Road bridge displacement monitoring method and system based on Internet of Things

Abstract

The invention provides a road bridge displacement monitoring method and system based on the Internet of Things, and relates to the technical field of the Internet of Things, and the method comprises the steps: obtaining an electrical vibration signal generated by a road bridge, forming an original vibration data set, packaging the original vibration data set, obtaining a packaged data package, carrying out the integrity verification, and obtaining a verified data package; according to a pre-stored bridge vibration measurement benchmark database, noise reduction and time sequence alignment processing are carried out on the verified electrical vibration signals in the verified data packet, a vibration sequence is generated, then the displacement trend is analyzed, a displacement trend data set is obtained, feature parameters are extracted, candidate displacement modes are extracted from historical displacement records according to the feature parameters, and the candidate displacement modes are stored in the bridge vibration measurement benchmark database. Generating a pattern recognition result; and comparing the displacement change parameter of the result with the vibration baseline range parameter list, and generating a structure safety early warning instruction containing an abnormal position and an abnormal degree, thereby realizing real-time and accurate monitoring and abnormal early warning of the road and bridge displacement.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things, and in particular to a road and bridge displacement monitoring method and system based on Internet of Things. BACKGROUND

[0002] With the acceleration of urbanization and the continuous expansion of the transportation network, the safety of road and bridge as a key infrastructure is increasingly concerned. In the long-term service process, the bridge structure is affected by multiple factors such as vehicle load, environmental erosion, and geological activity, and is prone to small but cumulative displacement deformation. If it is not found in time, it may evolve into structural damage or even collapse accident.

[0003] At present, there are bridge displacement monitoring schemes based on distributed optical fiber sensing and cloud computing cooperation in research and application. By deploying optical fiber sensor network at key parts of the bridge, the phase shift of optical signal caused by strain change is captured in real time, and the original spectrum data is uploaded to the remote cloud platform for centralized signal demodulation and displacement trend modeling, so as to realize the macroscopic evaluation of the overall deformation state of the bridge. However, the existing scheme exposes the problems of data processing lag and high communication load in actual deployment. Since all original sensing data need to be uploaded to the remote server for analysis, there is a significant delay between signal acquisition and generation of warning information, which is difficult to meet the demand of rapid response in emergency; the continuous transmission of massive spectrum data causes great pressure on communication bandwidth, especially in the multi-point concurrent monitoring scene, which easily causes network congestion and affects system stability. SUMMARY

[0004] The purpose of the present application is to provide a road and bridge displacement monitoring method and system based on Internet of Things, to solve the problems in the prior art that it is difficult to meet the demand of rapid response in emergency; the communication load is too high, and network congestion is easily caused in the multi-point concurrent monitoring scene, and the system stability is insufficient.

[0005] To solve the above technical problems, in a first aspect, the present application provides a road and bridge displacement monitoring method based on Internet of Things, comprising: Obtaining an electrical vibration signal generated by a road and bridge, forming an original vibration data set according to the time stamp and spatial coordinate information of the electrical vibration signal, and the electrical vibration signal is obtained by converting the vibration mechanical energy generated by the traffic load; Encapsulating the original vibration data set to obtain an encapsulated data packet, and using an edge computing node deployed locally on the road and bridge to perform integrity check on the encapsulated data packet to obtain a checked data packet; According to a pre-stored bridge vibration measurement reference database, the checked electrical vibration signal in the checked data packet is processed by noise reduction and time sequence alignment to generate a vibration sequence; Based on the vibration sequence, a dynamic displacement change rate is calculated to analyze a displacement trend, and a displacement trend dataset is obtained; From the displacement trend dataset, a feature parameter is extracted, and a candidate displacement mode is extracted from a pre-stored historical displacement record according to the feature parameter, so as to generate a mode recognition result; The displacement change parameter in the mode recognition result is compared with a pre-stored vibration baseline range parameter list, and a structure safety early warning instruction containing an abnormal position and an abnormal degree is generated.

[0006] Optionally, a feature parameter is extracted from the displacement trend dataset, and a candidate displacement mode is extracted from a pre-stored historical displacement record according to the feature parameter, so as to generate a mode recognition result, including: From the displacement trend dataset, a feature parameter of each continuous time period is extracted, and the feature parameter includes a maximum cumulative displacement change rate, a longest duration, and an interval number of direction conversion; According to the feature parameter, a plurality of candidate displacement modes are extracted from a pre-stored historical displacement record, and the historical displacement record contains typical displacement modes corresponding to different traffic load types; According to the time range of the displacement trend dataset, the time correlation of the candidate displacement mode and the displacement trend is judged, so as to generate a mode recognition result.

[0007] Optionally, according to the feature parameter, a plurality of candidate displacement modes are extracted from a pre-stored historical displacement record, and the historical displacement record contains typical displacement modes corresponding to different traffic load types, including: From the pre-stored historical displacement record, an initial typical displacement mode and a corresponding feature parameter range are selected, and the feature parameter range includes an upper limit of the maximum cumulative displacement change rate, a lower limit of the maximum cumulative displacement change rate, a longest duration interval, and an interval number of direction conversion allowed to be converted; The initial typical displacement mode with the maximum cumulative displacement change rate of the feature parameter between the upper limit of the maximum cumulative displacement change rate and the lower limit of the maximum cumulative displacement change rate is marked as a first screening mode, the first screening mode with the longest duration of the feature parameter in the longest duration interval is marked as a second screening mode, and the second screening mode with the interval number of displacement change direction conversion of the feature parameter less than the interval number of direction conversion allowed to be converted is marked as a third screening mode; When there are a plurality of third screening modes, a third screening mode with a matching degree higher than a preset matching degree is selected as a candidate displacement mode.

[0008] Optionally, according to the time range of the displacement trend dataset, the time correlation of the candidate displacement mode and the displacement trend is judged, so as to generate a mode recognition result, including: determining a time range of the displacement trend dataset, and calculating a total duration of the time range; extracting a historical time range corresponding to each candidate displacement mode in the pre-stored historical displacement record, and calculating a historical total duration of the historical time range, combining the total duration, and calculating a time overlap ratio; dividing the time range into a plurality of displacement trend periods, each corresponding to displacement change information in the displacement trend dataset, and dividing the historical time range into a plurality of mode historical periods, each corresponding to historical displacement change information in the candidate displacement mode; comparing the displacement change characteristics of the displacement trend periods and the mode historical periods overlapping on the time axis to calculate a period characteristic matching ratio; judging the candidate displacement mode corresponding to the time overlap ratio exceeding a preset time ratio threshold and the period characteristic matching ratio exceeding a preset matching ratio threshold as having a time correlation with the displacement trend; If there are multiple candidate displacement modes having a time correlation, the candidate displacement mode with the largest sum of the time overlap ratio and the period characteristic matching ratio is determined as the main correlation mode, and if all candidate displacement modes have no time correlation with the displacement trend, a no-match identifier is generated; Integrating each mode and the corresponding time overlap ratio, period characteristic matching ratio, overlapping period information, or no-match identifier to form a mode recognition result, each mode including the main correlation mode and the candidate displacement mode without time correlation.

[0009] Optionally, according to the pre-stored bridge vibration measurement benchmark database, the post-verification data packet is subjected to noise reduction and time sequence alignment processing to generate a vibration sequence, including: From the pre-stored bridge vibration measurement benchmark database, the benchmark vibration signal corresponding to the post-verification electrical vibration signal in the post-verification data packet is retrieved; The post-verification electrical vibration signal and the benchmark vibration signal are compared segment by segment to remove vibration difference signals with amplitude differences exceeding a preset threshold to obtain a preliminary processed signal; According to the timestamp information of the post-verification electrical vibration signal, the time interval between different post-verification electrical vibration signals is determined; According to the time interval, the starting record time of each preliminary processed signal is adjusted to obtain an adjusted preliminary processed signal, and the adjusted preliminary processed signal is arranged to form a vibration sequence.

[0010] Optionally, based on the vibration sequence, a dynamic displacement change rate is calculated to analyze the displacement trend to obtain a displacement trend dataset, including: extracting the vibration amplitude and corresponding time information of each recording time from the vibration sequence to form vibration time series data containing time-amplitude correspondence; calculating the time difference and vibration amplitude difference between adjacent recording times in the vibration time series data to form a displacement change rate time series sequence based on the time difference and vibration amplitude difference; determining the displacement variation direction in the corresponding time period according to the positive and negative attributes of each displacement change rate in the displacement change rate time series sequence; determining the time range and cumulative displacement change rate of the continuous time period with the same displacement variation direction, and summarizing the time range and cumulative displacement change rate of the continuous time period with different displacement variation directions to form a displacement trend data set.

[0011] Optionally, the displacement change parameter in the pattern recognition result is compared with a pre-stored vibration baseline range parameter list to generate a structure safety warning instruction containing an abnormal position and an abnormal degree, including: extracting the displacement change parameter from the pattern recognition result, the displacement change parameter including the maximum cumulative displacement change rate, the abnormal duration, and the direction conversion frequency; comparing the maximum cumulative displacement change rate of the displacement change parameter with the corresponding normal fluctuation upper limit and normal fluctuation lower limit in the pre-stored vibration reference range parameter list to mark the target parameter that exceeds the range; comparing the abnormal duration of the target parameter with the corresponding allowed duration in the vibration reference range parameter list to record the time period information that exceeds the allowed duration; locating the abnormal occurrence position of the bridge structure according to the target parameter and the corresponding spatial coordinate information; calculating the numerical difference between the target parameter and the corresponding reference parameter in the vibration reference range parameter list, and dividing the abnormal degree level in combination with a pre-set difference interval standard; integrating the abnormal occurrence position of the bridge structure, the abnormal degree level, the target parameter, and the time period information to generate a structure safety warning instruction.

[0012] In a second aspect, the present application provides a road and bridge displacement monitoring system based on Internet of Things, comprising: An acquisition module is configured to acquire an electrical vibration signal generated by a road and bridge, and form an original vibration data set according to the time stamp and spatial coordinate information of the electrical vibration signal, wherein the electrical vibration signal is converted from vibration mechanical energy generated by traffic load; The encapsulation and verification module is configured to encapsulate the original vibration data set to obtain an encapsulated data packet, and to perform integrity verification on the encapsulated data packet by using an edge computing node deployed locally on the road bridge to obtain a verified data packet; The processing module is configured to perform noise reduction and time alignment processing on the verified electrical vibration signal in the verified data packet according to a pre-stored bridge vibration measurement reference database to generate a vibration sequence. The analysis module is configured to calculate a dynamic displacement change rate based on the vibration sequence to analyze a displacement trend to obtain a displacement trend data set. The extraction module is configured to extract a feature parameter from the displacement trend data set, to extract a candidate displacement mode from a pre-stored historical displacement record according to the feature parameter, and to generate a mode recognition result. The generation module is configured to compare the displacement change parameter in the mode recognition result with a pre-stored vibration baseline range parameter list to generate a structure safety early warning instruction containing an abnormal position and an abnormal degree.

[0013] In a third aspect, the present application provides an electronic device, comprising: A memory configured to store a computer program; A processor configured to execute the computer program to implement the steps of the road bridge displacement monitoring method based on the Internet of Things according to the first aspect.

[0014] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executable by a processor to implement the steps of the road bridge displacement monitoring method based on the Internet of Things according to the first aspect.

[0015] The road bridge displacement monitoring method based on the Internet of Things provided in the application realizes accurate spatiotemporal correlation collection of the dynamic response of the bridge structure by obtaining the electrical vibration signals generated by the road bridge, forming an original vibration data set and encapsulating, obtaining the encapsulated data packet and performing integrity checking, obtaining the checked data packet, provides an original basis with position and time dimensions for subsequent analysis, and preliminary quality control can be completed before data transmission, avoiding the transmission of incorrect or damaged data into the subsequent processing flow and improving the overall data reliability of the system. According to the pre-stored bridge vibration measurement benchmark database, the noise reduction and time sequence alignment processing of the checked electrical vibration signals in the checked data packet can eliminate environmental noise interference and unify the time reference of multiple source signals, thereby generating a vibration sequence with high signal-to-noise ratio and time synchronization, laying a foundation for accurate displacement analysis. According to the vibration sequence, the displacement trend is analyzed to obtain a displacement trend data set, realizing the transformation from the original vibration signal to the evolution trend of the structural displacement, and enhancing the continuity of the description of the structural deformation process. Feature parameters are extracted from the displacement trend data set, and candidate displacement modes are matched by combining the pre-stored historical displacement records, which can identify the similarity between the current structural behavior and the typical deformation mode, and improve the recognition ability of complex displacement behavior. The displacement change parameters in the result are compared with the vibration baseline range parameter list to generate a structure safety warning instruction containing the abnormal position and abnormal degree, realizing the closed-loop response from data analysis to risk discrimination, and improving the positioning accuracy and operability of the warning information. Further, by extracting multi-dimensional feature parameters including the maximum cumulative displacement change rate, duration and direction conversion frequency from the displacement trend data set, combining the typical displacement modes corresponding to different traffic loads in the historical displacement records, performing mode matching, and further judging the time sequence correlation of the candidate displacement mode and the current displacement trend according to the time range, a mode recognition result with better context understanding ability is generated, the semantic understanding ability of the system to the structural displacement behavior is enhanced, and the system can distinguish between normal operation deformation and potential abnormal deformation under complex traffic excitation, and the false alarm or missed alarm problem caused by simply relying on threshold judgment is alleviated. At the same time, by introducing the time correlation judgment mechanism, the timeliness and situational adaptability of the mode recognition are improved, so that the system can realize intelligent discrimination of the evolution trend of the structural state locally without relying on a remote data center, thereby breaking through the technical bottlenecks of response delay and heavy communication burden caused by centralized processing in the prior art, and improving the real-time performance and autonomous decision-making ability of the monitoring system. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to make the technical scheme of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiment or prior art description will be briefly introduced. Obviously, the accompanying drawings described are only part of the embodiments of the present application and not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of the present application.

[0017] Figure 1 A flowchart of a road and bridge displacement monitoring method based on the Internet of Things provided by the embodiments of the present application is shown in the figure. Figure 2 A specific implementation schematic diagram of a road and bridge displacement monitoring method based on the Internet of Things provided by the embodiments of the present application is shown in the figure. Figure 3 A structural schematic diagram of a road and bridge displacement monitoring system based on the Internet of Things provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0018] The prior art relies on continuously uploading a large amount of raw spectral data to a remote cloud platform for centralized demodulation and analysis, resulting in high bandwidth occupation of data transmission, easy congestion in multi-point concurrency or poor network conditions, and obvious delay in signal processing and early warning generation, which is difficult to meet the real-time response demand of sudden structural abnormalities. At the same time, the system is highly dependent on the central server, and lacks local autonomous processing capability when communication is interrupted or the cloud is faulty. The overall architecture faces great challenges in real-time performance, stability and deployment flexibility. The present application builds an Internet of Things monitoring framework based on edge computing, uses local nodes to complete data verification, noise reduction, time sequence alignment and vibration signal to displacement trend conversion, and combines historical pattern matching and baseline comparison mechanism to realize abnormal identification and early warning generation at the front end, forming a local closed loop of perception, analysis and decision, thereby reducing the dependence on remote communication and central computing resources and improving the system response speed and operation reliability.

[0019] In order to make the technical scheme of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiment or prior art description will be briefly introduced. Obviously, the accompanying drawings described are only part of the embodiments of the present application and not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of the present application.

[0020] The core of the present application is to provide a road and bridge displacement monitoring method based on the Internet of Things, and a flowchart of a specific implementation method thereof is shown in the figure. Figure 1 The method comprises: Step 101: Obtain an electrical vibration signal generated by a road bridge, and form an original vibration data set according to a timestamp and spatial coordinate information of the electrical vibration signal, wherein the electrical vibration signal is converted from vibration mechanical energy generated by a traffic load.

[0021] In this step, the electrical vibration signal refers to an electrical signal converted from mechanical energy generated by vibration of a road bridge through a sensor, including electrical signal data reflecting vibration intensity, frequency and other characteristics. The spatial coordinate information refers to coordinate data used to identify the position of the vibration signal collection on the road bridge, including specific position parameters obtained based on a preset coordinate system, used to determine the specific location of vibration occurrence. The original vibration data set refers to a set of integrated electrical vibration signals, corresponding timestamps and spatial coordinate information, including all initially collected data related to bridge vibration. The traffic load refers to various loads acting on the road bridge, including forces generated by vehicle driving, pedestrian passing and the like, which can cause vibration of the bridge. The vibration mechanical energy refers to mechanical energy possessed by vibration generated by the traffic load and the like of the road bridge.

[0022] In the embodiment of the present application, a vibration sensor is installed at a key structural part of the road bridge, which can convert vibration mechanical energy caused by the traffic load (such as load generated by vehicle driving, pedestrian passing and the like) acting on the bridge into an electrical vibration signal, and record the corresponding timestamp (i.e. the specific time when the electrical vibration signal is generated) and spatial coordinate information (i.e. the installation position coordinate of the vibration sensor on the road bridge) of each electrical vibration signal. These signals, timestamps and spatial coordinate information are integrated together to form an original vibration data set.

[0023] Step 102: Package the original vibration data set to obtain a packaged data packet, and use an edge computing node deployed locally on the road bridge to perform integrity checking on the packaged data packet to obtain a checked data packet.

[0024] In this step, the packaged data packet refers to a data set formed by packaging the original vibration data set according to a certain format, including the original vibration data after the packaging operation, facilitating data transmission and processing. The checked data packet refers to the packaged data packet after integrity checking by the edge computing node, including data packets confirmed to be complete and error-free, ensuring the reliability of subsequent processing data.

[0025] In the embodiment of the present application, the original vibration data set is packaged according to a preset data format to obtain a packaged data packet; then, the edge computing node deployed locally on the road bridge is used to perform integrity checking on the packaged data packet, specifically to check whether the data packet has data loss, data error and the like, and the data packet confirmed to be complete and error-free after checking is the checked data packet.

[0026] Step 103: According to the pre-stored bridge vibration measurement benchmark database, the post-verification data packet is processed to generate a vibration sequence.

[0027] In this step, the pre-stored bridge vibration measurement benchmark database refers to a database of pre-stored vibration-related data of a road bridge in a normal state, including benchmark signals reflecting the normal vibration characteristics of the road bridge, etc., which is used as a comparison standard for processing the collected vibration signals. The post-verification electrical vibration signal refers to the electrical vibration signal contained in the post-verification data packet, including the vibration electrical signal that has passed the integrity verification, which is the basis for subsequent noise reduction and time sequence alignment processing. The vibration sequence refers to a set of vibration signals arranged in chronological order after noise reduction and time sequence alignment processing, including the sorted vibration signal data, which is used for subsequent calculation of dynamic displacement change rate.

[0028] Step 104: Based on the vibration sequence, calculate the dynamic displacement change rate to analyze the displacement trend and obtain a displacement trend dataset.

[0029] In this step, the displacement trend dataset refers to a set of displacement trend-related data of the road bridge, which is used to analyze the overall change of the displacement of the road bridge.

[0030] Step 105: Extract feature parameters from the displacement trend dataset, and according to the feature parameters, extract candidate displacement patterns from pre-stored historical displacement records to generate a pattern recognition result.

[0031] In this step, the feature parameters refer to data extracted from the displacement trend dataset that can reflect the characteristics of the displacement trend, including the maximum cumulative displacement change rate, the longest duration, and the interval number of direction conversion, etc., which are used to describe the key features of the displacement trend. The pre-stored historical displacement record refers to the pre-stored record data of the past displacement change of the road bridge, including the corresponding typical displacement patterns under different traffic load types, etc., which is used to provide a reference for extracting candidate displacement patterns. The candidate displacement pattern refers to the displacement pattern extracted from the pre-stored historical displacement record that matches the current displacement trend feature parameters, including the historical displacement pattern that may conform to the current displacement change. The pattern recognition result refers to the result obtained by judging the time correlation between the candidate displacement pattern and the current displacement trend.

[0032] Step 106: Compare the displacement change parameters in the pattern recognition result with the pre-stored vibration baseline range parameter list to generate a structure safety warning instruction containing abnormal position and abnormal degree.

[0033] In this step, the displacement change parameter refers to a parameter reflecting the displacement change of the road bridge, including the maximum cumulative displacement change rate, the abnormal duration and the direction conversion frequency, etc., for judging whether the displacement of the road bridge is abnormal. The vibration baseline range parameter list refers to a list of reasonable ranges of the displacement change parameters of the road bridge in the normal state, which is used as a standard for judging whether the displacement is abnormal. The structure safety warning instruction refers to an instruction generated when the displacement change parameter of the road bridge exceeds the vibration baseline range, including the abnormal position, the abnormal degree, etc., for prompting the possible safety hazards of the road bridge.

[0034] The embodiment of the present application reduces the delay of data transmission to the remote platform by locally deploying the edge computing node on the road bridge, improves the real-time performance of monitoring, and can quickly respond to emergencies. The reliability of the data is ensured by encapsulating and integrity checking the data. The accuracy of displacement monitoring and abnormality judgment is improved by processing and comparing based on the pre-stored bridge vibration measurement benchmark database and historical displacement records. The remote transmission of massive data is reduced, the pressure on the communication bandwidth is reduced, network congestion is avoided, the stability of the system is enhanced, the displacement deformation of the bridge can be found more timely, and the occurrence of structural damage or even collapse accidents is prevented.

[0035] The present application provides a specific embodiment, step 103, according to the pre-stored bridge vibration measurement benchmark database, the noise reduction and time sequence alignment processing of the checked electrical vibration signal in the checked data packet are carried out, and the vibration sequence is generated, which specifically includes the following steps: Step 301: From the pre-stored bridge vibration measurement benchmark database, the reference vibration signal corresponding to the checked electrical vibration signal in the checked data packet is retrieved.

[0036] In this step, the reference vibration signal refers to the vibration signal of the bridge in the normal state corresponding to the checked electrical vibration signal retrieved from the pre-stored bridge vibration measurement benchmark database, including signal data reflecting the normal vibration characteristics of the bridge at the same collection position and time period, which is used as a comparison standard for processing the checked electrical vibration signal.

[0037] In the embodiment of the present application, according to the collection position, collection time period and other information of the checked electrical vibration signal, the vibration signal of the road bridge in the normal state under the same condition, i.e. the reference vibration signal, is searched in the pre-stored bridge vibration measurement benchmark database, which is used as the comparison reference.

[0038] Step 302: The checked electrical vibration signal is compared with the reference vibration signal in sections to remove the vibration difference signal with an amplitude difference exceeding the preset threshold, and the preliminary processed signal is obtained.

[0039] In this step, the amplitude difference refers to the difference between the amplitudes of the electrical vibration signal after verification and the reference vibration signal in the same time period, including data reflecting the deviation degree of the two signals in vibration intensity, for judging whether the signal is abnormal. The preset threshold refers to a numerical standard preset for judging whether the amplitude difference exceeds the normal range, including the maximum allowed amplitude deviation value determined based on the normal vibration characteristics of the bridge, for distinguishing between normal signals and vibration difference signals. The vibration difference signal refers to the signal part in the electrical vibration signal after verification, whose amplitude difference with the reference vibration signal exceeds the preset threshold, including signal segments deviating from the normal range caused by noise, abnormal vibration and other factors, which need to be removed to achieve noise reduction. The preliminary processed signal refers to the signal obtained after removing the vibration difference signal from the electrical vibration signal after verification, including the signal part remaining within the preset threshold range of the amplitude difference with the reference vibration signal, which is the result of preliminary noise reduction processing.

[0040] In the embodiment of the present application, the signal comparison technique is used to divide the two signals into multiple segments according to a fixed time length, calculate the amplitude difference of each corresponding segment (i.e. the difference between the amplitude of the electrical vibration signal after verification and the amplitude of the reference vibration signal), and determine that the segment is a vibration difference signal when the amplitude difference exceeds the preset threshold, and remove it. The remaining signal part is the preliminary processed signal.

[0041] Step 303: According to the timestamp information of the electrical vibration signal after verification, determine the time interval between different electrical vibration signals after verification.

[0042] In this step, the timestamp information refers to the time data recording the time when the electrical vibration signal after verification is generated, including the specific time point accurate to seconds or milliseconds, for determining the time attribute of the signal. The time interval refers to the time difference between different electrical vibration signals after verification, including the interval of the recording time calculated based on the timestamp information, for reflecting the time law of signal collection.

[0043] In the embodiment of the present application, according to the timestamp information of the electrical vibration signal after verification, the recording time corresponding to each electrical vibration signal after verification is extracted, and the time interval between different electrical vibration signals after verification is determined by calculating the difference between the recording times of different electrical vibration signals after verification.

[0044] Step 304: According to the time interval, adjust the starting recording time of each preliminary processed signal to obtain an adjusted preliminary processed signal, and arrange the adjusted preliminary processed signal to form a vibration sequence.

[0045] In this step, the initial recording time point refers to the time point when the preliminary processing signal starts to be recorded, including the initial position of each preliminary processing signal on the time axis, for adjusting the time alignment of the preliminary processing signal. The adjusted preliminary processing signal refers to the preliminary processing signal after the initial recording time point is adjusted, including signal parts arranged in uniform time intervals on the time axis, laying the foundation for forming the vibration sequence.

[0046] In the embodiment of the present application, according to the determined time interval, a time sequence adjustment technology is adopted, taking the initial recording time point of one of the preliminary processing signals as a reference, adjusting the initial recording time points of the other preliminary processing signals according to the time interval, so that all the preliminary processing signals maintain consistent intervals on the time axis, obtaining the adjusted preliminary processing signal, and then arranging these adjusted preliminary processing signals in time sequence to form the vibration sequence.

[0047] The embodiment of the present application can remove noise and abnormal components in the signal and improve signal quality by comparing the pre-stored reference vibration signal with the verified electrical vibration signal for noise reduction. The time sequence alignment of the signal is realized by determining the time interval and adjusting the initial recording time point through the timestamp information, forming a regular vibration sequence, providing an accurate and consistent data basis for subsequent dynamic displacement change rate calculation, reducing analysis errors caused by signal quality problems and time misalignment, and further improving the reliability and accuracy of the entire monitoring scheme, which helps to alleviate the processing lag and analysis deviation problems caused by low data quality.

[0048] The present application provides a specific embodiment, step 104, based on the vibration sequence, calculating the dynamic displacement change rate to analyze the displacement trend, obtaining the displacement trend data set, specifically including the following steps: Step 401: Extract the vibration amplitude and corresponding time information of each recording time point from the vibration sequence to form vibration time sequence data containing time amplitude correspondence.

[0049] In this step, the vibration amplitude refers to the intensity value of the vibration signal at a certain recording time point, including the physical quantity reflecting the strength of the bridge vibration at that time, which is converted based on the electrical vibration signal detected by the sensor. The time information refers to the specific time data corresponding to the recording of the vibration amplitude, including the time point accurate to seconds or milliseconds, for identifying the time position of the vibration amplitude. The time amplitude correspondence refers to the one-to-one correspondence between the time information and the vibration amplitude in the vibration time sequence data, including the mapping relationship of each time point associated with a unique vibration amplitude, for reflecting the change law of vibration with time. The vibration time sequence data refers to the data set containing the time information and the vibration amplitude correspondence, including the vibration amplitude and the corresponding time in time sequence, for subsequent calculation of displacement change rate.

[0050] In the embodiment of the present application, the vibration intensity value (i.e. vibration amplitude) of each recording point in the vibration sequence and the time point (i.e. time information) corresponding to the recording point are read one by one, and each time point is one-to-one corresponding to the vibration amplitude corresponding thereto, to form the vibration time sequence data containing the corresponding relationship between time and amplitude.

[0051] In step 402, the time difference and vibration amplitude difference of adjacent recording time points in the vibration time sequence data are calculated, to form the displacement change rate time sequence based on the time difference and vibration amplitude difference.

[0052] In this step, the time difference refers to the time difference between two adjacent recording time points in the vibration time sequence data, which is used to calculate the displacement change in unit time. The vibration amplitude difference refers to the difference between the vibration amplitudes corresponding to two adjacent recording time points in the vibration time sequence data, which is used to reflect the change amount of vibration intensity at adjacent time points. The displacement change rate time sequence refers to a sequence composed of displacement change rates of each adjacent time period arranged in time sequence, which is used to reflect the change speed of displacement with time.

[0053] In the embodiment of the present application, two adjacent recording time points in the vibration time sequence data are first selected, the time difference is obtained by subtracting the time of the former time point from the time of the latter time point, and the vibration amplitude difference is obtained by subtracting the vibration amplitude of the former time point from the vibration amplitude of the latter time point. Then, the displacement change rate of the adjacent time period is obtained by dividing the vibration amplitude difference by the time difference, and the displacement change rates of all adjacent time periods are arranged in time sequence to form the displacement change rate time sequence.

[0054] In step 403, the displacement change direction in the corresponding time period is determined according to the positive and negative properties of each displacement change rate in the displacement change rate time sequence.

[0055] In this step, the displacement change rate refers to the vibration amplitude change amount in unit time, which includes the result of dividing the vibration amplitude difference by the time difference, and reflects the fast and slow degree of displacement change. The positive and negative properties refer to the properties of the displacement change rate being positive or negative, which include the properties for distinguishing the displacement change direction, the positive property corresponding to one direction and the negative property corresponding to the opposite direction. The displacement change direction refers to the displacement direction of the road and bridge structure in a certain time period, which includes the direction (such as upward, downward or stretching direction) determined based on the positive and negative properties of the displacement change rate, and is used to describe the trend of displacement.

[0056] In the embodiment of the present application, the value of each displacement change rate in the displacement change rate time sequence is judged one by one to be positive or negative. If it is positive, it is determined that the displacement change direction in the time period is the first direction (such as upward displacement of the bridge structure), and if it is negative, it is determined to be the second direction (such as downward displacement of the bridge structure).

[0057] Step 404: determining the time range and cumulative displacement change rate of the continuous time period with the same displacement change direction, and collecting the time range and cumulative displacement change rate of the continuous time period with different displacement change directions to form a displacement trend data set.

[0058] In this step, the continuous time period refers to a continuous interval composed of multiple adjacent time periods with the same displacement change direction, including a time interval from a starting time to an ending time without direction change, for analyzing the continuous change characteristics of displacement. The cumulative displacement change rate refers to the sum of all displacement change rates in the continuous time period, including the sum of displacement change rates of adjacent time periods in the time period, reflecting the cumulative effect of displacement change in the interval. The time range of the time period refers to the starting time and the ending time of the continuous time period, including time data defining the starting and ending points of the time period, for clearly defining the range of the interval with the same displacement change direction.

[0059] In the embodiment of the application, the interval with the same displacement change direction in the continuous multiple time periods is identified from the judgment result of the displacement change direction (i.e. the continuous time period), the ending time of the continuous time period is subtracted from the starting time to obtain the time range of the time period, and the sum of all displacement change rates in the interval is obtained to obtain the cumulative displacement change rate. The time range and cumulative displacement change rate of all continuous time periods with different displacement change directions are integrated together to form a displacement trend data set.

[0060] The embodiment of the application accurately quantifies the change speed of displacement with time by calculating the time difference, amplitude difference and displacement change rate of adjacent time points; clearly presents the trend rule of displacement by judging the displacement change direction and collecting the characteristics of the continuous time period, and forms a displacement trend data set, which provides a reliable basis for subsequent feature parameter extraction and pattern recognition.

[0061] The application provides a specific embodiment, step 105, extracting a feature parameter from the displacement trend data set, and extracting a candidate displacement pattern from a pre-stored historical displacement record according to the feature parameter to generate a pattern recognition result, specifically including the following steps: Step 501: extracting a feature parameter of each continuous time period from the displacement trend data set, the feature parameter including a maximum cumulative displacement change rate, a longest duration and an interval number of direction conversion.

[0062] In this step, the maximum cumulative displacement change rate refers to the maximum value of the cumulative displacement change rate extracted from each continuous time period in the displacement trend data set, including a parameter reflecting the most significant degree of displacement accumulation change in a certain continuous time period. The longest duration refers to the length of the time period with the longest duration among all continuous time periods in the displacement trend data set, including a parameter reflecting the longest time of displacement change in the same direction, for describing the stability of displacement change.

[0063] In the embodiment of the present application, from all continuous time periods included in the displacement trend data set, the maximum value of the cumulative displacement change rate is selected as the maximum cumulative displacement change rate; the continuous time period with the longest duration is found, and the duration is the longest duration; the number of time periods between adjacent displacement change direction conversions is counted to obtain the interval number of direction conversions, and the three parameters are integrated as the characteristic parameters of each continuous time period.

[0064] Step 502: According to the characteristic parameters, a plurality of candidate displacement modes are extracted from pre-stored historical displacement records, and the historical displacement records include typical displacement modes corresponding to different traffic load types.

[0065] In this step, the traffic load type refers to different load categories acting on the road bridge, including loads generated by different types of vehicles such as small cars, large trucks, and buses, which are classified based on load sources and size differences. The typical displacement mode refers to a representative displacement change rule in the pre-stored historical displacement record corresponding to a specific traffic load type, including a characteristic change process of the bridge displacement under the action of this type of load, which is used as a reference template for displacement trend comparison.

[0066] Step 503: According to the time range of the displacement trend data set, the time correlation between the candidate displacement mode and the displacement trend is judged to generate a mode recognition result.

[0067] In this step, the time range refers to the overall time interval corresponding to the displacement trend data set, including the complete time period from the starting time to the ending time of the displacement trend, for defining the time span of the displacement trend. The time correlation refers to the overlap or matching degree between the historical time interval of the candidate displacement mode and the time range of the displacement trend data set, including an attribute reflecting the close correlation of the two in the time dimension, for judging the relevance of the candidate mode and the current displacement trend.

[0068] The embodiment of the present application accurately captures the key features of displacement trend by extracting feature parameters, provides clear basis for pattern matching, realizes historical reference comparison of the current displacement trend based on feature parameters from historical records, further verifies the rationality of pattern matching through time correlation judgment, and improves the accuracy of pattern recognition results, thereby enhancing the understanding of the bridge displacement trend through historical pattern comparison, and providing a reliable foundation for subsequent safety warning.

[0069] The present application provides an embodiment, step 502, extracting a plurality of candidate displacement patterns from pre-stored historical displacement records according to the feature parameters, wherein the historical displacement records contain typical displacement patterns corresponding to different traffic load types, and specifically comprising the following steps: Step 511: selecting an initial typical displacement pattern and corresponding feature parameter range from the pre-stored historical displacement records, wherein the feature parameter range includes the upper limit of the maximum cumulative displacement change rate, the lower limit of the maximum cumulative displacement change rate, the longest duration interval, and the maximum number of direction conversion intervals.

[0070] In this step, the initial typical displacement pattern refers to the representative original displacement pattern corresponding to different traffic load types selected from the pre-stored historical displacement records, including the mode reflecting the basic change rule of bridge displacement under the action of a specific load, as the initial object for screening. The feature parameter range refers to the boundary or interval of the feature parameter corresponding to the initial typical displacement pattern, which is used to define the reasonable fluctuation range of the mode feature parameter as the screening basis. The upper limit of the maximum cumulative displacement change rate refers to the highest allowable value of the maximum cumulative displacement change rate in the feature parameter range, which is used to judge whether the current feature parameter meets the range of the mode. The lower limit of the maximum cumulative displacement change rate refers to the lowest allowable value of the maximum cumulative displacement change rate in the feature parameter range, which together with the upper limit forms the effective interval of the parameter. The longest duration interval refers to the interval formed by the starting value and the ending value of the longest duration in the feature parameter range, which is used to screen the mode that meets the time characteristics. The maximum number of direction conversion intervals refers to the maximum value of the number of allowed displacement direction conversion intervals in the feature parameter range, which is used to limit the stability characteristics of the mode.

[0071] In the embodiment of the present application, all representative displacement patterns associated with different traffic load types are retrieved from the historical displacement records as initial typical displacement patterns, and the boundary values of the feature parameters corresponding to each initial typical displacement pattern are extracted to form the feature parameter range, which includes the maximum value (the upper limit of the maximum cumulative displacement change rate) and the minimum value (the lower limit of the maximum cumulative displacement change rate) of the maximum cumulative displacement change rate, the starting and ending interval of the longest duration (the longest duration interval), and the maximum value of the allowed direction conversion interval (the maximum number of direction conversion intervals).

[0072] Step 512: Mark the initial typical displacement pattern in which the maximum cumulative displacement change rate of the characteristic parameter is between the upper limit of the maximum cumulative displacement change rate and the lower limit of the maximum cumulative displacement change rate as a first-level screening pattern, mark the first-level screening pattern in which the longest duration of the characteristic parameter is within the longest duration interval as a second-level screening pattern, and mark the second-level screening pattern in which the number of displacement change direction conversion intervals of the characteristic parameter is less than the number of allowed direction conversion intervals as a third-level screening pattern.

[0073] In this step, the first-level screening pattern refers to the initial typical displacement pattern screened by the maximum cumulative displacement change rate, including the pattern whose maximum cumulative displacement change rate is between the corresponding upper and lower limits, and is the first-stage result of the three-level screening. The second-level screening pattern refers to the pattern screened by the maximum duration from the first-level screening pattern, including the pattern whose maximum duration falls within the corresponding interval, and is the second-stage result of the three-level screening. The third-level screening pattern refers to the pattern screened by the number of direction change intervals from the second-level screening pattern, including the pattern whose number of direction change intervals is less than the number of allowed direction change intervals, and is the final stage result of the three-level screening.

[0074] In an embodiment of the present invention, three-level screening is performed to mark different screening modes. First, the maximum cumulative displacement change rate in the characteristic parameters of the displacement trend data set is compared with the upper and lower limits of the maximum cumulative displacement change rate of the initial typical displacement pattern. If the value is between the two, the corresponding initial typical displacement pattern is marked as a first-level screening mode; then, the mode whose longest duration falls within the longest duration interval is selected from the first-level screening mode and marked as a second-level screening mode; finally, the mode whose number of displacement change direction conversion intervals is less than the number of allowed direction conversion intervals is selected from the second-level screening mode and marked as a third-level screening mode.

[0075] Step 513: When there are multiple three-level screening patterns, a three-level screening pattern having a matching degree with the characteristic parameter higher than a preset matching degree is selected as a candidate displacement pattern.

[0076] In this step, the degree of match refers to the degree of agreement between the characteristic parameters of the three-level screening pattern and the characteristic parameters of the displacement trend dataset. This includes a similarity index calculated based on the difference between each parameter, which is used to measure the degree of match between the pattern and the current displacement trend. The preset degree of match refers to a pre-set standard value used to determine whether the match meets the standard. This includes a minimum similarity threshold determined based on historical matching results, which is used to determine candidate displacement patterns from the three-level screening patterns.

[0077] In the embodiment of the present application, the matching degree is obtained by calculating the fitting degree (such as the total sum of parameter difference ratio) of the characteristic parameters (maximum cumulative displacement change rate, longest duration, and direction conversion interval number) of each three-level screening mode and the characteristic parameters of the displacement trend data set, and the three-level screening mode with a matching degree greater than a pre-set matching degree standard (preset matching degree) is determined as the candidate displacement mode.

[0078] For example, in the monitoring of a bridge on an urban expressway, the pre-stored historical displacement records include initial typical displacement modes corresponding to three traffic load types: small trucks, large buses, and heavy trucks. First, the initial modes and the characteristic parameter ranges are retrieved: the upper limit of the maximum cumulative displacement change rate of the initial typical displacement mode of a small truck is 0.5 mm / s, the lower limit is 0.3 mm / s, the longest duration is 3-5 minutes, and the direction conversion interval number is 2 times; the corresponding parameters of the initial typical displacement mode of a large bus are 0.6-0.8 mm / s, 4-6 minutes, and 3 times; and the corresponding parameters of the initial typical displacement mode of a heavy truck are 0.9-1.2 mm / s, 5-8 minutes, and 2 times. Then, the characteristic parameters of the displacement trend data set (the maximum cumulative change rate is 0.7 mm / s, the longest duration is 5 minutes, and the direction conversion interval number is 2 times) are screened: in the first-level screening, 0.7 mm / s is within the 0.6-0.8 mm / s range of the large bus, so it is marked as a first-level screening mode; in the second-level screening, 5 minutes falls within the 4-6 minute range of the large bus, so it is marked as a second-level screening mode; and in the third-level screening, 2 times is less than the 3 times of the large bus, so it is marked as a third-level screening mode. It is assumed that the initial typical displacement mode of a medium truck is also a third-level screening mode after screening. Finally, the matching degrees of the two third-level screening modes and the current characteristic parameters are calculated: the matching degree of the initial typical displacement mode of the large bus is 90%, the matching degree of the initial typical displacement mode of the medium truck is 70%, and the pre-set matching degree is 80%, so the initial typical displacement mode of the large bus is selected as the candidate displacement mode.

[0079] The embodiment of the present application provides clear reference standards for mode screening by selecting initial typical displacement modes and characteristic parameter ranges; the three-level progressive screening gradually narrows the range, improving the accuracy of screening; the selection of the candidate mode based on the matching degree further ensures the relevance of the mode to the current displacement trend, and the multi-dimensional screening improves the reliability of the candidate mode, laying a high-quality foundation for subsequent time correlation judgment.

[0080] The present application provides a specific embodiment, step 503, according to the time range of the displacement trend data set, judging the time correlation of the candidate displacement mode and the displacement trend to generate a mode recognition result, specifically including the following steps: Step 521: determining the time range of the displacement trend data set and calculating the total duration of the time range.

[0081] In the embodiment of the present application, the earliest starting time and the latest ending time are extracted from the displacement trend data set, the interval defined by the two time points is taken as the time range, and the total duration of the time range is obtained by subtracting the starting time from the ending time.

[0082] Step 522: Extract the historical time range corresponding to each candidate displacement mode in the pre-stored historical displacement record, and calculate the historical total duration of the historical time range. The time overlap ratio is calculated in combination with the total duration.

[0083] In this step, the historical time range refers to the time interval corresponding to the candidate displacement mode in the pre-stored historical displacement record, including the starting time and the ending time of the mode occurring in history, which is used to compare the time correlation with the time range of the displacement trend data set. The time overlap ratio refers to the duration of the overlapping part of the time range of the displacement trend data set and the historical time range of the candidate displacement mode, which is used to measure the closeness of the time correlation.

[0084] In the embodiment of the present application, the starting time and the ending time of each candidate displacement mode occurring in the historical displacement record are extracted, the historical total duration of the historical time range is calculated, i.e. the ending time minus the starting time; and then the overlapping part of the time range of the displacement trend data set and the historical time range is compared and selected, and the time overlap ratio is obtained by dividing the duration of the overlapping part by the total duration of the displacement trend data set.

[0085] Step 523: Divide the time range into a plurality of displacement trend periods, each displacement trend period corresponding to the displacement change information in the displacement trend data set, and divide the historical time range into a plurality of mode historical periods, each mode historical period corresponding to the historical displacement change information in the candidate displacement mode.

[0086] In this step, the displacement trend period refers to the continuous sub-interval obtained by dividing the time range of the displacement trend data set at a fixed interval, including the displacement trend period corresponding to each sub-interval, which is used to refine the displacement change analysis in the time dimension. The displacement change information refers to the displacement feature data in the displacement trend period, including the displacement change direction, the cumulative displacement change rate, and the duration in the period, etc., which is used to describe the displacement law of the period. The mode historical period refers to the continuous sub-interval obtained by dividing the historical time range of the candidate displacement mode at a fixed interval, which is consistent with the division standard of the displacement trend period, including the historical time period corresponding to each sub-interval, which is used for feature comparison with the displacement trend period. The historical displacement change information refers to the displacement feature data in the mode historical period, including the historical displacement change direction and the cumulative displacement change rate in the period, which is used for comparison with the displacement change information.

[0087] In the embodiment of the present application, the time range of the displacement trend data set is divided into a plurality of continuous displacement trend periods at fixed time intervals (such as every 5 minutes), and each displacement trend period corresponds to displacement change information (such as displacement change direction, cumulative displacement change rate, etc.) in the time period. Meanwhile, the historical time range of the candidate displacement mode is divided into a plurality of mode historical periods at the same time interval, and each period corresponds to historical displacement change information of the mode in the historical record, ensuring that the two division standards are consistent.

[0088] Step 524: Comparing the displacement change characteristics of the overlapping displacement trend period and the mode historical period on the time axis to calculate the period characteristic matching proportion.

[0089] In this step, the overlapping on the time axis means that there is an intersection part of the interval of the displacement trend period and the mode historical period on the time axis, which is used to determine the feature interval that needs to be compared. The displacement change characteristic means the displacement attribute in the displacement trend period or the mode historical period, including the displacement change direction, the size range of the maximum cumulative displacement change rate, etc., which is used to measure whether the displacement laws of the two periods are consistent. The period characteristic matching proportion means the proportion of the number of periods in which the displacement change characteristics are consistent in the overlapping displacement trend period and the mode historical period on the time axis to the total number of overlapping periods.

[0090] In the embodiment of the present application, the displacement change direction, cumulative displacement change rate, etc. in the overlapping period are compared one by one to determine whether the characteristics are consistent, and the proportion of the number of overlapping periods in which the characteristics are consistent to the total number of overlapping periods is calculated to obtain the period characteristic matching proportion.

[0091] Step 525: The candidate displacement mode corresponding to the time overlap proportion exceeding the preset time proportion threshold and the period characteristic matching proportion exceeding the preset matching proportion threshold is determined to have time correlation with the displacement trend.

[0092] In this step, the preset time proportion threshold means the minimum standard value for judging whether the time overlap proportion meets the standard, which is set in advance based on historical data statistics, and is used to filter the candidate modes with basic time correlation. The preset matching proportion threshold means the minimum standard value for judging whether the period characteristic matching proportion meets the standard, which is set in advance based on the feature similarity requirement, and is used to filter the candidate modes with feature level matching.

[0093] In the embodiment of the present application, the time overlap proportion is compared with the preset time proportion threshold (such as 60%), and the period characteristic matching proportion is compared with the preset matching proportion threshold (such as 70%), and if both proportions exceed the corresponding threshold, it is determined that the candidate displacement mode has time correlation with the displacement trend.

[0094] Step 526: If there are multiple candidate displacement patterns with time correlation, the candidate displacement pattern with the maximum sum of time overlap ratio and period feature matching ratio is determined as the main correlation pattern, and if all candidate displacement patterns have no time correlation with displacement trend, a no-match identifier is generated.

[0095] In this step, the main correlation pattern refers to the mode selected from multiple candidate displacement patterns with time correlation, and the mode with the maximum sum of time overlap ratio and period feature matching ratio is selected as the core result of pattern recognition. The no-match identifier refers to a specific marker generated when all candidate displacement patterns do not meet the time correlation condition, facilitating subsequent processing and recognition.

[0096] In the embodiment of the present application, if there are multiple candidate displacement patterns with time correlation, the sum of time overlap ratio and period feature matching ratio of each candidate displacement pattern is calculated, and the candidate displacement pattern with the maximum sum is selected as the main correlation pattern. If both ratios of all candidate displacement patterns do not exceed the threshold, a no-match pattern identifier (such as a specific character or code) is generated.

[0097] Step 527: The modes and corresponding time overlap ratio, period feature matching ratio, overlapping period information, or no-match identifier are integrated to form a pattern recognition result, and the modes include the main correlation pattern and candidate displacement patterns without time correlation.

[0098] In the embodiment of the present application, first, all candidate displacement patterns are classified: for the main correlation pattern, the mode name (such as large truck load typical displacement pattern), corresponding time overlap ratio (such as 75%), period feature matching ratio (such as 80%) and overlapping period information (such as 08:10-08:25, 08:30-08:40) are recorded; for candidate displacement patterns without time correlation, the mode name, time overlap ratio (such as 40%), period feature matching ratio (such as 60%) and overlapping period information (such as 08:05-08:10) are also recorded, and no time correlation is marked; if all candidate patterns have no time correlation, the no-match pattern identifier is recorded. Then, these information is arranged in the logical order of main correlation pattern-non-correlation candidate pattern-no-match identifier into structured data, such as table form containing mode type, each ratio and overlapping period, and finally a complete pattern recognition result is formed, which clearly presents the correlation of all modes and key parameters, providing clear basis for subsequent comparison with the baseline range parameter list.

[0099] The embodiment of the present application realizes accurate time comparison of displacement trend and historical mode by refining time range and period division; improves the accuracy of time correlation judgment by combining double judgment of time overlap proportion and period characteristic matching proportion; ensures the definiteness of mode recognition result by screening main correlation mode or generating no matching identification; and enhances the reliability of mode matching, thereby providing high-quality decision basis for subsequent safety warning.

[0100] The present application provides a specific embodiment, step 106, comparing the displacement change parameter in the mode recognition result with the pre-stored vibration baseline range parameter list, generating a structure safety warning instruction containing abnormal position and abnormal degree, specifically including the following steps: Step 601: Extracting the displacement change parameter from the mode recognition result, the displacement change parameter including maximum cumulative displacement change rate, abnormal duration and direction conversion frequency.

[0101] In this step, the abnormal duration refers to the continuous time length that the displacement change parameter exceeds the normal fluctuation range in the vibration reference range parameter list, which is calculated based on the starting time and the ending time of the out-of-range displacement change parameter (ending time minus starting time). The direction conversion frequency refers to the number of displacement change direction conversions per unit time, which is calculated based on the total number of direction conversions per unit time (such as 1 hour), and the higher the frequency, the more unstable the displacement change.

[0102] In the embodiment of the present application, first, the detailed data partition corresponding to the main correlation mode (if any) or the unique candidate displacement mode recorded in the structured data of the pattern recognition result is located, which contains the displacement feature information of all continuous time periods corresponding to the mode correlation. For the maximum cumulative displacement change rate, the cumulative displacement change rate data of all continuous time periods under the mode is traversed, and the maximum cumulative displacement change rate is selected by comparing the cumulative values of each period one by one. For the abnormal duration, the normal fluctuation interval of the corresponding parameter in the pre-stored vibration reference range parameter list is first called, and then it is checked whether the cumulative displacement change rate of each continuous time period under the mode exceeds the interval. The starting and ending time of all out-of-range periods is recorded, and the continuous total duration of these out-of-range periods is calculated as the abnormal duration. For the direction conversion frequency, the total number of displacement direction conversion times (such as from continuous time period 1 to continuous time period 2, from continuous time period 2 to continuous time period 3, etc.) is counted, and then the total conversion times are divided by the total time range duration corresponding to the mode to obtain the conversion frequency per unit time. Finally, the three parameters of the extracted maximum cumulative displacement change rate, abnormal duration and direction conversion frequency are arranged into an association array in the format of parameter name-value-unit to form complete displacement change parameters.

[0103] Step 602: Compare the maximum cumulative displacement change rate of the displacement change parameter with the corresponding normal fluctuation upper limit and normal fluctuation lower limit in the pre-stored vibration reference range parameter list to mark the target parameter that exceeds the range.

[0104] In this step, the normal fluctuation upper limit refers to the maximum reasonable value of the displacement change parameter (such as the maximum cumulative displacement change rate) allowed in the vibration reference range parameter list, which is determined based on historical normal monitoring data and structural safety standards. The normal fluctuation lower limit refers to the minimum reasonable value of the displacement change parameter allowed in the vibration reference range parameter list, which together with the normal fluctuation upper limit forms the normal interval of the parameter. The target parameter refers to the parameter whose maximum cumulative displacement change rate exceeds the normal fluctuation upper limit or lower limit, which is marked by comparison with the reference range.

[0105] In the embodiment of the present application, the normal fluctuation upper limit and the normal fluctuation lower limit corresponding to the maximum cumulative displacement change rate of the displacement change parameter in the vibration reference range parameter list are called one by one. If the maximum cumulative displacement change rate is greater than the normal fluctuation upper limit or less than the normal fluctuation lower limit, the parameter is marked as a target parameter that exceeds the range.

[0106] Step 603: Compare the abnormal duration of the target parameter with the corresponding allowed duration in the vibration reference range parameter list to record the time period information that exceeds the allowed duration.

[0107] In this step, the allowed continuous time length refers to the longest continuous time that the displacement variation parameter exceeds the normal range in the vibration reference range parameter list, which is set based on the structural tolerance capacity. The time period information refers to the specific time period when the abnormal continuous time length of the target parameter exceeds the allowed continuous time length, which is used to determine the time range when the abnormality occurs.

[0108] In the embodiments of the present application, the abnormal continuous time length of the target parameter (such as the continuous time length of displacement exceeding the range in a certain time period) is compared with the preset allowed continuous time length (the longest time length of exceeding the range that can be accepted under normal circumstances) in the list, and the specific time period when all abnormal continuous time lengths exceed the allowed continuous time length (such as 09:15-09:30) is recorded to form the time period information.

[0109] Step 604: Locating the abnormal occurrence position of the bridge structure according to the target parameter and the corresponding spatial coordinate information; In this step, the abnormal occurrence position refers to the specific physical position where the displacement abnormality occurs in the bridge structure, which includes the position determined based on the spatial coordinate information corresponding to the target parameter, and is used to locate the spatial distribution of the abnormality.

[0110] In the embodiments of the present application, first, the metadata of the target parameter is read, which contains the unique identifier of the sensor collecting the parameter, and the identifier is bound to the installation position of the sensor on the bridge; then, the corresponding spatial coordinate information is retrieved based on the unique identifier of the sensor by querying the pre-stored sensor position database, including the X-axis (in the length direction of the bridge), Y-axis (in the width direction of the bridge), and Z-axis (perpendicular to the bridge deck) coordinate values in the global coordinate system of the bridge (such as X=350m, Y=12m, Z=0m); then, the retrieved X, Y, and Z coordinate values are matched to the corresponding physical area (such as the No. 5 bridge body) through the coordinate-physical position mapping table (which pre-recorded the correspondence between the coordinate range and the physical name of each key part of the bridge, such as X=340-360m, Y=10-15m corresponding to the No. 5 bridge body); and combined with the specific offset of the coordinate value in the area, such as Y=12m being in the middle position of the 10-15m interval, corresponding to the centerline of the bridge body 2 meters east), the accurate physical position description is refined; finally, through cross verification (comparing the installation position description of the historical record of the sensor to ensure consistency with the current mapping result), the centerline of the No. 5 bridge body 2 meters east is determined as the abnormal occurrence position of the bridge structure.

[0111] Step 605: Calculating the numerical difference between the target parameter and the corresponding reference parameter in the vibration reference range parameter list, and combining the preset difference interval standard to divide the abnormality degree level; In this step, the corresponding reference parameter refers to the normal fluctuation boundary value (such as the normal fluctuation upper limit if the target parameter is the upper limit) corresponding to the target parameter in the vibration reference range parameter list, including the reference reference for calculating the numerical difference, which is determined based on the preset parameter range in the list. The preset difference interval standard refers to the numerical difference interval preset for dividing the abnormality level (such as level 1, level 2, and level 3), and each interval corresponds to a level, which is set based on the structure damage risk assessment. The abnormality level refers to the abnormality level (such as level 1, level 2, and level 3) divided according to the numerical difference between the target parameter and the corresponding reference parameter. The higher the level, the greater the risk.

[0112] In the embodiment of the present application, the target parameter is subtracted from the corresponding reference parameter (such as the normal fluctuation upper limit or lower limit) to obtain the numerical difference; then the numerical difference is compared with the preset difference interval standard (such as 0-5mm / s for level 1 and 5-10mm / s for level 2), and the abnormality level is divided according to the interval into which the numerical difference falls (such as level 1 and level 2).

[0113] Step 606: integrating the abnormality occurrence position of the bridge structure, the abnormality level, the target parameter, and the time period information to generate a structure safety warning instruction.

[0114] In the embodiment of the present application, first, the fixed fields of the structure safety warning instruction are defined: abnormal position, abnormal level, key parameter, and duration, and the data format of each field is set (such as position for physical description text, level for Chinese capital number, parameter for name + value + unit, and time period for start time-end time; for example, 2 meters east of the centerline of the No. 5 span beam is filled in the abnormal position field, level 1 is filled in the abnormal level field, the maximum cumulative displacement change rate 1.2mm / s is filled in the key parameter field, and 10:00-10:20 is filled in the duration field; then, it is checked whether the contents of each field match, such as whether the abnormal period corresponding to the key parameter matches the duration, whether the abnormal level corresponds to the parameter difference calculation result, to ensure that there is no information mismatch; then, a generation timestamp and an instruction number are added at the end of the instruction for tracing and management; finally, these fields are combined in the format of abnormal position, [abnormal level] abnormality: [key parameter], duration [duration] (instruction number: [number], generation time: [timestamp]) to form the structured text of 2 meters east of the centerline of the No. 5 span beam, level 1 abnormality: maximum cumulative displacement change rate 1.2mm / s, duration 10:00-10:20 (instruction number: xx, generation time: xx), and the structure safety warning instruction is finally generated. The instruction can be directly parsed and displayed by the monitoring terminal.

[0115] The embodiment of the present application can accurately identify abnormal parameters exceeding the normal range by extracting displacement change parameters and comparing them with the vibration reference range; can determine the time range and position of the abnormality by combining the abnormal duration and spatial coordinate information; can quantify the severity of the abnormality through numerical difference calculation and grade division; and finally integrates the information to generate a warning instruction, realizes a closed loop from abnormality identification to warning output; multi-dimensional parameter comparison and quantitative grading enhance the accuracy and pertinence of the warning, solve the problems of data processing lag and fuzzy warning, and provide timely and reliable protection for the safety of bridge structure.

[0116] Figure 3 A structural schematic diagram of a specific embodiment of a road and bridge displacement monitoring system based on the Internet of Things is provided for the embodiments of the present application, referring to Figure 3 The system can include: An acquisition module 21 is configured to acquire an electrical vibration signal generated by a road and bridge, form an original vibration data set according to a timestamp and spatial coordinate information of the electrical vibration signal, and convert the vibration mechanical energy generated by the traffic load to obtain the electrical vibration signal. An encapsulation and verification module 22 is configured to encapsulate the original vibration data set to obtain an encapsulated data packet, and use an edge computing node deployed locally on the road and bridge to perform integrity verification on the encapsulated data packet to obtain a verified data packet. A processing module 23 is configured to perform noise reduction and time sequence alignment processing on the verified electrical vibration signal in the verified data packet according to a pre-stored bridge vibration measurement reference database to generate a vibration sequence. An analysis module 24 is configured to calculate a dynamic displacement change rate based on the vibration sequence to analyze a displacement trend and obtain a displacement trend data set. An extraction module 25 is configured to extract a feature parameter from the displacement trend data set, extract a candidate displacement mode from a pre-stored historical displacement record according to the feature parameter, and generate a mode recognition result. A generation module 26 is configured to compare a displacement change parameter in the mode recognition result with a pre-stored vibration baseline range parameter list to generate a structure safety warning instruction containing an abnormal position and an abnormal degree.

[0117] The road and bridge displacement monitoring system based on the Internet of Things can be used to implement the road and bridge displacement monitoring method based on the Internet of Things, and the specific embodiments of the road and bridge displacement monitoring system based on the Internet of Things can be seen from the foregoing embodiment of the road and bridge displacement monitoring method based on the Internet of Things. The specific embodiments can be described with reference to the descriptions of the respective embodiments, and will not be described here.

[0118] The application further provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-mentioned road and bridge displacement monitoring methods based on Internet of Things.

[0119] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of any of the above-mentioned road and bridge displacement monitoring methods based on Internet of Things.

[0120] In an exemplary embodiment, the above-mentioned computer readable storage medium can include, but is not limited to, a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media capable of storing computer programs.

[0121] The embodiments of the application further provide a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps in any of the above-mentioned road and bridge displacement monitoring methods based on Internet of Things.

[0122] The skilled person can further realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0123] The above describes in detail the road and bridge displacement monitoring method and system based on Internet of Things provided by the application. The principles and implementation modes of the application are described by applying specific examples. The above description of the examples is only used to help understand the method of the application and its core idea. It should be pointed out that, for those skilled in the art, without departing from the principles of the application, some improvements and modifications can be made to the application, and these improvements and modifications also fall within the protection scope of the application.

Claims

1. A method for monitoring displacement of a road bridge based on Internet of Things, characterized in that, The method comprises the following steps: obtaining an electrical vibration signal generated by a road bridge, and forming an original vibration data set according to a time stamp and spatial coordinate information of the electrical vibration signal, wherein the electrical vibration signal is obtained by converting vibration mechanical energy generated by a traffic load; packaging the original vibration data set to obtain a packaged data packet, and performing integrity verification on the packaged data packet by using an edge computing node deployed locally on the road bridge to obtain a verified data packet; performing noise reduction and time sequence alignment processing on the verified electrical vibration signal in the verified data packet according to a pre-stored bridge vibration measurement benchmark database to generate a vibration sequence; calculating a dynamic displacement change rate based on the vibration sequence to analyze a displacement trend and obtain a displacement trend data set; extracting a feature parameter from the displacement trend data set, extracting a candidate displacement mode from a pre-stored historical displacement record according to the feature parameter, and generating a mode recognition result; comparing a displacement change parameter in the mode recognition result with a pre-stored vibration baseline range parameter list to generate a structure safety early warning instruction containing an abnormal position and an abnormal degree.

2. The method of claim 1, wherein, extracting a feature parameter from the displacement trend data set, extracting a candidate displacement mode from a pre-stored historical displacement record according to the feature parameter, and generating a mode recognition result, comprising: extracting a feature parameter of each continuous time period from the displacement trend data set, wherein the feature parameter comprises a maximum cumulative displacement change rate, a longest duration, and an interval number of direction conversion; extracting a plurality of candidate displacement modes from a pre-stored historical displacement record according to the feature parameter, wherein the historical displacement record contains typical displacement modes corresponding to different traffic load types; judging the time correlation of the candidate displacement mode and the displacement trend according to the time range of the displacement trend data set to generate a mode recognition result.

3. The method of claim 2, wherein, extracting a plurality of candidate displacement modes from a pre-stored historical displacement record according to the feature parameter, wherein the historical displacement record contains typical displacement modes corresponding to different traffic load types, comprising: selecting an initial typical displacement mode and a corresponding feature parameter range from the pre-stored historical displacement record, wherein the feature parameter range comprises an upper limit of the maximum cumulative displacement change rate, a lower limit of the maximum cumulative displacement change rate, a longest duration interval, and an interval number of allowed direction conversion; labeling the initial typical displacement mode whose maximum cumulative displacement change rate is between the upper limit of the maximum cumulative displacement change rate and the lower limit of the maximum cumulative displacement change rate as a first-level screening mode, labeling the first-level screening mode whose longest duration is within the longest duration interval as a second-level screening mode, and labeling the second-level screening mode whose interval number of displacement change direction conversion is less than the interval number of allowed direction conversion as a third-level screening mode; when there are a plurality of third-level screening modes, selecting a third-level screening mode with a matching degree higher than a preset matching degree as a candidate displacement mode.

4. The method of claim 2, wherein, judging the time correlation of the candidate displacement mode and the displacement trend according to the time range of the displacement trend data set to generate a mode recognition result, comprising: determine a time range of the displacement trend data set, and calculate a total duration of the time range; extract a historical time range corresponding to each candidate displacement mode in the pre-stored historical displacement record, and calculate a historical total duration of the historical time range, combine the total duration to calculate a time overlap ratio; divide the time range into a plurality of displacement trend periods, each displacement trend period corresponding to displacement change information in the displacement trend data set, and divide the historical time range into a plurality of mode historical periods, each mode historical period corresponding to historical displacement change information in the candidate displacement mode; compare the displacement change characteristics of the displacement trend periods and the mode historical periods overlapping on the time axis to calculate a period characteristic matching ratio; determine the candidate displacement mode corresponding to the time overlap ratio exceeding a preset time ratio threshold and the period characteristic matching ratio exceeding a preset matching ratio threshold as having a time correlation with the displacement trend; if there are multiple candidate displacement modes having a time correlation, determine the candidate displacement mode with the sum of the time overlap ratio and the period characteristic matching ratio being the largest as the main associated mode, and if all candidate displacement modes have no time correlation with the displacement trend, generate a no-match identifier; integrate each mode and the corresponding time overlap ratio, period characteristic matching ratio, overlapping period information, or no-match identifier to form a mode recognition result, each mode including the main associated mode and the candidate displacement mode having no time correlation.

5. The method of claim 1, wherein, According to the pre-stored bridge vibration measurement benchmark database, the noise reduction and time sequence alignment processing are performed on the verified electrical vibration signal in the verified data packet to generate a vibration sequence, including: From the pre-stored bridge vibration measurement benchmark database, the benchmark vibration signal corresponding to the verified electrical vibration signal in the verified data packet is called; The verified electrical vibration signal and the benchmark vibration signal are compared segment by segment to remove vibration difference signals with amplitude difference exceeding a preset threshold to obtain a preliminary processed signal; According to the timestamp information of the verified electrical vibration signal, the time interval between different verified electrical vibration signals is determined; According to the time interval, the starting record time of each preliminary processed signal is adjusted to obtain an adjusted preliminary processed signal, and the adjusted preliminary processed signal is arranged to form a vibration sequence.

6. The method of claim 1, wherein, Based on the vibration sequence, the dynamic displacement change rate is calculated to analyze the displacement trend to obtain a displacement trend data set, including: Extract the vibration amplitude and corresponding time information of each record time from the vibration sequence to form vibration time sequence data containing time amplitude correspondence; Calculate the time difference and vibration amplitude difference between adjacent record times in the vibration time sequence data to form a displacement change rate time sequence based on the time difference and vibration amplitude difference; According to the positive and negative attributes of each displacement change rate in the displacement change rate time sequence, the displacement change direction in the corresponding time period is determined; The period time range and the cumulative displacement change rate of the continuous time period with the same displacement change direction are determined, the period time range and the cumulative displacement change rate of the continuous time period with different displacement change directions are summarized, and a displacement trend data set is formed.

7. The method of claim 1, wherein, The displacement change parameters in the pattern recognition result are compared with a pre-stored vibration baseline range parameter list, and a structure safety warning instruction containing an abnormal position and an abnormal degree is generated. The displacement change parameters are extracted from the pattern recognition result, and the displacement change parameters include a maximum cumulative displacement change rate, an abnormal duration, and a direction conversion frequency. The maximum cumulative displacement change rate of the displacement change parameters is compared with corresponding normal fluctuation upper and lower limits in the pre-stored vibration reference range parameter list to mark target parameters that are out of range. The abnormal duration of the target parameters is compared with the corresponding allowed duration in the vibration reference range parameter list to record period information that exceeds the allowed duration. The abnormal position of the bridge structure is located according to the target parameters and corresponding spatial coordinate information. The numerical difference between the target parameters and the corresponding reference parameters in the vibration reference range parameter list is calculated, and an abnormal degree level is divided in combination with a pre-set difference interval standard. The abnormal position of the bridge structure, the abnormal degree level, the target parameters, and the period information are integrated to generate a structure safety warning instruction.

8. A road bridge displacement monitoring system based on Internet of Things, characterized in that, The method comprises the following steps: An acquisition module is configured to acquire an electrical vibration signal generated by a road bridge, and form an original vibration data set according to the time stamp and spatial coordinate information of the electrical vibration signal, wherein the electrical vibration signal is converted from vibration mechanical energy generated by traffic load. An encapsulation and verification module is configured to encapsulate the original vibration data set to obtain an encapsulated data packet, and perform integrity verification on the encapsulated data packet by using an edge computing node deployed locally on the road bridge to obtain a verified data packet. A processing module is configured to perform noise reduction and time sequence alignment processing on the verified electrical vibration signal in the verified data packet according to a pre-stored bridge vibration measurement reference database to generate a vibration sequence. An analysis module is configured to calculate a dynamic displacement change rate based on the vibration sequence to analyze displacement trends and obtain a displacement trend data set. An extraction module is configured to extract feature parameters from the displacement trend data set, extract candidate displacement patterns from a pre-stored historical displacement record according to the feature parameters, and generate a pattern recognition result. A generation module is configured to compare the displacement change parameters in the pattern recognition result with a pre-stored vibration baseline range parameter list, and generate a structure safety warning instruction containing an abnormal position and an abnormal degree.

9. An electronic device, comprising: The method comprises the following steps: A memory is configured to store a computer program. A processor is configured to execute the computer program to implement the steps of the road bridge displacement monitoring method based on the Internet of Things.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the road and bridge displacement monitoring method based on the Internet of Things.

Images