A method for detecting abnormality of road bridge parameters

Abstract

The application discloses a kind of abnormal detection methods of road bridge parameters, belong to civil engineering technical field.It includes the following steps: step 1, establish the spatio-temporal correlation between monitoring points and data mapping relationship;Step 2, realize the adaptive update of determination rule, to adapt to the state evolution of bridge service stage;Step 3, the anomaly in monitoring data is intelligently attributed analysis;Step 4, sudden structural damage and slowly changing degradation process are identified and comprehensively evaluated;Step 5, the deviation degree of bridge health state is quantitatively analyzed, and generates standardized bridge health index.The application establishes the spatio-temporal correlation network between monitoring points and environment-structure mapping function, combined with multidimensional feature extraction and dynamic weight distribution mechanism, realizes environment interference elimination, abnormal attribution intelligent analysis and the joint identification of sudden damage and slowly changing degradation, and finally quantitatively generates standardized health index.

Description

Technical Field

[0001] This application relates to the field of civil engineering technology, and more specifically, to a method for detecting anomalies in road and bridge parameters. Background Technology

[0002] To ensure the safe operation and extend the service life of road and bridge structures, real-time monitoring and analysis of structural parameters has become a routine task for highway operation and maintenance units. Currently, common structural monitoring parameters include strain, deflection, displacement, tilt angle, acceleration, and temperature. These parameters reflect the response characteristics of bridge structures under different loads and environmental conditions. Analysis of these parameters can effectively identify the structural health status and potential safety hazards.

[0003] However, in actual operation, many factors influence road and bridge parameters, including natural conditions such as traffic load and ambient temperature, as well as engineering defects such as structural aging, uneven foundation settlement, and loose connecting components. The superposition of these factors often leads to complex changes in parameter data, such as nonlinearity, abrupt changes, and periodic disturbances, making it difficult to identify abnormal states. Currently, widely used anomaly detection methods mainly include threshold judgment methods, statistical modeling methods, and machine learning-based intelligent identification methods. Among them, traditional threshold methods, although simple to implement, are difficult to handle the joint analysis of multi-dimensional complex parameters and are prone to false alarms and missed alarms; statistical modeling methods are sensitive to data distribution assumptions and have poor adaptability; while intelligent identification methods have improved accuracy, they are often difficult to promote and apply in practice due to problems such as algorithm complexity, insufficient model generalization ability, and strong sample dependence.

[0004] In addition, existing methods generally have the following problems: First, the parameter data quality control mechanism is not sound, and it is difficult to effectively distinguish between outliers and sensing noise; second, there is a lack of modeling constraints for the physical characteristics of road and bridge structures, resulting in a certain "black box" nature of the detection results; third, the coupling relationship between spatial distribution and temporal evolution characteristics is not fully considered, making it difficult to identify some potential anomalies in a timely manner.

[0005] In summary, how to construct a high-precision, robust, and interpretable anomaly detection method for the multi-source parameter characteristics of road and bridge structures has become an urgent technical problem to be solved. Summary of the Invention

[0006] To overcome a series of shortcomings in the existing technology, the purpose of this application is to provide a method for detecting anomalies in road and bridge parameters, comprising the following steps:

[0007] Step 1: Establish the spatiotemporal correlation and data mapping relationship between monitoring points;

[0008] Step 2: Implement adaptive updates to the decision rules to adapt to the state evolution of the bridge during its service phase;

[0009] Step 3: Perform intelligent attribution analysis on anomalies in the monitoring data;

[0010] Step 4: Jointly identify and comprehensively assess sudden structural damage and gradual degradation processes;

[0011] Step 5: Quantitatively analyze the degree of deviation of the bridge's health status and generate a standardized bridge health index.

[0012] Furthermore, step 1 includes the following steps:

[0013] Structural response parameters and environmental impact parameters are collected through a distributed sensor network and preprocessed to form a structured multidimensional time series dataset.

[0014] Based on the physical structural characteristics of the bridge, a spatiotemporal correlation network reflecting the spatial topology and temporal series correlation of monitoring points is constructed.

[0015] Identify and quantify the impact of environmental factors on structural response and their hysteresis effects, and form an environment-structure mapping function library;

[0016] Based on measured data, the response transfer characteristics between monitoring points are calculated, the signal propagation path and its attenuation law are identified, and a spatial transfer function matrix reflecting the structural dynamic characteristics is constructed.

[0017] Dimensionality reduction and feature extraction are performed on high-dimensional monitoring data, and feature combinations affecting structural health status are identified to form a feature fingerprint set characterizing structural health status.

[0018] Furthermore, the construction of the spatiotemporal correlation network includes:

[0019] Based on the physical structure layout of the bridge, the monitoring points are mapped to a three-dimensional coordinate system to construct an initial spatial topology model;

[0020] Calculate the Euclidean distance and structural connectivity between monitoring points to form a spatial adjacency matrix;

[0021] For different types of monitoring parameters, the cross-correlation coefficient, Granger causality coefficient, and mutual information entropy value of the time series are calculated to quantitatively characterize the strength of time series correlation.

[0022] By fusing spatial adjacency relationships with temporal correlation strength, a weighted spatiotemporal correlation network is generated, where the edge weights reflect the degree of physical correlation between monitoring points.

[0023] Identify the community structure and key nodes in the network, and calculate the global and local characteristic parameters of the network, including average path length, clustering coefficient, centrality and robustness index;

[0024] As monitoring data continues to accumulate, the edge weights and topology of the spatiotemporal correlation network are updated regularly to dynamically reflect the changes in the correlation characteristics of the bridge structure over time.

[0025] Furthermore, the process of establishing the environment-structure mapping function library includes:

[0026] Establish a linear mapping relationship between environmental parameters and structural response, and calculate the sensitivity coefficients of each environmental factor;

[0027] A response delay parameter τ is introduced to quantify the time delay effect between environmental changes and structural responses. For temperature field changes, short-term response delay τ1 and long-term response delay τ2 are set.

[0028] Establish a nonlinear mapping function f(E,τ) between environmental parameters and structural response, where E represents the environmental parameter vector;

[0029] Based on seasonality analysis, a seasonal adjustment coefficient matrix S of environment-structure mapping is constructed to reflect the differences in structural response under different seasonal conditions.

[0030] Furthermore, step 2 includes the following steps:

[0031] Based on historical monitoring data during the normal operation of the bridge, a multi-level dynamic envelope system integrating time evolution and periodic change factors is constructed as the basic threshold for subsequent anomaly detection.

[0032] By using the environment-structure mapping function library, the measured structural response parameters are corrected for environmental influences, and the residual response after removing environmental interference is obtained, thus eliminating the structural response changes caused by environmental fluctuations.

[0033] Based on the sensitivity and importance of each monitoring parameter in the structural state characterization, a differentiated weighting system for spatial partitioning and parameter classification is established.

[0034] The environmentally corrected structural response parameters are compared with the baseline envelope in real time, and the overall deviation is calculated by combining the differential weights.

[0035] Regularly update the benchmark dataset and envelope parameters to highlight recent operational characteristics and dynamically adapt to performance changes in bridges caused by aging.

[0036] To address the differences in performance characteristics across different service stages of bridges, a phased judgment standard library was constructed. Based on years of service, maintenance records, and performance evaluation results, the anomaly judgment threshold was dynamically adjusted, and the judgment rule parameters were optimized.

[0037] Furthermore, the establishment of the differentiated weighting system includes:

[0038] Based on the structural function division of the bridge, the monitoring area is divided into the main beam area, bridge tower area, anchorage area, and auxiliary component area, and a spatial weight coefficient w is assigned to each area according to its importance to the overall structural safety. i ;

[0039] Based on the sensitivity analysis results of monitoring parameters to structural damage, the monitoring parameters are divided into displacement, strain, vibration, and environmental categories, and a category weight w is assigned to each parameter. j ;

[0040] To address the differences in importance of parameters of the same category at different spatial locations, a location-parameter joint weight matrix W = {w ij}, where w ij =w i ×w j ×α ij α ij For adjustment coefficients;

[0041] The design incorporates an adaptive weight update mechanism that dynamically adjusts the weight coefficients of each monitoring point based on the historical accuracy and false alarm rate of anomaly detection, thereby optimizing the accuracy of anomaly determination.

[0042] Furthermore, step 3 includes the following steps:

[0043] Establish a conditional probability table that reflects the relationship between environmental conditions, material state, load characteristics and the response at each monitoring point, and form a complete probabilistic reasoning framework;

[0044] Summarize the characteristic patterns of different types of anomalies, and record the spatiotemporal distribution characteristics, duration, and recovery characteristics of multi-parameter responses to form an anomaly pattern feature library;

[0045] The abnormal response in the monitoring data is decomposed into three parts: environmental factors, load factors, and structural performance changes. The contribution of each factor to the anomaly is quantitatively analyzed, and the real anomalies caused by structural performance changes are identified and evaluated.

[0046] Based on the differences in structural response over time scales caused by different factors, the relationship between different time patterns and environmental disturbances, load changes and structural damage is analyzed.

[0047] By analyzing the spatial distribution characteristics of structural responses, the spatial propagation patterns of anomalous responses are identified, and the measured spatial distribution is compared with the expected pattern to assess the locality or globality of the anomaly.

[0048] Calculate the confidence level and uncertainty of the cause of the anomaly, and make root cause judgments based on the set rules to achieve anomaly attribution decision.

[0049] Furthermore, the construction of the abnormal pattern feature library includes:

[0050] Collect and organize historical abnormal event data, including anomalies caused by environmental factors, anomalies caused by overload, anomalies caused by structural damage, and anomalies caused by sensor failure;

[0051] For each type of anomalous event, extract its temporal feature vector FT = {duration, rise time, recovery time, peak intensity, root mean square value, kurtosis, skewness, waveform factor} to describe the temporal evolution characteristics of the anomalous event.

[0052] Extract the frequency domain feature vector FF = {spectral centroid, frequency band energy distribution, dominant frequency offset, harmonic ratio, spectral entropy} of the abnormal event to describe the frequency characteristics of the abnormality;

[0053] Extract the spatial distribution feature vector FS = {influence range, decay gradient, propagation speed, spatial correlation, principal component direction} of the abnormal event to describe the spatial diffusion characteristics of the abnormality.

[0054] The recovery characteristics of different types of anomalies are summarized, including three categories: fully recoverable anomalies, partially recoverable anomalies, and unrecoverable anomalies. The recovery index IR∈[0,1] is defined to quantify the degree of recovery.

[0055] Historical anomalous events are categorized into patterns to form an anomalous pattern set M = {M1, M2, ..., M}. k Each pattern Mg contains a feature vector [FT, FF, FS] and a class label;

[0056] Establish a mapping table R(M→C) between abnormal patterns and possible causes to provide attribution references for newly discovered anomalies;

[0057] We design an anomaly pattern matching mechanism based on similarity to compare newly detected abnormal events with patterns in the feature library and identify the most likely anomaly type.

[0058] Furthermore, step 4 includes the following steps:

[0059] Based on the time series data of monitoring points, statistical feature analysis, trend analysis and change point detection are carried out to extract time domain features to identify long-term change trends, sudden damage events and dynamic response transmission patterns.

[0060] The time-domain signal is converted to the frequency domain to extract the dynamic characteristic parameters of the structure, analyze the frequency drift, modal changes and higher-order harmonic components, identify stiffness changes and local damage, and construct a spectral feature vector for structural parameter change identification.

[0061] Establish a quantitative assessment index system for the identification of sudden injuries, and combine it with the spatial distribution characteristics of the injury location to achieve rapid response and accurate positioning of sudden injuries;

[0062] Extract the gradual variation characteristics of structural parameters, identify the overall stiffness decay and material degradation process, calculate the degradation rate and cumulative effect, and predict the future evolution trend of structural performance.

[0063] Construct a unified feature space that integrates multidimensional features to achieve synergistic characterization and effective differentiation of sudden damage and slow degradation;

[0064] Based on the above analysis results, the impact of damage and degradation on structural safety is quantitatively assessed, the structural risk index is calculated, and a comprehensive assessment report containing qualitative judgments and quantitative indicators is generated.

[0065] Furthermore, step 5 includes the following steps:

[0066] Based on multiphysics coupling theory and structural characteristic parameters, a high-precision finite element reference model is constructed that comprehensively considers geometry, material properties, boundary conditions and environmental influences to realistically reflect the service behavior of the bridge.

[0067] By comparing and analyzing the measured data with the predicted values ​​of the reference model, a multi-dimensional deviation index system including frequency domain characteristics, time domain characteristics and energy distribution characteristics is established to achieve comprehensive capture of abnormal bridge conditions.

[0068] Based on the spatiotemporal distribution patterns of deviation indicators at each monitoring point, a comprehensive scoring mechanism considering structural importance, parameter sensitivity, and anomaly persistence is constructed, and the multidimensional deviation indicators are mapped to a standardized health index within the range of [0-100].

[0069] By combining seasonal changes and long-term deterioration factors, a probabilistic prediction of the future condition of bridges is made.

[0070] The overall health index is decomposed into key component level and functional unit level indicators to achieve a mapping of health status from macro to micro, accurately locate potential problem areas, and quantitatively assess their impact on the overall structural safety.

[0071] Compared with the prior art, this application has the following beneficial effects:

[0072] This application establishes a spatiotemporal correlation network and environment-structure mapping function among monitoring points, combined with multidimensional feature extraction and dynamic weight allocation mechanisms, to achieve joint identification of environmental interference removal, intelligent anomaly attribution analysis, and sudden damage and gradual degradation, ultimately quantifying and generating a standardized health index. This method significantly improves the accuracy, adaptability, and interpretability of bridge anomaly identification, possessing clear engineering practical value and technological innovation. Attached Figure Description

[0073] Figure 1 This is a flowchart illustrating an anomaly detection method for road and bridge parameters disclosed in an embodiment of this application. Detailed Implementation

[0074] This invention provides a method for anomaly detection of road and bridge parameters. This method achieves real-time monitoring and early warning of anomalies in road and bridge structures by establishing spatiotemporal correlation of monitoring points, adaptively updating judgment rules, intelligently attributing anomalies, jointly identifying structural damage and degradation, and quantitatively assessing the health status of bridges. The following is combined with… Figure 1 The specific embodiments of the present invention will be described in detail below.

[0075] like Figure 1 As shown, a method for detecting anomalies in road and bridge parameters includes the following steps:

[0076] Step 1: Establish the spatiotemporal correlation and data mapping relationship between monitoring points.

[0077] This step involves collecting structural response parameters and environmental impact parameters through a distributed sensor network, performing preprocessing and feature extraction, and constructing a network model and mapping function library that reflects the spatiotemporal correlation characteristics of the monitoring points. The specific implementation method is as follows:

[0078] 1) Data Acquisition and Preprocessing

[0079] A distributed sensor network deployed at key locations on the bridge is used to collect structural response parameters and environmental impact parameters in real time. The structural response parameters include vibration acceleration, displacement, strain, tilt angle, crack width, and cable force parameters; the environmental impact parameters include temperature field distribution, humidity variation, wind speed and direction, rainfall, traffic flow, and vehicle type distribution. The collected data undergoes preliminary preprocessing, including data cleaning, noise reduction, and interpolation, to form a structured multidimensional time-series dataset.

[0080] 2) Construction of spatiotemporal correlation network

[0081] Based on the physical structural characteristics of the bridge, a spatiotemporal correlation network reflecting the correlation between the spatial topology and time series of monitoring points is constructed. The specific steps are as follows:

[0082] The monitoring points are mapped to a three-dimensional coordinate system, and an initial spatial topology model is constructed based on the layout of the bridge's physical structure.

[0083] Calculate the Euclidean distance and structural connectivity between monitoring points to form a spatial adjacency matrix;

[0084] For different types of monitoring parameters, the cross-correlation coefficient, Granger causality coefficient, and mutual information entropy value of the time series are calculated to quantitatively characterize the strength of time series correlation.

[0085] By fusing spatial adjacency relationships with temporal correlation strength, a weighted spatiotemporal correlation network is generated, where the edge weights reflect the degree of physical correlation between monitoring points.

[0086] Identify the community structure and key nodes in the network, and calculate the global and local characteristic parameters of the network, including average path length, clustering coefficient, centrality and robustness index;

[0087] As monitoring data continues to accumulate, the edge weights and topology of the spatiotemporal correlation network are updated regularly to dynamically reflect the correlation characteristics of the bridge structure over time.

[0088] 3) Establishment of the environment-structure mapping function library

[0089] The impact of environmental factors on structural response and their hysteresis effects are identified and quantified, forming an environment-structure mapping function library. The specific steps are as follows: Establish a linear mapping relationship between environmental parameters and structural response, and calculate the sensitivity coefficients of each environmental factor; introduce a response delay parameter τ to quantify the time lag effect between environmental changes and structural response; for temperature field changes, set short-term response lag τ1 and long-term response lag τ2; establish a nonlinear mapping function f(E,τ) between environmental parameters and structural response, where E represents the environmental parameter vector; based on seasonal analysis, construct a seasonal adjustment coefficient matrix S for the environment-structure mapping, reflecting the structural response under different seasonal conditions.

[0090] 4) Construction of the spatial transfer function matrix

[0091] Based on measured data, the response transfer characteristics between monitoring points are calculated, the signal propagation path and its attenuation law are identified, and a spatial transfer function matrix reflecting the structural dynamic characteristics is constructed.

[0092] 5) Feature extraction and fingerprint set generation

[0093] Dimensionality reduction and feature extraction are performed on high-dimensional monitoring data. Principal component analysis (PCA) and independent component analysis (ICA) are used to identify feature combinations that affect the structural health status, forming a feature fingerprint set that characterizes the structural health status.

[0094] Step 2: Implement adaptive updates to the decision rules to adapt to the state evolution of the bridge during its service phase;

[0095] This step achieves adaptive updates to the judgment rules by constructing a dynamic envelope system and a differentiated weight system to adapt to the state evolution of the bridge during its service life. The specific implementation method is as follows:

[0096] 1) Construction of a multi-level dynamic envelope system

[0097] Based on historical monitoring data during the normal operation of the bridge, a multi-level dynamic envelope system integrating temporal evolution and periodic change factors is constructed. The specific steps are as follows:

[0098] The time-domain decomposition of each monitoring parameter sequence was performed to extract four components: long-term trend T(t), seasonal cycle S(t), daily variation cycle D(t), and random fluctuation R(t).

[0099] For T(t), calculate the dynamic trend envelope [T] u (t),T I [(t)] reflects the long-term performance characteristics of the structure;

[0100] For S(t), a seasonal pattern library is constructed, and the seasonal variation envelope [S] is calculated. u (t),S I [(t)], whose envelope width increases near the seasonal transition point;

[0101] For D(t), considering the differences between weekdays and rest days, diurnal variation envelopes [D] are established separately. u (t),D I (t)];

[0102] For R(t), set the allowable fluctuation range [R]. u (t),R I [(t)], the allowable interval width is proportional to the historical fluctuation range of the monitoring parameters;

[0103] The envelopes at each level are synthesized to form a comprehensive discrimination envelope for the monitoring parameters [U]. u (t),U I [(t)], used for anomaly detection;

[0104] The design incorporates a dynamic update mechanism for envelope parameters, adjusting the width and baseline of each envelope level based on structural aging characteristics, maintenance activities, and changes in the usage environment, thus reflecting the natural evolution of structural performance over time.

[0105] 2) Environmental impact correction

[0106] By using the environment-structure mapping function library, the measured structural response parameters are corrected for environmental influences, eliminating structural response changes caused by environmental fluctuations, and obtaining the residual response after removing environmental interference.

[0107] 3) Establishment of a differentiated weighting system

[0108] Based on the sensitivity and importance of each monitoring parameter in structural state characterization, a differentiated weighting system for spatial partitioning and parameter classification is established. The specific steps are as follows:

[0109] Based on the structural function division of the bridge, the monitoring area is divided into the main beam area, bridge tower area, anchorage area, and auxiliary component area, and a spatial weight coefficient w is assigned to each area according to its importance to the overall structural safety. i Where i = 1, 2, ..., N, N represents the number of monitoring areas, i.e., the number of areas under the functional division of the bridge structure;

[0110] Based on the sensitivity analysis results of monitoring parameters to structural damage, the monitoring parameters are divided into displacement, strain, vibration, and environmental categories, and a category weight w is assigned to each parameter. j , where j = 1, 2, ..., M, M represents the number of monitoring parameter categories, i.e. the parameter types classified based on structural damage sensitivity;

[0111] To address the differences in importance of parameters of the same category at different spatial locations, a location-parameter joint weight matrix W = {w ij}, where w ij =w i ×w j ×α ij α ij For adjustment coefficients;

[0112] The design incorporates an adaptive weight update mechanism to dynamically adjust the weight coefficients of each monitoring point based on the historical accuracy and false alarm rate of anomaly detection.

[0113] 4) Optimization of comprehensive deviation calculation and judgment rules

[0114] The environmentally corrected structural response parameters are compared with the baseline envelope in real time, and the overall deviation is calculated by combining the differential weights. The specific steps are as follows:

[0115] Response after correction And simultaneously read the corresponding upper and lower limits of the reference envelope.

[0116] For each structural response parameter, the standardized deviation is calculated according to the following formula:

[0117]

[0118] Where, δ r (t) represents the standardized deviation of the monitoring parameter r over time t;

[0119] Based on the sensitivity of the structural response parameter r to the overall state perception and the importance of the structure, corresponding weight coefficients are set and dynamically updated according to the characteristics of the structural stage.

[0120] The deviations of each response parameter are weighted and summed to calculate the overall structural deviation index D. total (t).

[0121] The benchmark dataset and envelope parameters are updated regularly to highlight recent operational characteristics; a phased judgment standard library is constructed to address the performance characteristics differences of bridges during their service stages, and the anomaly judgment threshold is dynamically adjusted to optimize the judgment rule parameters.

[0122] Step 3: Perform intelligent attribution analysis on anomalies in the monitoring data.

[0123] This step establishes a probabilistic reasoning framework and an anomaly pattern feature library to achieve intelligent attribution analysis of anomalies in monitoring data. The specific implementation method is as follows:

[0124] 1) Establishment of a probabilistic reasoning framework

[0125] Establish a conditional probability table that reflects the relationship between environmental conditions, material state, load characteristics and the response at each monitoring point, forming a complete probabilistic reasoning framework.

[0126] 2) Construction of anomaly pattern feature library

[0127] To summarize the characteristic patterns of different types of anomalies and construct an anomaly pattern feature library: collect and organize historical anomaly event data, including anomalies caused by environmental factors, overload, structural damage, and sensor failure; for each type of anomaly event, extract its time-domain feature vector (FT), frequency-domain feature vector (FF), and spatial distribution feature vector (FS); summarize the recovery characteristics of different types of anomalies and define the recovery index (IR) to quantify the degree of recovery; classify historical anomaly events into patterns to form an anomaly pattern set M, and establish a mapping relationship table R(M→C) between anomaly patterns and possible causes; design a similarity-based anomaly pattern matching mechanism to compare newly detected anomalies with patterns in the feature library.

[0128] 3) Decomposition and analysis of abnormal contributions

[0129] The abnormal responses in the monitoring data are decomposed into three parts: environmental factors, load factors, and structural performance changes. The contribution of each factor to the anomaly is quantitatively analyzed, and the true anomalies caused by structural performance changes are identified and evaluated.

[0130] 4) Analysis of temporal and spatial characteristics

[0131] Based on the differences in structural response over time caused by different factors, the relationship between different time patterns and environmental disturbances, load changes and structural damage is analyzed; by analyzing the spatial distribution characteristics of structural response, the spatial propagation law of abnormal response is identified, and compared with the expected pattern to assess the locality or globality of the anomaly.

[0132] 5) Root cause judgment and decision-making

[0133] Calculate the confidence level and uncertainty of the cause of the anomaly, and make root cause judgments based on the set rules to achieve anomaly attribution decision.

[0134] Step 4: Jointly identify and comprehensively assess sudden structural damage and gradual degradation processes.

[0135] This step extracts the time-domain and frequency-domain features of the structural response to achieve joint identification and comprehensive evaluation of sudden structural damage and gradual degradation processes. The specific implementation method is as follows:

[0136] 1) Temporal feature analysis and change point detection

[0137] Based on time-series data from monitoring points, statistical feature analysis, trend analysis, and change point detection are conducted to extract time-domain features to identify long-term trends, sudden damage events, and dynamic response transmission patterns.

[0138] 2) Frequency Domain Feature Extraction and Analysis

[0139] The time-domain signal is converted to the frequency domain to extract the dynamic characteristic parameters of the structure, analyze frequency drift, modal changes and higher-order harmonic components, identify stiffness changes and local damage, and construct a spectral feature vector for structural parameter change identification.

[0140] 3) Sudden injury identification and localization

[0141] Establish a quantitative assessment index system for identifying sudden injuries, and combine it with the spatial distribution characteristics of the injury location to achieve rapid response and accurate positioning of sudden injuries.

[0142] 4) Identification and prediction of slow-degradation

[0143] Extract the gradual variation characteristics of structural parameters, identify the overall stiffness decay and material degradation process, calculate the degradation rate and cumulative effect, and predict the future evolution trend of structural performance.

[0144] 5) Collaborative Representation and Differentiation

[0145] Construct a unified feature space that integrates multidimensional features to achieve collaborative characterization and effective differentiation of sudden damage and gradual degradation.

[0146] 6) Comprehensive assessment and report generation

[0147] Based on the above analysis results, the impact of damage and degradation on structural safety is quantitatively assessed, the structural risk index is calculated, and a comprehensive assessment report containing qualitative judgments and quantitative indicators is generated.

[0148] Step 5: Quantitatively analyze the deviation of the bridge's health status and generate a standardized bridge health index.

[0149] This step achieves quantitative assessment and standardized representation of the bridge's health status by constructing a finite element reference model and a multidimensional deviation index system. The specific implementation method is as follows:

[0150] 1) Construction of finite element reference model

[0151] Based on multiphysics coupling theory and structural characteristic parameters, a high-precision finite element reference model is constructed that comprehensively considers geometry, material properties, boundary conditions and environmental influences to realistically reflect the service behavior of bridges.

[0152] 2) Establishment of a multidimensional deviation index system

[0153] By comparing and analyzing the measured data with the predicted values ​​of the reference model, a multi-dimensional deviation index system including frequency domain characteristics, time domain characteristics and energy distribution characteristics is established to achieve comprehensive capture of abnormal bridge conditions.

[0154] 3) Health Index Calculation and Mapping

[0155] Based on the spatiotemporal distribution patterns of deviation indicators at each monitoring point, a comprehensive scoring mechanism considering structural importance, parameter sensitivity, and anomaly persistence is constructed, and the multidimensional deviation indicators are mapped to a standardized health index within the range of [0-100].

[0156] 4) Future state probability prediction

[0157] By combining seasonal variations and long-term deterioration factors, time series analysis, machine learning, and other methods are used to make probabilistic predictions about the future condition of bridges.

[0158] 5) Health Index Decomposition and Positioning

[0159] The overall health index is decomposed into key component level and functional unit level indicators to achieve a mapping of health status from macro to micro, accurately locate potential problem areas, and quantitatively assess their impact on the overall structural safety.

[0160] Through the above steps, this invention achieves comprehensive monitoring and intelligent detection of road and bridge parameters, enabling real-time capture of structural state changes, accurate identification of anomaly causes, and providing a scientific basis for bridge maintenance decisions.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting anomalies in road and bridge parameters, characterized in that, Includes the following steps: Step 1: Establish the spatiotemporal correlation and data mapping relationship between monitoring points; Step 2: Implement adaptive updates to the decision rules to adapt to the state evolution of the bridge during its service phase; Step 3: Perform intelligent attribution analysis on anomalies in the monitoring data; Step 4: Jointly identify and comprehensively assess sudden structural damage and gradual degradation processes; Step 5: Quantitatively analyze the degree of deviation of the bridge's health status and generate a standardized bridge health index; Step 2 includes the following steps: Based on historical monitoring data during the normal operation of the bridge, a multi-level dynamic envelope system integrating time evolution and periodic change factors is constructed as the basic threshold for subsequent anomaly detection. By using the environment-structure mapping function library, the measured structural response parameters are corrected for environmental influences, and the residual response after removing environmental interference is obtained, thus eliminating the structural response changes caused by environmental fluctuations. Based on the sensitivity and importance of each monitoring parameter in the structural state characterization, a differentiated weighting system for spatial partitioning and parameter classification is established. The environmentally corrected structural response parameters are compared with the baseline envelope in real time, and the overall deviation is calculated by combining the differential weights. Regularly update the benchmark dataset and envelope parameters to highlight recent operational characteristics and dynamically adapt to performance changes in bridges caused by aging. To address the differences in performance characteristics of bridges during their service stages, a phased judgment standard library was constructed, and the anomaly judgment threshold was dynamically adjusted based on service life, maintenance records, and performance evaluation results, thereby optimizing the judgment rule parameters. The establishment of the differentiated weighting system includes: Based on the structural function division of the bridge, the monitoring area is divided into the main beam area, bridge tower area, anchorage area, and auxiliary component area, and a spatial weight coefficient w is assigned to each area according to its importance to the overall structural safety. i ; Based on the sensitivity analysis results of monitoring parameters to structural damage, the monitoring parameters are divided into displacement, strain, vibration, and environmental categories, and a category weight w is assigned to each parameter. j ; To address the differences in importance of parameters of the same category at different spatial locations, a location-parameter joint weight matrix W={w ij }, where w ij =wi×wj×α ij α ij For adjustment coefficients; The design incorporates an adaptive weight update mechanism that dynamically adjusts the weight coefficients of each monitoring point based on the historical accuracy and false alarm rate of anomaly detection, thereby optimizing the accuracy of anomaly determination.

2. The method for detecting anomalies in road and bridge parameters according to claim 1, characterized in that, Step 1 includes the following steps: Structural response parameters and environmental impact parameters are collected through a distributed sensor network and preprocessed to form a structured multidimensional time series dataset. Based on the physical structural characteristics of the bridge, a spatiotemporal correlation network reflecting the spatial topology and temporal series correlation of monitoring points is constructed. Identify and quantify the impact of environmental factors on structural response and their hysteresis effects, and form an environment-structure mapping function library; Based on measured data, the response transfer characteristics between monitoring points are calculated, the signal propagation path and its attenuation law are identified, and a spatial transfer function matrix reflecting the structural dynamic characteristics is constructed. Dimensionality reduction and feature extraction are performed on high-dimensional monitoring data, and feature combinations affecting structural health status are identified to form a feature fingerprint set characterizing structural health status.

3. The method for detecting anomalies in road and bridge parameters according to claim 2, characterized in that, The construction of the spatiotemporal correlation network includes: Based on the physical structure layout of the bridge, the monitoring points are mapped to a three-dimensional coordinate system to construct an initial spatial topology model; Calculate the Euclidean distance and structural connectivity between monitoring points to form a spatial adjacency matrix; For different types of monitoring parameters, the cross-correlation coefficient, Granger causality coefficient, and mutual information entropy value of the time series are calculated to quantitatively characterize the strength of time series correlation. By fusing spatial adjacency relationships with temporal correlation strength, a weighted spatiotemporal correlation network is generated, where the edge weights reflect the degree of physical correlation between monitoring points. Identify the community structure and key nodes in the network, and calculate the global and local characteristic parameters of the network, including average path length, clustering coefficient, centrality and robustness index; As monitoring data continues to accumulate, the edge weights and topology of the spatiotemporal correlation network are updated regularly to dynamically reflect the changes in the correlation characteristics of the bridge structure over time.

4. The method for detecting anomalies in road and bridge parameters according to claim 2, characterized in that, The process of establishing the environment-structure mapping function library includes: Establish a linear mapping relationship between environmental parameters and structural response, and calculate the sensitivity coefficients of each environmental factor; A response delay parameter τ is introduced to quantify the time delay effect between environmental changes and structural responses. For temperature field changes, short-term response delay τ1 and long-term response delay τ2 are set. Establish a nonlinear mapping function f(E,τ) between environmental parameters and structural response, where E represents the environmental parameter vector; Based on seasonality analysis, a seasonal adjustment coefficient matrix S of environment-structure mapping is constructed to reflect the differences in structural response under different seasonal conditions.

5. The method for detecting anomalies in road and bridge parameters according to claim 1, characterized in that, Step 3 includes the following steps: Establish a conditional probability table that reflects the relationship between environmental conditions, material state, load characteristics and the response at each monitoring point, and form a complete probabilistic reasoning framework; Summarize the characteristic patterns of different types of anomalies, and record the spatiotemporal distribution characteristics, duration, and recovery characteristics of multi-parameter responses to form an anomaly pattern feature library; The abnormal response in the monitoring data is decomposed into three parts: environmental factors, load factors, and structural performance changes. The contribution of each factor to the anomaly is quantitatively analyzed, and the real anomalies caused by structural performance changes are identified and evaluated. Based on the differences in structural response over time scales caused by different factors, the relationship between different time patterns and environmental disturbances, load changes and structural damage is analyzed. By analyzing the spatial distribution characteristics of structural responses, the spatial propagation patterns of anomalous responses are identified, and the measured spatial distribution is compared with the expected pattern to assess the locality or globality of the anomaly. Calculate the confidence level and uncertainty of the cause of the anomaly, and make root cause judgments based on the set rules to achieve anomaly attribution decision.

6. The method for detecting anomalies in road and bridge parameters according to claim 5, characterized in that, The construction of the abnormal pattern feature library includes: Collect and organize historical abnormal event data, including anomalies caused by environmental factors, anomalies caused by overload, anomalies caused by structural damage, and anomalies caused by sensor failure; For each type of anomalous event, extract its temporal feature vector FT={duration, rise time, recovery time, peak intensity, root mean square value, kurtosis, skewness, waveform factor} to describe the temporal evolution characteristics of the anomalous event. Extract the frequency domain feature vector FF={spectral centroid, frequency band energy distribution, dominant frequency offset, harmonic ratio, spectral entropy} of the abnormal event to describe the frequency characteristics of the abnormality; Extract the spatial distribution feature vector FS={influence range, decay gradient, propagation speed, spatial correlation, principal component direction} of the abnormal event to describe the spatial diffusion characteristics of the abnormality. The recovery characteristics of different types of anomalies are summarized, including three categories: fully recoverable anomalies, partially recoverable anomalies, and unrecoverable anomalies. The recovery index IR∈[0,1] is defined to quantify the degree of recovery. Historical anomalous events are categorized into patterns to form an anomalous pattern set M={M1,M2,...,M...} k Each pattern Mg contains a feature vector [FT, FF, FS] and a class label; Establish a mapping table R(M→C) between abnormal patterns and possible causes to provide attribution references for newly discovered anomalies; We design an anomaly pattern matching mechanism based on similarity to compare newly detected abnormal events with patterns in the feature library and identify the most likely anomaly type.

7. The method for detecting anomalies in road and bridge parameters according to claim 1, characterized in that, Step 4 includes the following steps: Based on the time series data of monitoring points, statistical feature analysis, trend analysis and change point detection are carried out to extract time domain features to identify long-term change trends, sudden damage events and dynamic response transmission patterns. The time-domain signal is converted to the frequency domain to extract the dynamic characteristic parameters of the structure, analyze the frequency drift, modal changes and higher-order harmonic components, identify stiffness changes and local damage, and construct a spectral feature vector for structural parameter change identification. Establish a quantitative assessment index system for the identification of sudden injuries, and combine it with the spatial distribution characteristics of the injury location to achieve rapid response and accurate positioning of sudden injuries; Extract the gradual variation characteristics of structural parameters, identify the overall stiffness decay and material degradation process, calculate the degradation rate and cumulative effect, and predict the future evolution trend of structural performance. Construct a unified feature space that integrates multidimensional features to achieve synergistic characterization and effective differentiation of sudden damage and slow degradation; Based on the above analysis results, the impact of damage and degradation on structural safety is quantitatively assessed, the structural risk index is calculated, and a comprehensive assessment report containing qualitative judgments and quantitative indicators is generated.

8. The method for detecting anomalies in road and bridge parameters according to claim 1, characterized in that, Step 5 includes the following steps: Based on multiphysics coupling theory and structural characteristic parameters, a high-precision finite element reference model is constructed that comprehensively considers geometry, material properties, boundary conditions and environmental influences to realistically reflect the service behavior of the bridge. By comparing and analyzing the measured data with the predicted values ​​of the reference model, a multi-dimensional deviation index system including frequency domain characteristics, time domain characteristics and energy distribution characteristics is established to achieve comprehensive capture of abnormal bridge conditions. Based on the spatiotemporal distribution patterns of deviation indicators at each monitoring point, a comprehensive scoring mechanism considering structural importance, parameter sensitivity, and anomaly persistence is constructed, and the multidimensional deviation indicators are mapped to a standardized health index within the range of [0-100]. By combining seasonal changes and long-term deterioration factors, a probabilistic prediction of the future condition of bridges is made. The overall health index is decomposed into key component level and functional unit level indicators to achieve a mapping of health status from macro to micro, accurately locate potential problem areas, and quantitatively assess their impact on the overall structural safety.

Images