matching preset material strength threshold matrix based on spatial distribution of damage index value;

[0135] Risk dynamic assessment submodule 232: Combine the spatiotemporal evolution characteristics of cumulative damage value to generate five-level failure risk level value from low to high using fuzzy comprehensive evaluation model;

[0136] Risk coverage verification submodule 233: Verify the coverage completeness of risk level determination logic through Monte Carlo simulation to exclude the risk of missed judgment;

[0137] Crack propagation life prediction submodule 234: Coupling extreme working condition distribution of environmental load spectrum value and safety margin coefficient decay curve, predict residual life prediction value based on Paris crack propagation law;

[0138] Adaptive calibration sub-module 235: According to the remaining life prediction result, the time-varying degradation rate value of the digital twin is optimized reversely, and an adaptive calibration mechanism of material performance degradation is established.

[0139] Closed-loop control sub-module 236: Through cross-validation of the twin and the physical entity, it is ensured that the prediction accuracy of the degradation model is controlled within a ±5% error band.

[0140] Maintenance decision and closed-loop feedback module 24: According to the failure risk level value, the remaining life prediction value and the safety margin coefficient value, a priority maintenance instruction is generated, and after execution, the maintenance effect data is fed back to the digital twin for updating, including the following sub-modules:

[0141] Hierarchical treatment sub-module 241: Based on the spatial thermal map of the failure risk level value, a high-risk area requiring emergency treatment and an observation monitoring area are divided;

[0142] Decision optimization sub-module 242: Combined with the remaining life prediction critical value, an intelligent maintenance instruction set containing construction timing and resource allocation is generated;

[0143] Twin performance feedback sub-module 243: Through the Internet of Things terminal, the change data of the structural dynamic characteristics after maintenance is collected, and is fed back to the digital twin to verify the effectiveness of the damage model correction;

[0144] Corresponding to the above-mentioned embodiments, the embodiments of the present application provide a computer storage medium, comprising: at least one memory and at least one processor;

[0145] The memory is used to store one or more program instructions;

[0146] The processor is used to run one or more program instructions to execute a bridge detection method based on digital twin technology.

[0147] Corresponding to the above-mentioned embodiments, the embodiments of the present application provide a computer readable storage medium, and the computer storage medium contains one or more program instructions, and the one or more program instructions are used to execute a bridge detection method based on digital twin technology by the processor.

[0148] The disclosed embodiments provide a computer readable storage medium, and the computer readable storage medium stores computer program instructions, when the computer program instructions run on the computer, so that the computer executes the above-mentioned bridge detection method based on digital twin technology.

[0149] In an embodiment of the present application, the processor can be an integrated circuit chip with the processing capability. The processor can be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

[0150] The disclosed methods, steps, and logic block diagrams in the embodiments of the present application can be implemented or executed by using a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general purpose processor can be a microprocessor, or the processor can be any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present application can be directly embodied in hardware, executed by a processor, or a combination thereof. The software module can reside in memories, flash memories, read-only memories, programmable read-only memories, electrically programmable read-only memories, registers, or other forms of the storage medium for storing data which are well known to those skilled in the art. The processor reads information in the storage medium, and combines the information with hardware to execute the steps of the above methods.

[0151] The storage medium can be a memory, for example, a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0152] The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory.

[0153] The volatile memory can be Random Access Memory (RAM), used as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The below-described embodiments do not limit the scope of the application to any particular RAM type.

[0154] The storage media described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.

[0155] Those skilled in the art should be aware that the functions described in the embodiments of the present application can be implemented in combination of hardware and software in one or more of the above examples. When the software is applied, the corresponding functions can be stored in a computer readable medium or transmitted as one or more instructions or codes on the computer readable medium. The computer readable medium includes computer storage medium and communication medium, wherein the communication medium includes any medium facilitating the transmission of computer programs from one place to another. The storage medium can be any available medium accessible by a general or special purpose computer.

[0156] The above detailed description sets forth the purposes, technical solutions and beneficial effects of the present application. It should be understood that the above detailed description is only a specific embodiment of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement made on the basis of the technical solutions of the present application shall be included in the protection scope of the present application.

Claims

1. A bridge detection method based on digital twin technology, characterized in that: include: The sensor network deployed on the physical bridge collects strain distribution values, vibration spectrum values, and environmental load spectrum values ​​in real time, generates a structural response dataset, and synchronizes it to the digital twin. Calculate the damage index value and cumulative damage value based on the structural response data set of the digital twin; Input the damage index value and the cumulative damage value into the preset safety criteria to calculate the safety margin coefficient value and the failure risk level value; Based on the safety margin coefficient value and environmental load spectrum value, the remaining life prediction value is calculated and the degradation rate value of the digital twin is simultaneously corrected; Generate priority maintenance instructions based on the failure risk level, remaining life prediction, and safety margin coefficient. After execution, the maintenance effect data is fed back to the digital twin to complete the update. The sensor network deployed on the physical bridge collects strain distribution values, vibration spectrum values, and environmental load spectrum values ​​in real time, generates a structural response dataset, and synchronizes it to the digital twin. This involves the following sub-steps: A high-density optical fiber strain sensor array is used to collect the three-dimensional strain distribution values ​​of the bridge main beam web, pier cap and cable tower anchorage area, and construct a stress field cloud map; A distributed accelerometer network is used to monitor the structural vibration response in real time, and the fundamental frequency and damping ratio vibration spectrum eigenvalues ​​are extracted through fast Fourier transform; Integrate monitoring data from temperature and humidity sensors, anemometers, and dynamic weighing systems to generate multi-dimensional environmental load spectrum values ​​including temperature gradient, wind load spectrum, and traffic load time history; Use the edge computing gateway to perform spatiotemporal data registration, form a structural response dataset with spatiotemporal labels and synchronize it to the digital twin; Based on the structural response dataset of the digital twin, the damage index value and the cumulative damage value are calculated, which includes the following sub-steps: A local micro-strain field model is established based on the strain distribution value, and the fatigue damage index value of the key components is calculated by combining the material SN curve and Miner linear cumulative damage criterion; Based on the modal parameter offset of the vibration spectrum value, the cumulative damage value of the structural stiffness degradation is quantified through the frequency domain decomposition algorithm; By correlating historical inspection data with real-time responses, a time series prediction model is used to dynamically update the cumulative damage value and generate a full life cycle degradation curve.

2. The bridge detection method based on digital twin technology according to claim 1 is characterized in that: Correlating historical inspection data with real-time responses, using a time series prediction model to dynamically update the cumulative damage value and generate a full life cycle degradation curve includes the following sub-steps: Extract the strain distribution peak sequence and vibration fundamental frequency attenuation data stored in the digital twin over the years; By integrating real-time monitoring values ​​with historical databases through long-short-term memory networks, the cumulative damage value considering the material aging effect is reconstructed; The statistical significance of the cumulative damage value is verified based on the Bayesian update mechanism, and the exponential degradation parameters in the fatigue damage model are dynamically calibrated.

3. The bridge detection method based on digital twin technology according to claim 1 is characterized in that: Input the damage index value and the cumulative damage value into the preset safety criteria to calculate the safety margin coefficient value and the failure risk level value, including the following sub-steps: According to the spatial distribution of damage index values, the safety margin coefficient value of each area is calculated by matching the preset material strength threshold matrix; Combined with the spatiotemporal evolution characteristics of the cumulative damage value, a fuzzy comprehensive evaluation model is used to generate five levels of failure risk from low to high; The coverage completeness of the risk level determination logic is verified through Monte Carlo simulation to eliminate the risk of missed determination.

4. The bridge detection method based on digital twin technology according to claim 1 is characterized in that: Based on the safety margin coefficient value and the environmental load spectrum value, the remaining life prediction value is calculated and the degradation rate value of the digital twin is simultaneously corrected. The following sub-steps are included: The extreme working condition distribution of coupled environmental load spectrum values ​​and the safety margin coefficient attenuation curve are used to predict the remaining life based on the Paris crack growth law; Inversely optimize the time-varying degradation rate value of the digital twin based on the remaining life prediction results and establish an adaptive calibration mechanism for material performance degradation; Cross-validation between twins and physical entities ensures that the prediction accuracy of the degradation model is controlled within the ±5% error band.

5. The bridge detection method based on digital twin technology according to claim 1 is characterized in that: Generate priority maintenance instructions based on the failure risk level, remaining life prediction, and safety margin coefficient. After execution, the maintenance effect data is fed back to the digital twin to complete the update. This includes the following sub-steps: Based on the spatial heat map of failure risk level values, high-risk areas requiring emergency treatment and observation and monitoring areas are divided; Combined with the remaining life prediction critical value, an intelligent maintenance instruction set including construction timing and resource allocation is generated; The data on changes in structural dynamic characteristics after maintenance is collected through the IoT terminal, and closed-loop feedback is fed back to the digital twin to verify the effectiveness of the damage model correction.

6. A bridge detection system based on digital twin technology, characterized in that: include: Data acquisition and synchronization module: This module collects strain distribution values, vibration spectrum values, and environmental load spectrum values ​​in real time through a sensor network deployed on the physical bridge, generates a structural response dataset, and synchronizes it to the digital twin. Structural health assessment module: Calculates damage index and cumulative damage values ​​based on the structural response dataset of the digital twin; Life prediction and state calibration module: inputs the damage index value and cumulative damage value into the preset safety criteria, calculates the safety margin coefficient value and failure risk level value; Based on the safety margin coefficient value and environmental load spectrum value, the remaining life prediction value is calculated and the degradation rate value of the digital twin is simultaneously corrected; Maintenance decision-making and closed-loop feedback module: Generates priority maintenance instructions based on the failure risk level, remaining life prediction value, and safety margin coefficient value. After execution, the maintenance effect data is fed back to the digital twin to complete the update; The data acquisition and synchronization module specifically includes: collecting three-dimensional strain distribution values ​​of the bridge main beam web, pier caps, and cable tower anchorage areas through a high-density fiber optic strain sensor array to construct a stress field cloud map; using a distributed accelerometer network to monitor the structural vibration response in real time, and extracting the fundamental frequency and damping ratio vibration spectrum characteristic values ​​through fast Fourier transform; integrating monitoring data from temperature and humidity sensors, anemometers, and dynamic weighing systems to generate multidimensional environmental load spectrum values ​​including temperature gradient, wind load spectrum, and traffic load time history; using an edge computing gateway to perform spatiotemporal data alignment to form a structural response dataset with spatiotemporal labels and synchronize it to the digital twin; The structural health assessment module specifically includes: establishing a local micro-strain field model based on the strain distribution value, and calculating the fatigue damage index value of key components by combining the material SN curve and Miner linear cumulative damage criterion; quantifying the cumulative damage value of structural stiffness degradation through the frequency domain decomposition algorithm based on the modal parameter offset of the vibration spectrum value; correlating historical detection data with real-time response, and using the time series prediction model to dynamically update the cumulative damage value and generate a full life cycle degradation curve.

7. A computer storage medium, characterized in that include: at least one memory and at least one processor; a memory for storing one or more program instructions; A processor is used to run one or more program instructions to execute a bridge detection method based on digital twin technology as described in any one of claims 1 to 5.

Images