Bridge displacement remote intelligent monitoring method and system and computer device

Abstract

The application relates to the technical field of data processing, and discloses a bridge displacement remote intelligent monitoring method and system and computer equipment. The method comprises the following steps: setting multiple trigger thresholds to perform grouped polling sampling to obtain displacement data; adopting dynamic weight fusion to remove noise, identify abnormalities, and generate a digital twin model by using a Kriging method; extracting features to classify and distinguish environmental and structural response displacements; calculating a deviation index to estimate fatigue damage formation and generate a health report; calculating a risk entropy value to set an early warning and generate a treatment scheme; and evaluating an improvement rate to update and configure a closed-loop optimization. By fusing environmental data and historical monitoring data, the application establishes an adaptive sampling strategy and an intelligent analysis and processing mechanism, accurately distinguishes displacement changes caused by environmental factors and structural factors, and performs accurate risk quantification and automatic decision support.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of data processing, and in particular to a bridge displacement remote intelligent monitoring method and system and a computer device. BACKGROUND

[0002] As a key infrastructure of the transportation system, the safety state of a bridge is directly related to the safety of people's lives and property and the development of the society and economy. Traditional bridge monitoring methods mainly rely on manual inspection and regular detection, which is difficult to find potential dangers in the bridge structure in a timely manner. With the development of sensor technology and communication technology, bridge health monitoring systems have gradually been applied to practical engineering, realizing the continuous monitoring of key parts of the bridge. At present, common bridge monitoring systems mainly include strain monitoring, displacement monitoring, vibration monitoring and environmental parameter monitoring and other types. These systems arrange various sensors at key parts of the bridge, collect structural response data, and after data transmission and processing, evaluate and warn the health state of the bridge.

[0003] However, the existing bridge displacement monitoring technology has a series of deficiencies: first, the sensor sampling strategy is fixed and cannot be dynamically adjusted according to the actual state of the bridge, resulting in energy waste or missing of key data; second, the analysis and processing of displacement data mainly rely on simple statistics and threshold comparison, lacking effective differentiation of environmental factors and structural factors, and being difficult to accurately identify real structural abnormalities; third, the early warning decision lacks a scientific and quantitative risk assessment mechanism, often relying on experience, and lacking in accuracy and timeliness; fourth, the monitoring system parameters are fixed and cannot be adaptively adjusted according to the monitoring effect and environmental changes, making it difficult to meet the long-term monitoring demand; finally, there is a lack of a complete closed-loop feedback mechanism, which cannot continuously optimize the monitoring strategy based on the actual intervention effect, and the system performance is difficult to improve. SUMMARY

[0004] The application provides a bridge displacement remote intelligent monitoring method and system and a computer device, which are used for establishing an adaptive sampling strategy and an intelligent analysis and processing mechanism by fusing environmental data and historical monitoring data, accurately distinguishing displacement changes caused by environmental factors and structural factors, and performing risk precise quantization and automatic decision support.

[0005] In a first aspect, the application provides a bridge displacement remote intelligent monitoring method, which comprises: grouping and polling sampling of sensors at key structural positions of a bridge by setting multi-stage trigger thresholds to obtain original displacement data packets; denoising and outlier identification of displacement data at different positions and types are performed by using a dynamic weight fusion technology according to the original displacement data packets, and a three-dimensional displacement field is constructed by using a Kriging interpolation method to generate a real-time bridge displacement digital twin model; displacement spatiotemporal features are extracted and pattern classification processing is performed according to the real-time bridge displacement digital twin model to distinguish between environmental response displacement and structural response displacement; a displacement deviation index is calculated and fatigue damage accumulation is estimated based on the environmental response displacement and the structural response displacement to form a bridge health state report; a displacement risk entropy value is calculated and an early warning level is set according to the bridge health state report to generate a graded disposal scheme; improvement rate index calculation is performed on displacement changes after implementation of the graded disposal scheme, a monitoring parameter configuration table is updated, and monitoring closed-loop optimization is completed.

[0006] In a second aspect, the application provides a bridge displacement remote intelligent monitoring system, which comprises:

[0007] A sampling module is configured to group and poll sample sensors at key structural positions of a bridge by setting multi-stage trigger thresholds to obtain original displacement data packets.

[0008] An identification module is configured to denoise and identify outliers of displacement data at different positions and types by using a dynamic weight fusion technology according to the original displacement data packets, and a three-dimensional displacement field is constructed by using a Kriging interpolation method to generate a real-time bridge displacement digital twin model.

[0009] A classification module is configured to extract displacement spatiotemporal features and perform pattern classification processing according to the real-time bridge displacement digital twin model to distinguish between environmental response displacement and structural response displacement.

[0010] An estimation module is configured to calculate a displacement deviation index and perform fatigue damage accumulation estimation based on the environmental response displacement and the structural response displacement to form a bridge health state report.

[0011] A grading module is configured to calculate a displacement risk entropy value and set an early warning level according to the bridge health state report to generate a graded disposal scheme.

[0012] A calculation module is configured to perform improvement rate index calculation on displacement changes after implementation of the graded disposal scheme, update a monitoring parameter configuration table, and complete monitoring closed-loop optimization.

[0013] The third aspect of the present application provides a computer device, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invoking the instructions in the memory to cause the computer device to perform the bridge displacement remote intelligent monitoring method described above.

[0014] The fourth aspect of the present application provides a computer readable storage medium having instructions stored therein, which, when executed on a computer, cause the computer to perform the bridge displacement remote intelligent monitoring method described above.

[0015] In the technical scheme provided in the present application, the sensors of the key structural parts of the bridge are grouped and polled for sampling by setting multiple trigger thresholds, realizing intelligent scheduling of data acquisition, ensuring the capture of key data and optimizing energy use efficiency; the dynamic weight fusion technology is used to denoise and identify abnormal values of displacement data of different positions and types, a three-dimensional displacement field is constructed by combining the Kriging interpolation method, and a real-time bridge displacement digital twin model is generated, which not only improves the data quality, but also realizes the leap from discrete monitoring points to continuous displacement field, providing a data basis for global analysis; by extracting the spatiotemporal characteristics of displacement and performing pattern classification processing, the environmental response displacement and the structural response displacement are distinguished, solving the core problem that the influence of environmental factors and structural factors cannot be distinguished in traditional monitoring, greatly improving the accuracy of abnormal identification; based on the environmental response displacement and the structural response displacement, the displacement deviation index is calculated and the fatigue damage accumulation is estimated, forming a bridge health state report, which changes qualitative judgment to quantitative evaluation, providing a scientific basis for decision-making; according to the bridge health state report, the displacement risk entropy value is calculated and the warning level is set, a graded disposal scheme is generated, realizing the transformation from passive response to active warning, and enhancing the risk control ability; the displacement change after the implementation of the graded disposal scheme is calculated for the improvement rate index, the monitoring parameter configuration table is updated, the monitoring closed-loop optimization is completed, and a complete feedback mechanism is established, enabling the monitoring system to self-learn and continuously evolve. It is particularly worth emphasizing that the present scheme fully considers the application characteristics of artificial intelligence algorithms in the field of bridge monitoring, such as using dynamic weight fusion technology to adaptively process sensor data of different positions and types, constructing a continuous displacement field by Kriging spatial interpolation algorithm, distinguishing environmental and structural factors by spatiotemporal feature extraction and pattern classification algorithm, and quantifying system uncertainty based on entropy value theory. These algorithm characteristics are deeply combined with the professional needs of bridge displacement monitoring, optimized and designed for the characteristics of high-dimensional, multi-source and nonlinear displacement data, significantly improving the accuracy, intelligence and adaptability of monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0017] Figure 1 An embodiment of the bridge displacement remote intelligent monitoring method in the present application is shown in the figure.

[0018] Figure 2 An embodiment of the bridge displacement remote intelligent monitoring system in the present application is shown in the figure.

[0019] Figure 3 The structural schematic block diagram of the computer device in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0020] The present application provides a bridge displacement remote intelligent monitoring method, system and computer device. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily mean a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0021] For the convenience of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 An embodiment of the bridge displacement remote intelligent monitoring method in the present application includes:

[0022] Step S101, the sensors of the key structure parts of the bridge are grouped and polled for sampling by setting multi-level trigger thresholds, and original displacement data packets are obtained;

[0023] Step S102, according to the original displacement data packets, dynamic weight fusion technology is used to denoise and identify abnormal values of displacement data of different positions and types, and Kriging interpolation method is used to construct a three-dimensional displacement field to generate a real-time bridge displacement digital twin model;

[0024] Step S103, according to the real-time bridge displacement digital twin model, extracting displacement spatio-temporal features and performing pattern classification processing to distinguish between environmental response displacement and structural response displacement;

[0025] Step S104, based on the environmental response displacement and the structural response displacement, calculating the displacement deviation index and performing fatigue damage accumulation estimation to form a bridge health state report;

[0026] Step S105, according to the bridge health state report, calculating the displacement risk entropy value and setting the warning level to generate a hierarchical treatment scheme;

[0027] Step S106, calculating the improvement rate index of the displacement change after the implementation of the hierarchical treatment scheme, updating the monitoring parameter configuration table, and completing the monitoring closed-loop optimization.

[0028] It can be understood that the execution subject of the present application can be a bridge displacement remote intelligent monitoring system, and can also be a terminal or a server, which is not limited here. The server is taken as an example for illustration in the embodiments of the present application.

[0029] Specifically, the sensors of the key structural parts of the bridge are grouped and polled for sampling by setting multi-level trigger thresholds. Specifically, the sensor deployment position is determined based on the historical stress distribution map of the bridge, the monitoring points are arranged for the key parts of the main girder, the pier, the support and the cable tower, the sensors are divided into a displacement sensor group, an inclination sensor group and a strain sensor group according to the function type, and different sampling time windows are allocated to form a sensor polling table. The multi-level trigger thresholds include a low-level threshold, a middle-level threshold and a high-level threshold, which correspond to low-frequency sampling parameters, medium-frequency sampling parameters and high-frequency sampling parameters, respectively. The trigger thresholds are dynamically adjusted according to the temperature, humidity and wind speed information contained in the real-time environmental data to generate environmental compensation threshold coefficients. The grouped polling sampling is performed according to the polling table and the environmental compensation threshold coefficients, the physical parameters are collected and encrypted, and the original displacement data packet is formed. According to the obtained original displacement data packet, the dynamic weight fusion technology is used to denoise and identify abnormal values of the displacement data of different positions and types, and the Kriging interpolation method is used to construct a three-dimensional displacement field. First, the multi-source displacement data is processed for multi-scale time alignment to generate a time-synchronized displacement matrix, the time domain statistical features are calculated by the sliding window technology, and a displacement fluctuation feature set is constructed. Based on the displacement fluctuation feature set, the Mahalanobis distance method is used to identify abnormal points, and the displacement effective data set is formed after removing the abnormal values. According to the structural importance and data quality index of each monitoring point, the dynamic fusion weight coefficient is calculated, and the displacement effective data set is weighted. The weighted data is input into the Kriging spatial interpolation processor, the displacement values of the non-monitoring points are calculated through the semi-variogram analysis and the optimal linear unbiased estimation, the displacement data of all monitoring points and interpolation points are mapped to the bridge three-dimensional structure model, and the real-time bridge displacement digital twin model is constructed.

[0030] According to the real-time bridge displacement digital twin model, the displacement spatiotemporal characteristics are extracted and mode classification processing is performed to distinguish between environmental response displacement and structural response displacement. The displacement time series is extracted from the displacement digital twin model, a multi-dimensional displacement feature vector is constructed, time domain and frequency domain transformation is performed, displacement waveform feature set and frequency component table are obtained. The displacement waveform feature set is time series matched with real-time meteorological data, displacement-temperature sensitivity coefficient and displacement-wind speed correlation degree are calculated, and an environmental factor influence separation matrix is constructed. The original displacement data is decomposed and operated through the environmental factor influence separation matrix, the displacement is separated into environmental response displacement and structural response displacement, and spatial distribution characteristics analysis is performed on the two types of displacement to form a displacement mode feature library. Based on the environmental response displacement and the structural response displacement, the displacement deviation index is calculated and the fatigue damage accumulation is estimated to form a bridge health state report. The environmental response displacement is compared with the normal range value in the historical environmental response database, and the environmental deviation rate is calculated. The structural response displacement is segmented by time window, the displacement amplitude sequence and frequency variation characteristics are extracted, and a structural displacement feature table is formed. According to the environmental deviation rate and the structural displacement feature table, a comprehensive weight matrix is constructed to quantify the displacement abnormality degree of each monitoring point, and a displacement deviation index is generated. The structural response displacement is subjected to rain flow counting processing, the displacement amplitude frequency and cycle number are counted, and a displacement stress spectrum is formed. According to the mapping relationship between the displacement stress spectrum and the material fatigue curve, the fatigue damage value of each key component is calculated according to the linear damage accumulation principle, and a damage distribution map is constructed. The displacement deviation index and the damage distribution map are combined with the bridge structure importance rating, and a bridge health state report is generated through multi-level weight superposition calculation.

[0031] According to the bridge health state report, the displacement risk entropy value is calculated and the warning level is set to generate a graded disposal scheme. The displacement deviation index and damage distribution parameters are extracted from the bridge health state report to establish a risk assessment basis table. The risk assessment basis table data is subjected to uncertainty quantification analysis to calculate the displacement volatility and trend indicators of each monitoring point to form a monitoring point risk probability distribution. According to the dispersion degree and fluctuation range of the monitoring point risk probability distribution, the displacement risk entropy value is constructed to quantify the uncertainty level of the bridge overall system. The displacement risk entropy value is divided into first warning, second warning and third warning according to the preset interval to determine the warning level. For different warning levels, the corresponding intervention measure set is matched from the preplan knowledge base, including speed limit and load limit measures, maintenance and reinforcement measures and emergency control measures. Combined with the bridge historical response characteristics and the surrounding environmental conditions, the intervention measure set is prioritized and optimized to generate a graded disposal scheme.

[0032] The displacement change after the implementation of the hierarchical treatment scheme is improved rate index calculation, the monitoring parameter configuration table is updated, and the monitoring closed loop optimization is completed. Record the bridge displacement data before and after the implementation of the hierarchical treatment scheme, construct the intervention effect comparison data set. The time series comparison is performed on the intervention effect comparison data set, the displacement amplitude change percentage and the abnormal point reduction rate are calculated, and the displacement improvement quantification table is formed. According to the displacement improvement quantification table, combined with the structure importance weight of each monitoring point, the comprehensive improvement rate index is calculated. The effectiveness of different types of intervention measures is sorted and evaluated based on the improvement rate index, and the intervention measure effect evaluation library is established. According to the historical data in the intervention measure effect evaluation library, the sensor sampling strategy, the trigger threshold and the early warning level determination standard are adjusted, and the monitoring parameter configuration table is updated. The updated monitoring parameter configuration table is applied to the next monitoring period, and a new round of data acquisition and analysis process is started, and the monitoring closed loop optimization is completed.

[0033] In a specific embodiment, the process of step S101 can specifically include the following steps:

[0034] (1) Determine the sensor deployment location based on the bridge historical stress distribution map, and arrange the monitoring points for the key parts of the main girder, pier, support and cable tower;

[0035] (2) Divide the sensors into displacement sensor group, inclination sensor group and strain sensor group according to the function type, assign the corresponding sampling time window, and form the sensor polling table;

[0036] (3) Set three trigger threshold value sets for each sensor group, which are low-level threshold, middle-level threshold and high-level threshold, and correspondingly configure low-frequency sampling parameters, medium-frequency sampling parameters and high-frequency sampling parameters;

[0037] (4) According to the temperature, humidity and wind speed information contained in the real-time environment data, dynamically adjust the trigger threshold of each sensor group, and generate an environmental compensation threshold coefficient;

[0038] (5) According to the sensor polling table and the environmental compensation threshold coefficient, perform grouped polling sampling, and collect the physical parameters of each monitoring point;

[0039] (6) Data encryption and marking are performed on the collected physical parameters, time stamp and position information are marked, and the original displacement data packet is packaged.

[0040] Specifically, the historical stress distribution map refers to the graphical representation of the stress concentration regions of various parts of the bridge obtained through finite element analysis or measured data accumulation, which contains the stress distribution of the bridge under various load conditions. By analyzing the historical stress distribution map, the regions with large stress gradient and obvious changes are found as the key monitoring regions, and the monitoring point arrangement is carried out for the components that bear important loads such as the main girder, bridge pier, support and cable tower. The main girder refers to the main load-bearing component of the bridge across the river or canyon, the bridge pier is the vertical component supporting the main girder, the support is the structure connecting the main girder and the bridge pier, and the cable tower is the high-rise component supporting the main cable of the suspension bridge. The monitoring point arrangement follows the principle of "highlighting the key points and covering comprehensively", and the points are densely arranged in the stress concentration regions and appropriately arranged in the conventional regions to form a grid-like coverage structure. The sensors are divided into displacement sensor group, inclination sensor group and strain sensor group according to the function type, the displacement sensor group mainly monitors the displacement changes of various parts of the bridge, the inclination sensor group monitors the inclination angle changes of the bridge components, and the strain sensor group monitors the internal stress and strain state of the components. The purpose of grouping is to optimize the data acquisition efficiency, and the sensors in the same group have similar data characteristics and processing requirements. According to the importance and data change frequency of each group of sensors, different sampling time windows are allocated to form a sensor polling table. The sensor polling table is a data acquisition time schedule that specifies the sampling order and duration of each group of sensors on the time axis, avoiding data communication conflicts and energy consumption peaks caused by simultaneous sampling.

[0041] A set of three-level trigger thresholds is set for each sensor group, which are low-level threshold, medium-level threshold and high-level threshold. The threshold refers to the displacement or strain change amount that activates different sampling frequencies, the low-level threshold corresponds to daily minor changes, the medium-level threshold corresponds to obvious but non-emergency changes, and the high-level threshold corresponds to significant changes that need immediate attention. These thresholds correspond to the configuration of low-frequency sampling parameters, medium-frequency sampling parameters and high-frequency sampling parameters. The low-frequency sampling parameter is usually set to about 1 Hz, which is suitable for static monitoring; the medium-frequency sampling parameter is set to about 10 Hz, which is suitable for quasi-dynamic monitoring; the high-frequency sampling parameter is set to 50-100 Hz, which is suitable for dynamic response monitoring. The core of the three-level trigger mechanism is to dynamically adjust the data acquisition frequency according to the degree of change of the bridge state, which ensures the integrity of the data and optimizes the use of system resources.

[0042] According to the real-time environmental data, the trigger threshold is dynamically adjusted, which is one of the innovations of the method. The real-time environmental data includes temperature, humidity and wind speed information, and these environmental factors will directly affect the natural displacement of the bridge. By establishing a correlation model between environmental factors and displacement changes, the trigger threshold is dynamically adjusted to generate an environmental compensation threshold coefficient. The environmental compensation threshold coefficient is an adjustment factor used to modify the basic threshold according to the current environmental conditions. For example, in high-temperature weather, the bridge will naturally expand and the displacement will increase, so the trigger threshold should be increased to avoid normal displacement caused by temperature being misjudged as abnormal. When calculating the environmental compensation threshold coefficient, the temperature influence coefficient, humidity influence coefficient and wind speed influence coefficient are considered to adjust the basic threshold by weighting.

[0043] According to the sensor polling table and the environmental compensation threshold coefficient, the grouped polling sampling is performed, which is a specific implementation step of data collection. Grouped polling sampling refers to sequentially activating sensors of different groups for data collection according to a preset schedule, rather than collecting all data simultaneously. The sampling process first checks the current environmental conditions, applies the environmental compensation threshold coefficient to modify the trigger threshold, and then determines the sampling frequency based on the modified threshold. When collecting physical parameters of each monitoring point, the original data such as displacement, inclination rate of change and strain value are recorded. Data encryption and labeling of the collected physical parameters are key steps for data security and management. Data encryption uses the AES encryption algorithm to protect data transmission security, and the labeling process adds a timestamp and location information to each group of data. The timestamp accurately records the specific time of data collection, and the location information includes the spatial coordinates of the monitoring point and the information of the component it belongs to. Finally, the encrypted and labeled data is packaged according to a unified format to form the original displacement data packet, preparing for subsequent analysis and processing.

[0044] In a specific embodiment, the process of performing step S102 can specifically include the following steps:

[0045] (1) Multi-scale time alignment processing is performed on the multi-source displacement data in the original displacement data packet to generate a time-synchronized displacement matrix;

[0046] (2) The time-synchronized displacement matrix is calculated using the sliding window technique to calculate the time-domain statistical features, and a displacement fluctuation feature set is constructed;

[0047] (3) Based on the displacement fluctuation feature set, the Mahalanobis distance method is used to identify abnormal points, and after removing the abnormal values, a displacement effective data set is formed;

[0048] (4) According to the structural importance and data quality index of each monitoring point, a dynamic fusion weight coefficient is calculated, and the displacement effective data set is weighted processed;

[0049] (5) input the weighted displacement effective dataset into the Kriging spatial interpolation processor to calculate the displacement values of the non-monitoring point positions through semi-variogram analysis and optimal linear unbiased estimation;

[0050] (6) map the displacement data of all monitoring points and interpolation points to the bridge three-dimensional structure model to form the real-time bridge displacement digital twin model.

[0051] Specifically, multi-source displacement data in the original displacement data packet are subjected to multi-scale time alignment processing to generate a time-synchronized displacement matrix. The multi-source displacement data refers to data recorded by different types of sensors (displacement sensors, inclination sensors, strain sensors) at different sampling frequencies, and the data is not completely consistent in time stamp. The multi-scale time alignment processing adopts a dynamic time warping (DTW) algorithm to map data points on different time sequences to a unified time axis to solve the problem of time desynchronization. Specifically, the data with the highest sampling frequency is taken as a reference, and the data with low sampling frequency is supplemented by linear or spline interpolation methods to align all data in the time dimension. The time-synchronized displacement matrix is a two-dimensional data structure, where the rows represent different time points, the columns represent different monitoring positions, and each element in the matrix represents the displacement value of a specific position at a specific time point. The time-synchronized displacement matrix is subjected to sliding window technology to calculate the time-domain statistical features and construct a displacement fluctuation feature set. The sliding window technology refers to setting a fixed-length window on the time sequence, and the window slides on the time axis according to a preset step size to calculate the statistical features of the data in each window. The window length is usually set to a length that can contain a complete displacement period, such as 10-30 seconds for displacement caused by vehicle load. The sliding step size determines the density of feature extraction, and the smaller the step size, the denser the features, but the larger the calculation amount. The statistical features, including mean, standard deviation, peak value, peak-valley ratio, and waveform factor, are calculated for the data in each sliding window to form the displacement fluctuation feature set. The displacement fluctuation feature set is a set of feature vectors that describe the variation characteristics of displacement data in the time domain, which contains both static displacement information and dynamic fluctuation characteristics.

[0052] Based on the displacement fluctuation feature set, the Mahalanobis distance method is used to identify abnormal points, and the abnormal values are removed to form a displacement effective dataset. The Mahalanobis distance method is an anomaly detection method that considers the distribution characteristics of data, which can effectively identify abnormal points in a multi-dimensional feature space. The Mahalanobis distance considers the correlation between features, which is particularly suitable for displacement data because the displacements at different positions of the bridge often have strong correlation. The Mahalanobis distance between each data point and the overall distribution center of the features is calculated, and the points with a distance exceeding a preset threshold (usually set to 3 times the standard deviation of the distribution) are marked as abnormal points and removed. After removing the abnormal points, the remaining data form the displacement effective dataset, which represents the displacement state of the bridge under normal conditions.

[0053] According to the structural importance and data quality index of each monitoring point, the dynamic fusion weight coefficient is calculated, and the displacement effective data set is weighted. The structural importance refers to the importance of the bridge member where the monitoring point is located in the overall structure, which is usually determined by the structural engineer according to the stress state and functional role of the member. The data quality index is a quantitative parameter to measure the reliability of monitoring data, including signal-to-noise ratio, stability index and integrity score. The formula for calculating the dynamic fusion weight coefficient is:

[0054] W ij = a · SI i + b · DQ ij + g · TC ij

[0055] Where W ij represents the weight coefficient of the ith monitoring point at the jth time; SI i represents the structural importance index of the ith monitoring point, with a value range of 0-1; DQ ij represents the data quality index of the ith monitoring point at the jth time, with a value range of 0-1; TC ij represents the time-varying credibility of the ith monitoring point at the jth time, reflecting the reliability trend of data changing with time; a, b, g are the weight factors of structural importance, data quality and time-varying credibility, respectively, and satisfy a+b+g=1. The weight coefficient calculated by applying to the displacement effective data set is weighted, emphasizing the contribution of important monitoring points and high-quality data, and suppressing the interference of secondary or low-quality data.

[0056] The weighted displacement effective data set is input into the Kriging spatial interpolation processor, and the displacement values of non-monitoring points are calculated through semi-variogram analysis and optimal linear unbiased estimation. Kriging spatial interpolation is a geostatistical method suitable for data interpolation with spatial correlation. In bridge displacement monitoring, due to the limitation of the number of monitoring points, only displacement data at limited positions can be obtained, while through Kriging interpolation, the continuous displacement field of the entire bridge structure can be estimated. Semi-variogram analysis is the premise of Kriging interpolation, which establishes a displacement spatial correlation model by calculating the displacement value difference between monitoring points at different distances. Optimal linear unbiased estimation is the core of Kriging interpolation, which calculates the displacement estimation value of any non-monitoring point position based on the displacement values of known monitoring points and semi-variogram function. The advantage of Kriging interpolation is that it considers both spatial distance and data directionality and anisotropy, especially suitable for structures with complex geometric shapes such as bridges.

[0057] The displacement data of all monitoring points and interpolation points are mapped to the bridge three-dimensional structure model to form a real-time bridge displacement digital twin model. The bridge three-dimensional structure model is a virtual bridge representation in a computer-aided design (CAD) or building information modeling (BIM) format, which contains the geometric shape, material properties and component relationships of the bridge. In the process of mapping the displacement data to the three-dimensional model, firstly, the spatial correspondence between the monitoring points and the model nodes is established, then the measured displacement values and the interpolated displacement values are assigned to the corresponding model nodes, and finally the displacement amplification display is used to intuitively show the deformation state of the bridge. The real-time bridge displacement digital twin model is a digital mapping of the physical bridge in the virtual space, which not only reflects the current displacement state of the bridge, but also supports historical displacement playback and future displacement prediction, providing an intuitive and effective tool for bridge health monitoring.

[0058] Taking a certain suspension bridge as an example, the original displacement data packet contains data from 48 monitoring points, with a sampling frequency of 10 Hz for the main cable, 5 Hz for the suspender, and 2 Hz for the bridge deck. Through multi-scale time alignment processing, all data are unified to a time axis with a sampling frequency of 10 Hz, forming a time-synchronized displacement matrix containing 48 columns (representing 48 monitoring points). A 30-second sliding window is set, and the window is slid on the time axis with a step of 10 seconds. The mean, standard deviation, peak value and other statistical characteristics of the data in each window are calculated to construct a displacement fluctuation feature set. The Mahalanobis distance method is applied for abnormal point identification, and it is found that the 3rd monitoring point of the main cable has abnormal vibration in a certain period, with a Mahalanobis distance value reaching 4.2 times the threshold value, which is marked as an abnormal point and excluded. According to the structural analysis results, the structural importance index of the monitoring points in the main cable anchorage zone is set to 0.9, the index of the midpoint of the main span is set to 0.8, and the index of other secondary positions is set to 0.6. Combined with the signal-to-noise ratio and data integrity score of each point, the dynamic fusion weight coefficient is calculated, and the maximum weight coefficient of the monitoring points in the main cable anchorage zone is 0.85. The weighted displacement effective data are applied to the Kriging interpolation method, and the displacement values of about 1000 non-monitoring points on the bridge are calculated by analyzing the semi-variogram relationship between the monitoring points to form a detailed displacement field. Finally, all displacement data are mapped to the pre-constructed bridge three-dimensional model to generate a digital twin model that can intuitively display displacement deformation, supporting engineers to conduct remote real-time monitoring and analysis.

[0059] In a specific embodiment, the process of performing step S103 can specifically include the following steps:

[0060] (1) extracting displacement time series from the real-time bridge displacement digital twin model to construct a multi-dimensional displacement feature vector;

[0061] (2) performing time domain and frequency domain transformation on the multi-dimensional displacement feature vector to obtain a displacement waveform feature set and a frequency component table;

[0062] (3) Time series matching of the displacement waveform feature set with real-time meteorological data, calculation of displacement-temperature sensitivity coefficient and displacement-wind speed correlation degree;

[0063] (4) Construction of an environmental factor influence separation matrix based on the displacement-temperature sensitivity coefficient and displacement-wind speed correlation degree;

[0064] (5) Decomposition operation of the original displacement data through the environmental factor influence separation matrix, separation of displacement into the environmental response displacement and the structural response displacement;

[0065] (6) Spatial distribution characteristic analysis of the environmental response displacement and the structural response displacement, formation of a displacement mode feature library.

[0066] Specifically, displacement time series are extracted from a real-time bridge displacement digital twin model to construct a multi-dimensional displacement feature vector. The real-time bridge displacement digital twin model is a digital mapping of the physical structure of the bridge in a virtual space, containing complete displacement information of each monitoring point and interpolation point. When extracting the displacement time series, a fixed time window (usually 24 hours) is set for each key node, and the continuous displacement records within the window are extracted to form time-displacement data pairs. The multi-dimensional displacement feature vector is a high-dimensional vector formed by combining the displacement data of different monitoring points within the same time window, with each dimension representing the displacement value of a monitoring point and the length of the vector equal to the number of monitoring points. This vector representation not only retains the spatial distribution information of displacement, but also contains the time continuity feature. Time and frequency domain transformation is performed on the multi-dimensional displacement feature vector to obtain a displacement waveform feature set and a frequency component table. Time domain transformation refers to feature extraction operations performed on the original time series, including calculation of statistical quantities (mean, variance, skewness, kurtosis), trend analysis (linear regression coefficient, interval maximum change rate), and morphological features (peak factor, wave crest factor), etc. Frequency domain transformation converts the time series into a frequency domain representation through Fast Fourier Transform (FFT) to analyze the frequency composition of the displacement signal. The displacement waveform feature set is the result of time domain transformation, describing the morphological characteristics of displacement over time; the frequency component table is the result of frequency domain transformation, showing the energy distribution of the displacement signal at different frequencies. The frequency component table is particularly important because displacement caused by environmental factors (such as temperature, wind speed) usually appears as low-frequency signals, while structural vibration appears as specific high-frequency resonance peaks.

[0067] Time series matching of the displacement waveform feature set with real-time meteorological data, calculation of displacement-temperature sensitivity coefficient and displacement-wind speed correlation degree. Real-time meteorological data includes environmental parameters such as temperature, humidity, wind speed, and wind direction recorded by monitoring stations. Time series matching aligns displacement data and meteorological data according to time stamps to establish a correspondence between the data. The formula for calculating the displacement-temperature sensitivity coefficient is:

[0068]

[0069] where S DT (p) represents the sensitivity coefficient of displacement of monitoring point p to temperature; D(p, t) represents the displacement value of monitoring point p at time t; represents the average value of displacement of monitoring point p; T(t) represents the temperature value at time t; represents the average value of temperature; T represents the total number of time points. The calculation of displacement-wind speed correlation degree uses cross-correlation coefficient:

[0070]

[0071] where R DW (p) represents the correlation coefficient of displacement of monitoring point p to wind speed; W(t) represents the wind speed value at time t; represents the average value of wind speed. These two coefficients quantify the response degree of displacement to environmental factors, providing basis for subsequent environmental factor separation.

[0072] Based on the displacement-temperature sensitivity coefficient and the displacement-wind speed correlation degree, an environmental factor influence separation matrix is constructed. The environmental factor influence separation matrix is a mathematical tool for decomposing the original displacement into the part caused by environmental factors and the part caused by structural response. When constructing the matrix, first, the main environmental influence factors (usually including temperature, wind speed, humidity, etc.) are determined, and then the response model of displacement to these factors is established. Each row in the environmental factor influence separation matrix corresponds to a monitoring point, each column corresponds to an environmental factor, and the matrix element represents the sensitivity of a specific monitoring point to a specific environmental factor.

[0073] Through the decomposition operation of the environmental factor influence separation matrix on the original displacement data, the displacement is separated into environmental response displacement and structural response displacement. The decomposition operation is based on the following model:

[0074] D(p, t) = D E (p, t) + D S (p, t)

[0075] where D(p, t) represents the original displacement value of monitoring point p at time t; D E (p, t) represents the environmental response displacement; D S (p, t) represents the structural response displacement. The calculation formula of environmental response displacement is:

[0076]

[0077] where D E (p, t) represents the environmental response displacement of monitoring point p at time t; S DT(p) represents the displacement-temperature sensitivity coefficient of monitoring point p; T(t) represents the temperature value at time t; T ref represents the reference temperature, usually taking the historical average value; R DW (p) represents the displacement-wind speed correlation coefficient of monitoring point p; K W represents the normalized coefficient of wind speed, which is used to convert the wind speed influence into displacement; W(t) represents the wind speed value at time t; W ref represents the reference wind speed, usually taking the historical average value; R DH (p) represents the displacement-humidity correlation coefficient of monitoring point p; K H represents the normalized coefficient of humidity, which is used to convert the humidity influence into displacement; H(t) represents the humidity value at time t; H ref represents the reference humidity, usually taking the historical average value.

[0078] D S (p, t) = D(p, t) - D E (p, t)

[0079] This decomposition method can effectively distinguish between normal displacement caused by environmental factors and abnormal displacement caused by structural state changes. Spatial distribution characteristic analysis is performed on the environmental response displacement and the structural response displacement to form a displacement mode feature library. Spatial distribution characteristic analysis refers to the study of the distribution law of displacement in different parts of the bridge, including synchronicity, symmetry and propagation characteristics, etc. For environmental response displacement, the distribution mode of the displacement on the entire bridge is analyzed to verify whether it conforms to the overall expansion and contraction characteristics caused by temperature changes or the lateral deformation characteristics caused by wind load. For structural response displacement, the focus is on analyzing the local abnormal deformation area and the deformation propagation path to detect potential structural problems. The displacement mode feature library is a knowledge base formed by extracting and classifying typical displacement modes in historical data, and contains displacement distribution characteristic templates under different types of loads, providing a reference basis for subsequent displacement cause identification.

[0080] Taking a cable-stayed bridge as an example, the displacement time series of three types of key monitoring points, including main cables, tower tops and bridge decks, are extracted from the real-time bridge displacement digital twin model. A multi-dimensional feature vector containing displacement values of 32 monitoring points is constructed. The time domain analysis of the feature vector shows that the 24-hour displacement mean value of the midpoint of the bridge deck is 22.8 mm, the standard deviation is 3.5 mm, and the peak-to-valley ratio is 1.8. The frequency domain analysis shows that the main frequency components of the displacement of this point are concentrated at 0.01 Hz (corresponding to the diurnal temperature change) and 0.25 Hz (corresponding to the wind load effect). The displacement waveform features are matched with the weather station data in time sequence, and the displacement-temperature sensitivity coefficient of the midpoint of the bridge deck is calculated to be 1.2 mm / ℃, indicating that the displacement increases by about 1.2 mm for every 1℃ increase in temperature. The displacement-wind speed correlation of this point is 0.78, indicating that there is a strong correlation between displacement and wind speed. Based on the sensitivity coefficients and correlation degrees of all monitoring points, an environmental factor influence separation matrix is constructed, with the first column being the temperature sensitivity coefficients of each point and the second column being the wind speed correlation degrees. The original displacement data is decomposed through the matrix to determine that 17.6 mm of the displacement of the midpoint of the bridge deck on the same day is due to temperature changes (environmental response displacement), and 5.2 mm is due to the structure itself (structural response displacement). By comparing and analyzing the environmental response displacement and structural response displacement of different monitoring points, it is found that the environmental response displacement presents a symmetrical distribution from both ends to the middle in the longitudinal direction of the bridge, which is consistent with the expansion characteristics caused by uniform temperature changes. The structural response displacement significantly increases near the right main cable, showing an asymmetric distribution, indicating that there may be structural abnormalities in this area. These analysis results are recorded in the displacement pattern feature library.

[0081] In an embodiment, the process of performing step S104 can specifically include the following steps:

[0082] (1) comparing the environmental response displacement with the normal range value in the historical environmental response database to calculate an environmental deviation rate;

[0083] (2) extracting displacement amplitude sequences and frequency change characteristics by time window segmentation of the structural response displacement to form a structural displacement feature table;

[0084] (3) constructing a comprehensive weight matrix according to the environmental deviation rate and the structural displacement feature table to quantify the displacement abnormality degree of each monitoring point and generate the displacement deviation index;

[0085] (4) performing rain flow counting processing on the structural response displacement to count displacement amplitude occurrence frequency and cycle times to form a displacement stress spectrum;

[0086] (5) calculating the fatigue damage value of each key component according to the mapping relationship between the displacement stress spectrum and the material fatigue curve and the linear damage accumulation principle to construct a damage distribution map;

[0087] (6) Combine the displacement deviation index and the damage distribution map with the bridge structure importance rating to generate the bridge health state report through multi-level weight superposition calculation.

[0088] Specifically, the environmental response displacement is compared with the normal range value in the historical environmental response database to calculate the environmental deviation rate. The environmental response displacement refers to the normal displacement change caused by environmental factors such as temperature, wind speed, humidity, etc. The historical environmental response database is a long-term monitoring accumulated environmental response displacement data set, which contains the normal change range of bridge displacement under different environmental conditions. The environmental deviation rate is a quantitative indicator that measures the degree of deviation of the current environmental response displacement from the historical normal range. The calculation method is to divide the difference between the current environmental response displacement and the displacement mean value under the same environmental condition in history by the historical standard deviation to obtain the standardized deviation degree. The larger the environmental deviation rate, the higher the degree of current environmental response abnormality, which may reflect the decrease in the applicability of the environmental factor influence model or the change in the response characteristics of the bridge to the environment. By segmenting the structural response displacement in time windows, the displacement amplitude sequence and frequency change characteristics are extracted to form a structural displacement feature table. The structural response displacement refers to the displacement caused by the change in the state of the bridge structure itself and is not affected by environmental factors. Time window segmentation is to divide the continuous time sequence into fixed length segments for local analysis. The displacement amplitude sequence refers to the maximum value, minimum value and difference value of the displacement in each time window, which reflects the intensity characteristics of the structural displacement. The frequency change characteristics are obtained by performing frequency spectrum analysis on the displacement data in each window to extract the main frequency components and their energy distribution, which reflects the dynamic characteristics of the structure. The structural displacement feature table is a data structure organized by time windows, which records the amplitude and frequency characteristics of each window and provides a comprehensive description of the change of the structural response displacement over time.

[0089] According to the environmental deviation rate and the structural displacement feature table, a comprehensive weight matrix is constructed to quantify the displacement abnormality degree of each monitoring point and generate the displacement deviation index. The comprehensive weight matrix is a mathematical tool used to integrate abnormal indicators from different sources and assign appropriate importance weights to different indicators. The construction process first determines the evaluation index system, including the environmental deviation rate, displacement amplitude abnormality degree, frequency characteristic deviation degree, etc. Then, a weight coefficient is set for each index, and the weight distribution considers the reliability, sensitivity and importance of the index. Finally, the index values are multiplied by the weights and added up to obtain the comprehensive score. The displacement deviation index is a general evaluation of the displacement abnormality degree after considering both environmental and structural factors. The higher the index value, the greater the degree of displacement deviation from the normal state, which needs to be paid more attention to.

[0090] The rainflow counting method is a commonly used cycle counting method in fatigue analysis, which is suitable for processing irregular load history and can effectively identify complete cycles and half cycles in the load. The processing process includes: rotating the displacement time history graph by 90 degrees, making the time axis vertical downward; imagining the path of raindrops flowing from each displacement peak and valley point, and determining the flow termination condition according to certain rules; recording the starting point and ending point of each flow to form a cycle, and the amplitude is the absolute value of the displacement difference between the starting point and the ending point. The displacement stress spectrum is the statistical result of the number of cycles of different amplitude displacements, usually represented in the form of a two-dimensional matrix, with rows representing displacement amplitude intervals, columns representing displacement mean value intervals, and matrix elements representing the number of cycles under corresponding conditions. The displacement stress spectrum is a bridge connecting displacement monitoring data and fatigue damage assessment, providing basic data for subsequent fatigue analysis.

[0091] According to the mapping relationship between the displacement stress spectrum and the material fatigue curve, the fatigue damage value of each key component is calculated according to the linear damage accumulation principle, and the damage distribution diagram is constructed. The material fatigue curve (S-N curve) describes the number of cycles that the material can withstand under different stress levels, which is an important representation of the fatigue characteristics of the material. Converting displacement to stress requires mapping through structural mechanics relationships, and the commonly used method is to calculate the corresponding stress level according to the displacement value through the finite element model or simplified mechanics model. The linear damage accumulation principle (Miner criterion) is a classic theory of fatigue damage accumulation, and its core formula is:

[0092]

[0093] where D f represents the cumulative fatigue damage value; n ab represents the number of cycles in the amplitude interval a and the mean value interval b in the displacement stress spectrum; N ab represents the total number of cycles that the material can withstand under the corresponding stress condition, which is determined by the S-N curve; A represents the total number of amplitude intervals; B represents the total number of mean value intervals. When the cumulative fatigue damage value D_{f} reaches 1, theoretically, the component is considered to have fatigue failure. The damage distribution diagram is a visual representation of the mapping of the calculated fatigue damage value to the bridge structure model, which intuitively shows the distribution of fatigue damage in each part of the bridge, and helps to identify high-risk areas of fatigue.

[0094] The displacement deviation index and the damage distribution map are combined with the bridge structure importance rating to generate a bridge health state report through multi-level weight superposition calculation. The bridge structure importance rating is a rating of the importance of each component of the bridge in the overall structure, which is usually determined by structural engineers according to factors such as the function, stress condition and failure consequence of the component. Multi-level weight superposition is a hierarchical analysis method that integrates the displacement deviation index, fatigue damage value and structure importance in different levels according to certain weight relationship to form a comprehensive evaluation result. The bridge health state report is the final evaluation result, which includes the overall health grade of the bridge, the state evaluation of key components, the identification of abnormal positions and maintenance suggestions, etc.

[0095] Taking a certain sea-crossing bridge as an example, the bridge has a main span of 240 meters, and the health assessment is carried out through the displacement data of 20 monitoring points. First, the environmental response displacement obtained by monitoring is compared with the historical database, and it is found that the environmental deviation rate of the main cable anchorage area is 2.3, which exceeds the warning threshold of 2.0, indicating that the response characteristics of this area to the environment may have changed. Then the structure response displacement is segmented by 30 minutes time window, and the displacement amplitude and frequency characteristics of each window are extracted, and it is found that the energy proportion of the main cable anchorage area in the 5-8Hz frequency band increases from 15% to 27% in history, indicating that the structure dynamic characteristics have changed significantly. According to the environmental deviation rate and the frequency characteristic change, a comprehensive weight matrix is constructed, in which the environmental deviation weight is 0.4 and the frequency characteristic weight is 0.6, and the displacement deviation index of the main cable anchorage area is calculated as 0.78, which is in a moderate abnormal state. The rain flow counting process is performed on the displacement data of the main cable anchorage area to obtain the cycle number under different amplitude and average value combinations, and the displacement stress spectrum is formed. According to the principle of linear damage accumulation and the S-N curve of the main cable material, the cumulative fatigue damage value of this area is calculated as 0.65, which has approached the warning line 0.7. Considering that the structure importance rating of the main cable anchorage area is A level (the highest level), after the comprehensive evaluation of the displacement deviation index, fatigue damage value and structure importance, the bridge health state report generated marks this area as a concern point that needs to be handled in priority, and suggests to increase the detection frequency and carry out targeted reinforcement and maintenance.

[0096] In a specific embodiment, the process of performing step S105 can specifically include the following steps:

[0097] (1) Extract the displacement deviation index and the damage distribution parameters from the bridge health state report to establish a bridge risk assessment basis table;

[0098] (2) Perform uncertainty quantification analysis on the data in the risk assessment basis table to calculate the displacement fluctuation and trend indicators of each monitoring point to form a monitoring point risk probability distribution;

[0099] (3) According to the dispersion degree and fluctuation range of the risk probability distribution of the monitoring point, the displacement risk entropy value is constructed to quantify the uncertainty level of the overall bridge system;

[0100] (4) The displacement risk entropy value is divided into a first warning, a second warning and a third warning according to a preset interval to determine the warning level;

[0101] (5) For different warning levels, a corresponding intervention measure set is matched from a preplan knowledge base, including speed limit and load limit measures, maintenance and reinforcement measures and emergency control measures;

[0102] (6) The intervention measure set is prioritized and combined and optimized in combination with the historical response characteristics of the bridge and the surrounding environmental conditions to generate the hierarchical treatment scheme.

[0103] Specifically, the displacement deviation index and damage distribution parameters are extracted from the bridge health state report to establish a bridge risk assessment basis table. The displacement deviation index is a comprehensive index that quantifies the degree of displacement deviation of each monitoring point from the normal state, and the damage distribution parameters describe the distribution of fatigue damage in different parts of the bridge. The risk assessment basis table is a structured data table, with each row representing a monitoring point and columns including location information, displacement deviation index, fatigue damage value, structure importance level and other attributes, providing a data basis for subsequent risk assessment. In actual operation, the data in the health state report is extracted according to the preset format and organized into a standardized table structure for easy analysis and processing in the next step. Uncertainty quantification analysis is performed on the data in the risk assessment basis table to calculate the displacement variability and trend indicators of each monitoring point to form the monitoring point risk probability distribution. Uncertainty quantification analysis is an important means of assessing data reliability and risk level, focusing on two characteristics in bridge monitoring: displacement variability and trend. The displacement variability index is characterized by calculating statistical quantities such as standard deviation and coefficient of variation of displacement data within a certain time window, reflecting the degree of dispersion of displacement data; the trend index is characterized by fitting the trend line of displacement data and calculating its slope and acceleration, reflecting the direction and rate of displacement change. The monitoring point risk probability distribution refers to estimating the displacement range and its probability that each monitoring point may occur in the future based on historical data and current state, usually represented by a probability density function. In the calculation process, a probability model is established for the displacement time series of each monitoring point, considering the historical distribution characteristics and recent trend of the data, and the risk probability distribution is generated through statistical inference methods.

[0104] According to the discrete degree and fluctuation range of the risk probability distribution of the monitoring points, the displacement risk entropy value is constructed to quantify the uncertainty level of the bridge overall system. The displacement risk entropy value is inspired by the concept of information entropy and is used to measure the uncertainty degree of the monitoring data. In the calculation, the risk probability distribution of each monitoring point is first discretized into several intervals, and the probability value of each interval is calculated. Then, according to the information entropy formula, the product of the probability of each interval and the logarithm of it is summed and taken as a negative value to obtain the single-point entropy value. The displacement risk entropy value of the bridge overall system is obtained by weighted averaging of the entropy values of each monitoring point, and the weight considers the structural importance and location representativeness of the monitoring point. The higher the displacement risk entropy value, the greater the uncertainty of the bridge displacement state and the higher the risk level. In the data processing process, attention should be paid to the normalization of the probability distribution and the rationality of the interval division to ensure the accuracy of the entropy value calculation.

[0105] The displacement risk entropy value is divided into first-level warning, second-level warning and third-level warning according to the preset interval to determine the warning level. Warning classification is a common method of risk management, and different response measures are taken according to the severity of the risk. In bridge displacement monitoring, the displacement risk entropy value is usually divided into three intervals: first-level warning (attention level) corresponds to the case where the entropy value is below the warning line but close to the warning line, indicating that the bridge state starts to appear abnormal and the monitoring frequency needs to be strengthened; second-level warning (warning level) corresponds to the case where the entropy value exceeds the warning line but does not reach the danger line, indicating that the bridge state has obvious abnormalities and needs to implement restrictive measures and arrange for maintenance; third-level warning (emergency level) corresponds to the case where the entropy value exceeds the danger line, indicating that the bridge state is seriously abnormal and there is a safety hazard, which needs to take emergency intervention measures immediately. The threshold of warning level division is usually determined according to historical monitoring data and expert experience, and there will be some differences for different types and importance of bridges. For different warning levels, the corresponding intervention measure set is matched from the preplan knowledge base, including speed limit and load limit measures, maintenance and reinforcement measures and emergency control measures. The preplan knowledge base is a set of emergency plans established by the bridge management department according to historical cases and professional knowledge, which contains disposal schemes for various abnormal situations. Speed limit and load limit measures are suitable for first-level warning, such as reducing vehicle speed limit, prohibiting overweight vehicles, etc.; maintenance and reinforcement measures are suitable for second-level warning, such as detailed detection of specific parts, local component reinforcement and maintenance, etc.; emergency control measures are suitable for third-level warning, such as temporary closure of the bridge, implementation of traffic diversion, emergency repair, etc. The matching process adopts a rule-based reasoning method, which selects the applicable measure set from the knowledge base according to the current warning level, abnormal position, abnormal type and other factors.

[0106] The intervention measure set is prioritized and combined optimized according to the bridge historical response characteristics and surrounding environmental conditions, to generate a hierarchical treatment scheme. The historical response characteristics refer to the response performance and treatment effect of the bridge in the past similar situations, and the surrounding environmental conditions include traffic flow, weather conditions, geographical location and other external factors. The priority ranking considers multiple factors: the effectiveness of the measures (evaluated according to historical cases), the implementation cost, the implementation difficulty, the impact range, etc. The combined optimization is to select the measure combination with strong complementarity and optimal overall effect from the candidate measures, to avoid redundancy or conflict. The hierarchical treatment scheme is a detailed action guidance document, which includes the basis for warning level judgment, the specific implementation method of each measure, the responsibility division, the time arrangement and the effect evaluation standard. The generation process of the scheme adopts a multi-criteria decision-making method, comprehensively considers the technical feasibility, economic rationality and social impact, and forms a systematic response strategy.

[0107] The entire processing flow is illustrated by taking a certain highway bridge as an example: the displacement deviation indexes of the main span middle part and the right support near part of the bridge are 0.75 and 0.82 respectively, and the fatigue damage values are 0.42 and 0.56 respectively. First, these data are recorded together with the location information, the structure importance level (the main span middle part is A level, and the support is B level) into the risk assessment basis table. Then, the historical displacement data of the two key points are subjected to uncertainty analysis, and the displacement fluctuation index of the main span middle part is calculated to be 0.35 (indicating relative stability), and the trend index is 0.12 (light upward trend); the displacement fluctuation index of the right support is 0.62 (larger fluctuation), and the trend index is 0.28 (obvious upward trend). Based on these indexes, the risk probability distribution of the two points is generated by a statistical model, and the entropy value of the main span middle part is calculated to be 0.68, and the entropy value of the right support is 0.85. Considering the structure importance weight, the overall displacement risk entropy value of the bridge is calculated to be 0.74, which is located in the preset secondary warning interval (0.7-0.9). According to the secondary warning level, the corresponding measure set is matched from the preplan knowledge base, including limiting the total weight of vehicles to be less than 25 tons, reducing the speed to 40 km / h, increasing the monitoring frequency to twice a day, arranging special detection of the right support, etc. Considering that the bridge is an important traffic trunk line, located in an area with large traffic flow but with a diversion road, and the weather forecast for the next three days is no strong wind and rain, the final optimized hierarchical treatment scheme is determined as follows: the weight limit and speed limit measures are implemented, and detailed detection of the right support is arranged in the low peak period from 2:00 to 5:00 the next day, the necessary reinforcement materials are prepared, and the monitoring frequency is increased to every 8 hours, and the displacement change trend is continuously observed.

[0108] In a specific embodiment, the process of performing step S106 can specifically include the following steps:

[0109] (1) Record the bridge displacement data before and after the implementation of the hierarchical treatment scheme, and construct an intervention effect comparison data set;

[0110] (2) Time series comparison is performed on the intervention effect comparison data set, the displacement amplitude change percentage and the abnormal point reduction rate are calculated, and a displacement improvement quantification table is formed;

[0111] (3) According to the displacement improvement quantification table, combined with the structure importance weight of each monitoring point, the comprehensive improvement rate index is calculated;

[0112] (4) Based on the improvement rate index, the effectiveness of different types of intervention measures is ranked and evaluated, and an intervention measure effect evaluation library is established;

[0113] (5) According to the historical data in the intervention measure effect evaluation library, adjust the sensor sampling strategy, trigger threshold and early warning level determination standard, update the monitoring parameter configuration table;

[0114] (6) Apply the updated monitoring parameter configuration table to the next monitoring cycle, start a new round of data collection and analysis process, and complete the monitoring closed-loop optimization.

[0115] Specifically, the monitoring system is continuously optimized to form a closed-loop feedback mechanism. First, record the bridge displacement data before and after the implementation of the hierarchical treatment scheme, and construct an intervention effect comparison data set. The hierarchical treatment scheme is a combination of intervention measures for different warning levels, such as speed limit, load limit, maintenance and reinforcement, or emergency control. The intervention effect comparison data set is a structured data set that contains displacement data within the same time span before and after intervention, which is used to evaluate the effectiveness of intervention measures. During the construction process, the exact time point of intervention implementation needs to be recorded to ensure the comparability of the data before and after the intervention, and the environmental conditions, traffic load and other external factors during the intervention period are recorded for condition correction in subsequent analysis. The data set adopts a two-dimensional table structure of time and space, with rows representing different time points, columns representing different monitoring positions, and cells recording corresponding displacement values, environmental parameters and external conditions.

[0116] The time series comparison is the core method for quantitative evaluation of intervention effect, which calculates the displacement difference of the same monitoring point under similar environmental conditions before and after intervention. The displacement amplitude percentage change reflects the degree of reduction in absolute displacement, and the calculation method is to divide the difference between the displacement amplitude after intervention and the displacement amplitude before intervention by the displacement amplitude before intervention, and then multiply by 100%. The abnormal point reduction rate measures the improvement degree of displacement abnormal phenomenon, and the calculation method is to change the number of data points exceeding the normal threshold within the same length of time before and after intervention. The displacement improvement quantification table is a systematic record of comparative analysis results, including the displacement amplitude percentage change, abnormal point reduction rate and other quantitative indicators of each monitoring point, providing basic data for overall effect evaluation.

[0117] According to the displacement improvement quantification table, combined with the structural importance weight of each monitoring point, the comprehensive improvement rate index is calculated. The structural importance weight is a weight coefficient determined according to the importance of the monitoring point in the overall structure of the bridge component, usually assessed by structural engineers based on the functional role, stress condition and failure consequence of the component. When calculating the comprehensive improvement rate index, the improvement index of each monitoring point is multiplied by the corresponding structural importance weight, and then the weighted average value is obtained. This process ensures that the improvement condition of important components has greater influence in the overall evaluation, and more accurately reflects the improvement effect of the intervention measures on the overall safety of the bridge. The comprehensive improvement rate index is a value between 0 and 1, and the larger the value, the more significant the intervention effect.

[0118] Based on the improvement rate index, the effectiveness of different types of intervention measures is ranked and evaluated, and an intervention measure effect evaluation library is established. In the ranking and evaluation process, multiple dimensions are considered: improvement rate index, implementation cost, implementation difficulty and intervention duration. For each type of intervention measure (such as speed limit, load limit, maintenance and reinforcement, emergency control, etc.), collect the evaluation indexes of historical application cases, calculate the comprehensive score, and form the effectiveness ranking. The intervention measure effect evaluation library is a knowledge base that records the application effect of different types of intervention measures under various bridge types, problem types and environmental conditions, including quantitative evaluation indexes and applicable condition descriptions. The evaluation library uses a combination of structured data and text description to facilitate quick retrieval and application recommendation.

[0119] According to historical data in the intervention effect evaluation library, adjust the sensor sampling strategy, trigger threshold and early warning level determination criteria, and update the monitoring parameter configuration table. The monitoring parameter configuration table is a key parameter set for controlling the operation of the monitoring system, including the sampling frequency, trigger condition, data processing parameters and early warning judgment criteria of various sensors. The adjustment process is based on a feedback learning mechanism, which analyzes the correlation between monitoring parameters and effects in historical intervention cases, and identifies the optimal parameter settings. For example, if it is found that a certain type of anomaly can be better captured at an early stage with a specific frequency of sampling, the frequency is increased accordingly; if a threshold setting leads to too many false positives, the threshold is adjusted appropriately. The adjustment strategy takes into account both monitoring efficiency and system resource consumption, seeking the best balance point. The updated configuration table is managed through a version control system to ensure the traceability of parameter adjustments.

[0120] Apply the updated monitoring parameter configuration table to the next monitoring period and start a new round of data collection and analysis process to complete the monitoring closed-loop optimization. The new round of monitoring uses the updated parameter settings to intensify the monitoring effort on key locations and time periods, optimizes the data processing algorithm parameters, and improves the accuracy of anomaly detection. Monitoring closed-loop optimization refers to the continuous improvement of monitoring methods and parameter settings through the iterative "monitoring-analysis-intervention-evaluation-adjustment" cycle, so that the monitoring system gradually adapts to the structural characteristics and environmental conditions of a specific bridge, achieving precise monitoring and efficient early warning.

[0121] Take a certain suspension bridge as an example to illustrate the whole process: after the implementation of the two-level early warning grading disposal scheme (including limiting weight 30 tons, limiting speed 40 km / h and main cable reinforcement) of the bridge, the displacement data of 7 days before and after the intervention are recorded to form the intervention effect comparison data set. Through time series comparison analysis, it is calculated that the displacement amplitude of the midpoint of the main cable is reduced from 125 mm to 78 mm, the change percentage is-37.6%; the displacement of the top of the main tower is reduced from 85 mm to 62 mm, the change percentage is-27.1%; the number of abnormal points (data points exceeding 3 times of the standard deviation) is reduced from an average of 12 per day before intervention to an average of 3 per day, the reduction rate is 75%. These data are recorded in the displacement improvement quantification table. Considering the importance weight of the midpoint of the main cable and the top of the main tower is 0.6 and 0.4 respectively, the comprehensive improvement rate index is calculated as 0.6x37.6%+0.4x27.1%=33.4%. By comparing this disposal case with historical cases, it is found that in similar cases, the effect of the combination of weight limit + speed limit + reinforcement is significantly better than that of simple weight limit or speed limit, and accordingly the related entries in the intervention measure effect evaluation library are updated. According to the evaluation results, the sensor parameters are adjusted: the first level warning trigger threshold of the midpoint of the main cable is adjusted from displacement exceeding 90 mm to exceeding 85 mm, the sampling frequency during the peak of vehicle flow is increased, and at the same time the wind speed trigger threshold of the top of the main tower is adjusted from 8 m / s to 7 m / s, these adjustments are recorded in the updated monitoring parameter configuration table. After the start of the new monitoring cycle, the monitoring system operates according to the updated parameter settings, realizes earlier identification and more accurate early warning of potential risks, and completes a complete monitoring closed-loop optimization.

[0122] The bridge displacement remote intelligent monitoring method in the embodiments of the present application is described above, and the bridge displacement remote intelligent monitoring system in the embodiments of the present application is described below, please refer to Figure 2 An embodiment of the bridge displacement remote intelligent monitoring system in the embodiments of the present application includes:

[0123] The sampling module is configured to group and poll the sensors of the key structural parts of the bridge by setting multiple trigger thresholds to obtain raw displacement data packets.

[0124] The identification module is configured to use dynamic weight fusion technology to denoise and identify abnormal values of displacement data of different positions and types according to the raw displacement data packets, and to construct a three-dimensional displacement field by using the Kriging interpolation method to generate a real-time bridge displacement digital twin model.

[0125] The classification module is configured to extract displacement spatio-temporal features and perform pattern classification processing according to the real-time bridge displacement digital twin model, and to distinguish between environmental response displacement and structural response displacement.

[0126] An estimation module is configured to calculate a displacement deviation index and perform fatigue damage accumulation estimation based on the environmental response displacement and the structural response displacement, and form a bridge health state report;

[0127] A grading module is configured to calculate a displacement risk entropy value and set an early warning level according to the bridge health state report, and generate a grading disposal scheme;

[0128] A calculation module is configured to calculate an improvement rate index of displacement change after implementation of the grading disposal scheme, update a monitoring parameter configuration table, and complete monitoring closed-loop optimization.

[0129] Through the cooperation of the above-mentioned components, the sensors of the key structural parts of the bridge are grouped and polled for sampling by setting multiple trigger thresholds, the intelligent scheduling of data acquisition is realized, the capture of key data is ensured, and the energy use efficiency is optimized; the dynamic weight fusion technology is used to denoise and identify abnormal values of displacement data of different positions and types, a three-dimensional displacement field is constructed by combining the Kriging interpolation method, a real-time bridge displacement digital twin model is generated, the data quality is improved, and the leap from discrete monitoring points to continuous displacement field is realized, providing a data basis for global analysis; the displacement space-time features are extracted and processed by pattern classification to distinguish between environmental response displacement and structural response displacement, solving the core problem that environmental factors and structural factors cannot be distinguished in traditional monitoring, and greatly improving the accuracy of abnormal identification; based on the environmental response displacement and the structural response displacement, the displacement deviation index is calculated and the fatigue damage accumulation estimation is performed to form the bridge health state report, which changes the qualitative judgment to quantitative evaluation, providing a scientific basis for decision-making; according to the bridge health state report, the displacement risk entropy value is calculated and the early warning level is set to generate the grading disposal scheme, realizing the change from passive response to active early warning and enhancing the risk control capability; the displacement change after implementation of the grading disposal scheme is calculated for improvement rate index, the monitoring parameter configuration table is updated, and the monitoring closed-loop optimization is completed, establishing a complete feedback mechanism to enable the monitoring system to self-learn and continuously evolve. It is particularly emphasized that the present scheme fully considers the application characteristics of artificial intelligence algorithms in the field of bridge monitoring, such as adaptive processing of sensor data of different positions and types by using dynamic weight fusion technology, construction of continuous displacement field by Kriging spatial interpolation algorithm, differentiation between environmental and structural factors by space-time feature extraction and pattern classification algorithm, and quantification of system uncertainty based on entropy value theory. These algorithm characteristics are deeply combined with the professional needs of bridge displacement monitoring, optimized and designed in view of the high-dimensional, multi-source and nonlinear characteristics of displacement data, and the precision, intelligence level and adaptability of monitoring are significantly improved.

[0130] Reference Figure 3 In the embodiment of the present application, a computer device is also provided, which can be a server, and the internal structure thereof can be as shown in Figure 3The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store corresponding data in the embodiment. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the above method.

[0131] Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied.

[0132] The computer readable storage medium in the embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to the memory, storage, database or other medium provided by the present application and used in the embodiments can include non-volatile and / or volatile memory. The non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. The volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM, etc.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0135] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0136] The above-described and above-mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A bridge displacement remote intelligent monitoring method, characterized in that, The bridge displacement remote intelligent monitoring method comprises: The bridge displacement remote intelligent monitoring method comprises: According to the original displacement data packet, a dynamic weight fusion technology is used to denoise and identify abnormal values of displacement data of different positions and types, and a three-dimensional displacement field is constructed by using a Kriging interpolation method to generate a real-time bridge displacement digital twin model; According to the real-time bridge displacement digital twin model, displacement space-time features are extracted and mode classification processing is performed to distinguish between environmental response displacement and structural response displacement, including: extracting displacement time series from the real-time bridge displacement digital twin model, and constructing a multi-dimensional displacement feature vector; The multi-dimensional displacement feature vector is subjected to time domain and frequency domain transformation to obtain a displacement waveform feature set and a frequency component table; the displacement waveform feature set is time-series matched with real-time meteorological data to calculate displacement-temperature sensitivity coefficients and displacement-wind speed correlation degrees; based on the displacement-temperature sensitivity coefficients and the displacement-wind speed correlation degrees, an environmental factor influence separation matrix is constructed; the original displacement data is subjected to decomposition operation through the environmental factor influence separation matrix to separate the displacement into the environmental response displacement and the structural response displacement; the environmental response displacement and the structural response displacement are subjected to spatial distribution characteristic analysis to form a displacement mode feature library; Based on the environmental response displacement and the structural response displacement, a displacement deviation index is calculated and fatigue damage accumulation estimation is performed to form a bridge health state report; According to the bridge health state report, a displacement risk entropy value is calculated and an early warning level is set to generate a graded disposal scheme; The displacement change after implementation of the graded disposal scheme is subjected to improvement rate index calculation, a monitoring parameter configuration table is updated, and monitoring closed-loop optimization is completed.

2. The bridge displacement remote intelligent monitoring method according to claim 1, characterized in that, The grouping polling sampling of the sensors of the key structural parts of the bridge by setting multi-stage trigger thresholds to obtain the original displacement data packet comprises: Based on a bridge historical stress distribution map, sensor deployment positions are determined, and monitoring point arrangements are made for key parts of a main girder, a pier, an abutment and a cable tower; The sensors are divided into a displacement sensor group, an inclination sensor group and a strain sensor group according to functional types, corresponding sampling time windows are allocated, and a sensor polling table is formed; Three-stage trigger threshold value sets are set for each sensor group, which are a low-stage threshold, a middle-stage threshold and a high-stage threshold, and low-frequency sampling parameters, middle-frequency sampling parameters and high-frequency sampling parameters are correspondingly configured; According to temperature, humidity and wind speed information contained in real-time environmental data, trigger thresholds of each sensor group are dynamically adjusted to generate environmental compensation threshold coefficients; According to the sensor polling table and the environmental compensation threshold coefficients, grouping polling sampling is performed to collect physical parameters of each monitoring point; The collected physical parameters are subjected to data encryption and marking, time stamps and position information are marked, and the original displacement data packet is packaged.

3. The bridge displacement remote intelligent monitoring method according to claim 1, characterized in that, The grouping polling sampling of the sensors of the key structural parts of the bridge by setting multi-stage trigger thresholds to obtain the original displacement data packet comprises: Multi-source displacement data in the original displacement data packet are subjected to multi-scale time alignment processing to generate a time-synchronized displacement matrix; Time-domain statistical features are calculated for the time-synchronized displacement matrix through a sliding window technique to construct a displacement fluctuation feature set; Based on the displacement fluctuation feature set, a Mahalanobis distance method is used to identify abnormal points, and after removing abnormal values, an effective displacement data set is formed; According to the structural importance and data quality indicators of each monitoring point, a dynamic fusion weight coefficient is calculated, and the effective displacement data set is subjected to weighted processing; The weighted effective displacement data set is input into a Kriging spatial interpolation processor to calculate the displacement values of non-monitoring points through semi-variogram analysis and optimal linear unbiased estimation; The displacement data of all monitoring points and interpolation points are mapped to a bridge three-dimensional structure model to form the real-time bridge displacement digital twin model.

4. The bridge displacement remote intelligent monitoring method according to claim 1, characterized in that, Based on the environmental response displacement and the structural response displacement, a displacement deviation index is calculated and fatigue damage accumulation is estimated to form a bridge health state report, including: The environmental response displacement is compared with the normal range values in the historical environmental response database to calculate an environmental deviation rate; The structural response displacement is subjected to time window segmentation to extract displacement amplitude sequences and frequency variation characteristics to form a structural displacement feature table; According to the environmental deviation rate and the structural displacement feature table, a comprehensive weight matrix is constructed to quantify the displacement abnormality degree of each monitoring point to generate the displacement deviation index; The structural response displacement is subjected to rainflow counting processing to count the displacement amplitude occurrence frequency and cycle times to form a displacement stress spectrum; According to the mapping relationship between the displacement stress spectrum and the material fatigue curve, the fatigue damage values of each key component are calculated according to the linear damage accumulation principle to construct a damage distribution map; The displacement deviation index and the damage distribution map are combined with the bridge structure importance rating to generate the bridge health state report through multi-level weight superposition calculation.

5. The bridge displacement remote intelligent monitoring method according to claim 1, characterized in that, According to the bridge health state report, a displacement risk entropy value is calculated and a warning level is set to generate a hierarchical disposal scheme, including: Displacement deviation indexes and damage distribution parameters are extracted from the bridge health state report to establish a bridge risk assessment basic table; Uncertainty quantification analysis is performed on the data in the risk assessment basic table to calculate the displacement fluctuation and trend indicators of each monitoring point to form a monitoring point risk probability distribution; According to the dispersion degree and fluctuation range of the monitoring point risk probability distribution, the displacement risk entropy value is constructed to quantify the uncertainty level of the overall bridge system; The displacement risk entropy value is divided into a first-level warning, a second-level warning and a third-level warning according to a preset interval to determine the warning level; For different warning levels, a corresponding intervention measure set is matched from a preplan knowledge base, including speed limit and load limit measures, maintenance and reinforcement measures and emergency control measures; The intervention measure set is prioritized and combined and optimized in combination with the historical response characteristics of the bridge and the surrounding environmental conditions to generate the hierarchical disposal scheme.

6. The bridge displacement remote intelligent monitoring method according to claim 1, characterized in that, The displacement change after implementation of the hierarchical disposal scheme is subjected to improvement rate indicator calculation, the monitoring parameter configuration table is updated, and monitoring closed-loop optimization is completed, including: Record the bridge displacement data before and after the implementation of the hierarchical treatment scheme, and construct an intervention effect comparison data set; Perform time series comparison on the intervention effect comparison data set, calculate the displacement amplitude change percentage and abnormal point reduction rate, and form a displacement improvement quantification table; According to the displacement improvement quantification table, combined with the structure importance weight of each monitoring point, the comprehensive improvement rate index is calculated; Based on the improvement rate index, the effectiveness of different types of intervention measures is ranked and evaluated, and an intervention measure effect evaluation library is established; According to the historical data in the intervention measure effect evaluation library, adjust the sensor sampling strategy, trigger threshold and early warning level judgment standard, and update the monitoring parameter configuration table; Apply the updated monitoring parameter configuration table to the next monitoring period, start a new round of data collection and analysis process, and complete the monitoring closed-loop optimization.

7. A bridge displacement remote intelligent monitoring system for implementing the bridge displacement remote intelligent monitoring method according to any one of claims 1 to 6, characterized in that, The bridge displacement remote intelligent monitoring system comprises: A sampling module for polling and sampling sensors at key structural parts of the bridge by setting multiple trigger thresholds to obtain raw displacement data packets; An identification module for denoising and outlier identification of displacement data at different positions and types using dynamic weight fusion technology based on raw displacement data packets, and for constructing a three-dimensional displacement field using Kriging interpolation method to generate a real-time bridge displacement digital twin model; A classification module for extracting displacement spatio-temporal features and performing pattern classification processing based on the real-time bridge displacement digital twin model to distinguish between environmental response displacement and structural response displacement, including: extracting displacement time series from the real-time bridge displacement digital twin model to construct a multi-dimensional displacement feature vector; performing time domain and frequency domain transformation on the multi-dimensional displacement feature vector to obtain displacement waveform feature set and frequency component table; time sequence matching the displacement waveform feature set with real-time meteorological data to calculate displacement-temperature sensitivity coefficient and displacement-wind speed correlation degree; constructing an environmental factor influence separation matrix based on the displacement-temperature sensitivity coefficient and displacement-wind speed correlation degree; decomposing the original displacement data through the environmental factor influence separation matrix to separate the displacement into the environmental response displacement and the structural response displacement; analyzing the spatial distribution characteristics of the environmental response displacement and the structural response displacement to form a displacement pattern feature library; An estimation module for calculating displacement deviation index and fatigue damage accumulation estimation based on environmental response displacement and structural response displacement to form a bridge health status report; A hierarchical module for calculating displacement risk entropy value and setting early warning levels based on the bridge health status report to generate a hierarchical treatment scheme; A calculation module for calculating the improvement rate index of displacement change after the implementation of the hierarchical treatment scheme, updating the monitoring parameter configuration table, and completing the monitoring closed-loop optimization.

8. A computer device, comprising: A memory and a processor, the memory stores a computer program executable on the processor, characterized in that the processor executes the computer program to realize the bridge displacement remote intelligent monitoring method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, which, when executed by a processor, causes the processor to carry out the bridge displacement remote intelligent monitoring method according to any one of claims 1 to 6.

Images