Bridge vibration monitoring and early warning method and system

Abstract

The present invention provides a bridge vibration monitoring and early warning method and system, relating to the field of monitoring and early warning technology. The method comprises: obtaining to-be-processed vibration data at multiple times during a monitoring cycle using a combination of sensors positioned at preset locations; obtaining processed vibration data based on the to-be-processed vibration data; determining the vibration source, vibration pattern, and vibration intensity coefficient based on the processed vibration data; determining abnormal vibration pattern results based on the vibration pattern; obtaining environmental data at multiple times during the monitoring cycle using environmental sensors positioned at preset locations; inputting the abnormal vibration pattern results, vibration intensity coefficient, and environmental data into a trained fault occurrence time prediction model to determine a predicted fault occurrence time; and generating early warning information based on the vibration source and predicted fault occurrence time. According to the present invention, the accuracy of bridge vibration monitoring and early warning can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and early warning, and in particular to a bridge vibration monitoring and early warning method and system. Background Art

[0002] In related technologies, bridge vibration monitoring and early warning mainly rely on drone monitoring. During the use of drones for monitoring, the periodic inspection intervals are large and drones have difficulty working in strong winds and heavy rain. Therefore, the use of drones for vibration monitoring may not be able to maintain the timeliness of vibration monitoring and its applicability to the monitoring environment.

[0003] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the Invention

[0004] The present invention provides a bridge vibration monitoring and early warning method and system, which can solve the technical problem that related technologies cannot maintain the timeliness of vibration monitoring and the applicability to the monitoring environment.

[0005] According to a first aspect of the present invention, a bridge vibration monitoring and early warning method is provided, comprising:

[0006] At multiple moments in the monitoring cycle, vibration data to be processed is obtained through a combination of sensors set at preset positions;

[0007] acquiring processed vibration data according to the vibration data to be processed;

[0008] determining a vibration source, a vibration mode, and a vibration intensity coefficient based on the processed vibration data;

[0009] determining a vibration pattern abnormality result based on the vibration pattern;

[0010] At multiple moments in the monitoring cycle, environmental data is acquired through environmental sensors disposed at preset locations, wherein the environmental data includes: temperature data, humidity data, and wind speed data;

[0011] Inputting the vibration pattern abnormality result, the vibration intensity coefficient and the environmental data into a trained fault occurrence time prediction model to determine a predicted fault occurrence time;

[0012] Generate early warning information based on the vibration source and the predicted fault occurrence time.

[0013] According to the present invention, determining the vibration source, vibration mode and vibration intensity coefficient based on the processed vibration data includes:

[0014] obtaining an original vibration signal and a time-frequency spectrum diagram according to the processed vibration data;

[0015] Inputting the original vibration signal and the time-frequency spectrum into a vibration pattern recognition model to determine the vibration pattern;

[0016] Inputting the original vibration signal and the time-frequency spectrum into a vibration source identification model to determine the vibration source;

[0017] determining vibration displacement, vibration acceleration, and vibration frequency based on the original vibration signal;

[0018] A vibration intensity coefficient is determined according to the vibration displacement, the vibration acceleration, and the vibration frequency.

[0019] According to the present invention, determining the vibration intensity coefficient according to the vibration displacement, the vibration acceleration and the vibration frequency includes:

[0020] Obtain the measured damping ratio, designed damping ratio and natural frequency of the bridge;

[0021] Determine acceleration limits and displacement limits;

[0022] A vibration intensity coefficient is determined according to the measured damping ratio, the designed damping ratio, the natural frequency, the vibration acceleration, the vibration displacement, the vibration frequency, the acceleration limit, and the displacement limit.

[0023] According to the present invention, determining the vibration intensity coefficient according to the measured damping ratio, the designed damping ratio, the natural frequency, the vibration acceleration, the vibration displacement, the vibration frequency, the acceleration limit, and the displacement limit includes:

[0024] According to the formula

[0025]

[0026] Determine the vibration intensity coefficient of the kth preset position at the i-th moment in the monitoring cycle , where if is a conditional function, 、 and is the preset weight, is the vibration frequency of the kth preset position at the i-th moment in the monitoring period, is the natural frequency, is the vibration acceleration of the k-th preset position at the i-th moment in the monitoring cycle, is the acceleration limit, is the measured damping ratio of the kth preset position at the i-th moment in the monitoring period, To design the damping ratio, is the vibration displacement of the k-th preset position at the i-th moment in the monitoring period, is the displacement limit.

[0027] According to the present invention, determining a vibration pattern abnormality result according to the vibration pattern includes:

[0028] Get the location category of each preset location;

[0029] determining a regular vibration pattern based on the location category;

[0030] A vibration pattern abnormality result is determined based on the vibration pattern and the normal vibration pattern.

[0031] According to the present invention, the training step of the fault occurrence time prediction model includes:

[0032] Acquire historical processed vibration data and historical environmental data of historical preset positions of other bridges in a historical time period, wherein the historical environmental data includes: historical temperature data, historical wind data, and historical humidity data;

[0033] determining a historical vibration pattern and a historical vibration intensity coefficient based on the historical processed vibration data;

[0034] determining an abnormal result of the historical vibration pattern based on the historical vibration pattern;

[0035] Inputting the historical vibration pattern abnormal results, the historical vibration intensity coefficient and the historical environmental data into a fault occurrence time prediction model to determine a sample predicted fault occurrence time;

[0036] Obtain historical maintenance records for other bridges;

[0037] Determine the most recent historical maintenance time based on the historical maintenance records;

[0038] Determining a training loss function for a fault occurrence time prediction model based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormality result, the historical vibration intensity coefficient, and the historical environmental data;

[0039] The fault occurrence time prediction model is trained according to the training loss function of the fault occurrence time prediction model to obtain a trained fault occurrence time prediction model.

[0040] According to the present invention, a training loss function of a fault occurrence time prediction model is determined based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormality result, the historical vibration intensity coefficient, and the historical environmental data, including:

[0041] According to the formula

[0042]

[0043] Determine the training loss function of the failure time prediction model , where if is a conditional function, is the most recent historical maintenance time of the rth historical preset position of the eth other bridge in the jth historical time period, For the sample prediction failure time of the rth historical preset position of the eth other bridge in the jth historical time period, is the historical vibration intensity coefficient of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, To preset the vibration intensity coefficient threshold, is the historical temperature data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, is the first preset temperature threshold, is the second preset temperature threshold, is the historical humidity data of the rth historical preset position of the eth other bridge in the jth historical time period, is the preset humidity threshold, is the historical wind force data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, To preset the wind data threshold, is the abnormal vibration pattern result of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, , n is the number of historical time periods, j≤n, E is the number of other bridges, e≤E, S is the number of moments in the historical time period, t≤S, R is the number of historical preset positions, r≤R, n, j, E, e, S, t, r and R are all positive integers.

[0044] According to the present invention, generating early warning information according to the vibration source and the predicted fault occurrence time includes:

[0045] Determining a preset first time threshold and a preset second time threshold;

[0046] Determining the warning level at each preset location based on the predicted fault occurrence time at each preset location, the preset first time threshold, and the preset second time threshold;

[0047] Warning information is generated according to the vibration source, the location category of each preset location, and the warning level at each preset location.

[0048] According to the present invention, determining the warning level at each preset location based on the predicted fault occurrence time at each preset location, the preset first time threshold, and the preset second time threshold includes:

[0049] When the predicted fault occurrence time at the k-th preset position is less than the preset first time threshold, the warning level at the k-th preset position is a high warning;

[0050] When the predicted fault occurrence time at the k-th preset position is greater than or equal to the preset first time threshold and less than or equal to the preset second time threshold, the warning level at the k-th preset position is a medium warning;

[0051] When the predicted fault occurrence time at the k-th preset position is greater than the preset second time threshold, the warning level at the k-th preset position is a low-level warning.

[0052] According to a second aspect of the present invention, a bridge vibration monitoring and early warning system is provided, comprising:

[0053] A vibration data module is used to obtain vibration data to be processed through a combination of sensors set at preset positions at multiple moments in the monitoring cycle;

[0054] a data processing module, configured to obtain processed vibration data based on the vibration data to be processed;

[0055] a vibration pattern module, configured to determine a vibration source, a vibration pattern, and a vibration intensity coefficient based on the processed vibration data;

[0056] A pattern abnormality module, configured to determine a vibration pattern abnormality result based on the vibration pattern;

[0057] An environmental data module is used to obtain environmental data at multiple moments in a monitoring period through environmental sensors set at preset positions, wherein the environmental data includes: temperature data, humidity data and wind speed data;

[0058] a time prediction module, configured to input the vibration pattern abnormality result, the vibration intensity coefficient, and the environmental data into a trained fault occurrence time prediction model to determine a predicted fault occurrence time;

[0059] The early warning information module is used to generate early warning information according to the vibration source and the predicted fault occurrence time.

[0060] Technical effect: According to the present invention, vibration data can be accurately collected and processed, and the vibration source, vibration mode and vibration intensity coefficient can be accurately analyzed based on the processed vibration data. Furthermore, the time of occurrence of faults at various preset positions of the bridge can be predicted based on the environmental data, vibration mode and vibration intensity coefficient, and early warning information can be generated based on the vibration source and the predicted time of occurrence of the fault, thereby improving the accuracy of bridge vibration monitoring and early warning. When determining the vibration intensity coefficient, the vibration intensity coefficient can be determined based on the measured damping ratio, design damping ratio, natural frequency, vibration acceleration, vibration displacement, vibration frequency, acceleration limit and displacement limit. During the calculation process, the impact intensity of the vibration can be evaluated based on the three aspects of resonant risk condition, sudden instability risk condition and displacement condition, thereby improving the comprehensiveness and accuracy of the vibration intensity coefficient. When determining the training loss function, the training loss function of the fault occurrence time prediction model can be determined based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormal results, the historical vibration intensity coefficient and the historical environmental data. The influence of vibration intensity, vibration pattern and environmental data on the sample predicted fault occurrence time can be determined, and the training loss function can be set based on the influence and the relative error of the sample predicted fault occurrence time, so that the training loss function of the fault occurrence time prediction model can be reduced during the training process, and the accuracy of the fault occurrence time prediction model can be improved in a more targeted manner.

[0061] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and not limiting of the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can derive other embodiments based on these drawings without inventive efforts.

[0063] Figure 1 A schematic flow chart of a bridge vibration monitoring and early warning method according to an embodiment of the present invention is exemplarily shown;

[0064] Figure 2 A schematic diagram exemplarily illustrates the determination of vibration sources, vibration modes, and vibration intensity coefficients according to an embodiment of the present invention;

[0065] Figure 3 A schematic diagram exemplarily illustrates the determination of abnormal vibration pattern results according to an embodiment of the present invention;

[0066] Figure 4 A schematic diagram exemplarily shows generation of warning information according to an embodiment of the present invention;

[0067] Figure 5 The following is a block diagram of a bridge vibration monitoring and early warning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0069] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0070] Figure 1 The following is a flow chart showing a bridge vibration monitoring and early warning method according to an embodiment of the present invention. The method includes:

[0071] Step S1, at multiple moments in a monitoring period, obtaining vibration data to be processed through a combination of sensors set at preset positions;

[0072] Step S2, obtaining processed vibration data according to the vibration data to be processed;

[0073] Step S3, determining the vibration source, vibration mode and vibration intensity coefficient based on the processed vibration data;

[0074] Step S4, determining a vibration pattern abnormality result according to the vibration pattern;

[0075] Step S5, acquiring environmental data at multiple moments during the monitoring period through environmental sensors disposed at preset locations, wherein the environmental data includes temperature data, humidity data, and wind speed data;

[0076] Step S6, inputting the vibration pattern abnormality result, the vibration intensity coefficient and the environmental data into the trained fault occurrence time prediction model to determine the predicted fault occurrence time;

[0077] Step S7: generating warning information according to the vibration source and the predicted fault occurrence time.

[0078] According to the bridge vibration monitoring and early warning method of an embodiment of the present invention, vibration data can be accurately collected and processed, and the vibration source, vibration pattern and vibration intensity coefficient can be accurately analyzed based on the processed vibration data. Furthermore, according to the environmental data, vibration pattern and vibration intensity coefficient, the fault occurrence time at each preset position of the bridge is predicted, and according to the vibration source and the predicted fault occurrence time, early warning information is generated, thereby improving the accuracy of bridge vibration monitoring and early warning.

[0079] According to one embodiment of the present invention, in step S1 , vibration data to be processed is acquired at multiple moments in a monitoring period by a combination of sensors arranged at preset positions.

[0080] For example, a sensor combination is set at preset positions of the bridge (such as stress concentration areas such as piers, mid-span, supports and cantilever ends). The sensor combination includes: accelerometers, displacement sensors and vibration sensors. The sensor combination collects the vibration data to be processed at each preset position.

[0081] According to an embodiment of the present invention, in step S2, processed vibration data is obtained according to the vibration data to be processed.

[0082] For example, the vibration data to be processed can be subjected to denoising (e.g., using wavelet thresholding to separate valid signals), data alignment (e.g., achieving microsecond-level time synchronization based on GPS and PTP protocols), and outlier detection (e.g., using the isolation forest algorithm to eliminate abnormal data) to obtain processed vibration data.

[0083] According to an embodiment of the present invention, in step S3, the vibration source, vibration mode and vibration intensity coefficient are determined based on the processed vibration data.

[0084] Figure 2 A schematic diagram exemplarily illustrates the determination of vibration sources, vibration modes, and vibration intensity coefficients according to an embodiment of the present invention.

[0085] According to one embodiment of the present invention, step S3 includes:

[0086] Step S31, obtaining an original vibration signal and a time-frequency spectrum according to the processed vibration data;

[0087] Step S32, inputting the original vibration signal and the time-frequency spectrum into a vibration pattern recognition model to determine the vibration pattern;

[0088] Step S33, inputting the original vibration signal and the time-frequency spectrum into a vibration source identification model to determine the vibration source;

[0089] Step S34, determining the vibration displacement, vibration acceleration and vibration frequency according to the original vibration signal;

[0090] Step S35 : determining a vibration intensity coefficient according to the vibration displacement, the vibration acceleration, and the vibration frequency.

[0091] For example, the STFT time-frequency spectrum is obtained through time-frequency analysis tools (such as MATLAB), and the original vibration signal is obtained based on the processed vibration data. The original vibration signal is a vibration signal that has been normalized and filtered. The vibration signal that has been normalized and filtered plays an important role in the performance of the machine learning model; the vibration pattern recognition model is a type of Transformer model in the deep learning model. It captures the global features of the vibration signal through the attention mechanism and can be used to identify complex vibration patterns. The vibration pattern recognition model is trained through historical data so that the vibration pattern recognition model can identify the vibration patterns at various preset positions, such as vertical bending vibration and lateral bending vibration. The vibration pattern recognition model is used to train the original vibration signal and the ST The FT time-frequency spectrum is used to identify the vibration pattern; the vibration source identification model is a type of generative adversarial network model of the deep learning model, which can use the generator-discriminator framework to identify unknown vibration sources. The vibration source identification model is trained through historical data so that the vibration source identification model can identify the vibration sources at each preset location, such as vehicles and wind; according to the original vibration signal, the acceleration signal, velocity signal and displacement signal are obtained, and the signal is pre-processed and converted into physical quantities to determine the vibration displacement, vibration acceleration and vibration frequency; according to the vibration displacement, vibration acceleration and vibration frequency, the impact of the vibration on the preset location is evaluated and the vibration intensity coefficient is determined. The larger the vibration intensity coefficient, the stronger the impact of the vibration on the preset location.

[0092] According to one embodiment of the present invention, step S35 includes:

[0093] Step S351, obtaining the measured damping ratio, designed damping ratio and natural frequency of the bridge;

[0094] Step S352, determining the acceleration limit and the displacement limit;

[0095] Step S353 : determining a vibration intensity coefficient according to the measured damping ratio, the designed damping ratio, the natural frequency, the vibration acceleration, the vibration displacement, the vibration frequency, the acceleration limit, and the displacement limit.

[0096] For example, the measured damping ratio at each location of the bridge is obtained through the half-power bandwidth method, the design damping ratio is obtained through the bridge design manual, and the natural frequency of the bridge is obtained through the active excitation method (controllable excitation is applied through external equipment to stimulate the vibration response of the bridge, and peak value extraction is performed based on the vibration response data); according to industry specifications and standards, the acceleration limit is determined to be 0.2g, where g is the acceleration of gravity, and the displacement limit is 1 / 2000 of the span. For example, the displacement limit of a bridge with a span of 100m is 5cm; based on the measured damping ratio, design damping ratio, natural frequency, vibration acceleration, vibration displacement, vibration frequency, acceleration limit and displacement limit, the vibration intensity coefficient at the preset position is determined.

[0097] According to the first embodiment of the present invention, step S353 includes: determining the vibration intensity coefficient of the k-th preset position at the i-th moment in the monitoring period according to formula (1): ,

[0098] (1)

[0099] Among them, if is a conditional function, 、 and is the preset weight, is the vibration frequency of the kth preset position at the i-th moment in the monitoring period, is the natural frequency, is the vibration acceleration of the k-th preset position at the i-th moment in the monitoring cycle, is the acceleration limit, is the measured damping ratio of the kth preset position at the i-th moment in the monitoring period, To design the damping ratio, is the vibration displacement of the k-th preset position at the i-th moment in the monitoring period, is the displacement limit.

[0100] According to one embodiment of the present invention, is the relative difference between the vibration frequency and the natural frequency at the kth preset position at the i-th moment in the monitoring cycle. The smaller the ratio, the closer the vibration frequency is to the natural frequency. is the ratio of the measured damping ratio at the kth preset position at the i-th moment in the monitoring cycle to the designed damping ratio. The smaller the ratio, the lower the measured damping ratio. The resonance risk condition is determined based on the vibration frequency and the measured damping ratio. The closer the vibration frequency is to the natural frequency, the lower the measured damping ratio is. The larger the value, the higher the risk of resonance.

[0101] According to one embodiment of the present invention, in formula (1), the conditional function The value of includes the following two cases, when it satisfies When the condition is met, the vibration acceleration is less than the acceleration limit, indicating that the acceleration is within the limit, and the value of the condition function is 0. When the condition is met, it means that the acceleration exceeds the limit, and the value of the condition function is , is the relative difference between the vibration acceleration and the acceleration limit at the kth preset position at the i-th moment in the monitoring cycle. The larger the ratio, the greater the vibration acceleration. The risk of sudden instability is determined based on the acceleration conditions and the measured damping ratio conditions. When the measured damping value is low and the acceleration exceeds the limit, local buckling of thin-walled components (such as the web of a steel box girder) may occur, and there will be insufficient damping to suppress the expansion of instability, resulting in a higher risk of sudden instability.

[0102] According to one embodiment of the present invention, It is the ratio of the vibration displacement of the k-th preset position at the i-th moment in the monitoring period to the displacement limit. The larger the ratio, the greater the vibration displacement, the greater the impact on structural safety, and the greater the vibration intensity.

[0103] According to one embodiment of the present invention, To determine the vibration intensity based on the three aspects of resonant risk, sudden instability risk and displacement, 、 and Can be set to 2, 1.5, and 1 respectively.

[0104] In this way, the vibration intensity coefficient can be determined based on the measured damping ratio, design damping ratio, natural frequency, vibration acceleration, vibration displacement, vibration frequency, acceleration limit and displacement limit. During the calculation process, the impact intensity of vibration can be evaluated based on the three aspects of resonance risk condition, sudden instability risk condition and displacement condition, thereby improving the comprehensiveness and accuracy of the vibration intensity coefficient.

[0105] According to an embodiment of the present invention, in step S4, a vibration pattern abnormality result is determined based on the vibration pattern.

[0106] Figure 3 A schematic diagram exemplarily illustrates the determination of abnormal vibration pattern results according to an embodiment of the present invention.

[0107] According to one embodiment of the present invention, step S4 includes:

[0108] Step S41, obtaining the location category of each preset location;

[0109] Step S42, determining a normal vibration mode according to the location category;

[0110] Step S43: determining a vibration pattern abnormality result according to the vibration pattern and the normal vibration pattern.

[0111] For example, the position category is determined according to the location of each preset position in the bridge. For example, if the first preset position is at the main beam of the bridge, the position category of the first preset position is "main structure", the second preset position is at the pier of the bridge, the position category of the second preset position is "secondary structure", and the third preset position is at the bridge deck of the bridge, the position category of the third preset position is "local component"; the conventional vibration modes corresponding to the main structure include: low-frequency overall bending vibration, low-frequency torsional vibration and longitudinal expansion vibration, etc., the conventional vibration modes corresponding to the secondary structure include medium-frequency cable vibration and medium-frequency vibration of the pier, etc., and the conventional vibration modes corresponding to the local components include high-frequency bridge deck vibration, high-frequency vibration of welds / bolts, etc.; if the vibration mode at the preset position does not match the corresponding conventional vibration mode, it means that there is an abnormality in the vibration mode, and the vibration mode abnormality result is 1, otherwise the vibration mode abnormality result is 0.

[0112] According to one embodiment of the present invention, in step S5, environmental data is acquired at multiple moments in the monitoring period by environmental sensors disposed at preset positions, wherein the environmental data includes temperature data, humidity data, and wind data.

[0113] For example, temperature data, humidity data, and wind data at a preset location are acquired by setting a temperature sensor, a humidity sensor, and a wind sensor at the preset location.

[0114] According to one embodiment of the present invention, in step S6, the vibration pattern abnormality result, the vibration intensity coefficient and the environmental data are input into a trained fault occurrence time prediction model to determine the predicted fault occurrence time.

[0115] For example, the fault occurrence time prediction model is a deep learning neural network model (such as a long short-term memory network), which is a special recurrent neural network. By introducing gating mechanisms and cell states, it can effectively capture long-term dependencies in time series. It can be processed based on vibration pattern abnormal results, vibration intensity coefficients and environmental data to obtain the predicted fault occurrence time at each preset location.

[0116] According to one embodiment of the present invention, the training step of the fault occurrence time prediction model includes:

[0117] Acquire historical processed vibration data and historical environmental data of historical preset positions of other bridges in a historical time period, wherein the historical environmental data includes: historical temperature data, historical wind data, and historical humidity data;

[0118] determining a historical vibration pattern and a historical vibration intensity coefficient based on the historical processed vibration data;

[0119] determining an abnormal result of the historical vibration pattern based on the historical vibration pattern;

[0120] Inputting the historical vibration pattern abnormal results, the historical vibration intensity coefficient and the historical environmental data into a fault occurrence time prediction model to determine a sample predicted fault occurrence time;

[0121] Obtain historical maintenance records for other bridges;

[0122] Determine the most recent historical maintenance time based on the historical maintenance records;

[0123] Determining a training loss function for a fault occurrence time prediction model based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormality result, the historical vibration intensity coefficient, and the historical environmental data;

[0124] The fault occurrence time prediction model is trained according to the training loss function of the fault occurrence time prediction model to obtain a trained fault occurrence time prediction model.

[0125] For example, obtain historical processed vibration data and historical environmental data of other bridges with similar structures and spans to this bridge in a historical time period; determine the historical vibration pattern and historical vibration intensity coefficient based on the historical processed vibration data. The method of obtaining the historical vibration pattern and historical vibration intensity coefficient is similar to the method of obtaining the vibration pattern and vibration intensity coefficient, which will not be repeated here; determine the historical vibration pattern abnormal results corresponding to the historical preset positions of other bridges based on the historical vibration pattern. The method of determining the historical vibration pattern abnormal results is similar to the method of determining the vibration pattern abnormal results, which will not be repeated here; process the historical vibration pattern abnormal results, historical vibration intensity coefficients and historical environmental data according to the fault occurrence time prediction model to determine the sample predicted fault occurrence time. The sample predicted fault occurrence time is the length of time from the predicted time when each historical preset position needs to be repaired to the historical time period; obtain Historical maintenance records of other bridges; based on the historical maintenance records, determine the most recent historical maintenance time, for example, the first historical preset position of the first other bridge is located at the pier of the bridge, and the date of the first historical time period is January 1. According to the historical maintenance records, the pier was repaired at the location and the most recent maintenance time from January 1 was January 11. The time from January 11 to January 1 is 10 days, so the most recent historical maintenance time of the first historical preset position of the first other bridge in the first historical time period is 10 days; based on the most recent historical maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormality result, the historical vibration intensity coefficient and the historical environmental data, determine the training loss function of the fault occurrence time prediction model; train the fault occurrence time prediction model according to the training loss function to obtain a trained fault occurrence time prediction model.

[0126] According to one embodiment of the present invention, the training loss function of the fault occurrence time prediction model is determined based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormal result, the historical vibration intensity coefficient and the historical environmental data, including: determining the training loss function of the fault occurrence time prediction model according to formula (2): ,

[0127] (2)

[0128] Among them, if is a conditional function, is the most recent historical maintenance time of the rth historical preset position of the eth other bridge in the jth historical time period, For the sample prediction failure time of the rth historical preset position of the eth other bridge in the jth historical time period, is the historical vibration intensity coefficient of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, To preset the vibration intensity coefficient threshold, is the historical temperature data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, is the first preset temperature threshold, is the second preset temperature threshold, is the historical humidity data of the rth historical preset position of the eth other bridge in the jth historical time period, is the preset humidity threshold, is the historical wind force data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, To preset the wind data threshold, is the abnormal vibration pattern result of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, , n is the number of historical time periods, j≤n, E is the number of other bridges, e≤E, S is the number of moments in the historical time period, t≤S, R is the number of historical preset positions, r≤R, n, j, E, e, S, t, r and R are all positive integers.

[0129] According to one embodiment of the present invention, The ratio of the historical vibration intensity coefficient of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period to the preset vibration intensity coefficient threshold. The larger the ratio, the greater the historical vibration intensity coefficient of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period. The preset vibration intensity coefficient threshold can be set to , which means that the vibration frequency is significantly different from the natural frequency, the acceleration is within the limit, and the displacement is small, that is, the vibration intensity is in normal condition. is the abnormal result of the vibration pattern at the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period. When the vibration pattern is abnormal, The value of is 1, when the vibration mode is normal, The value of is 0, It indicates the vibration danger condition of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period. When the vibration mode is abnormal or the vibration intensity coefficient is larger, the larger the value is, the more serious the vibration danger condition is. = indicates that the magnitude of the vibration hazard condition and the sample predicted fault occurrence time are negatively correlated. For example, when the vibration hazard condition is more serious, the possibility of failure is greater and the sample predicted fault occurrence time is shorter. Therefore, the items related to the historical vibration intensity coefficient and the abnormal vibration pattern results are placed in the denominator, indicating that The larger the value of , the shorter the sample prediction failure time.

[0130] According to one embodiment of the present invention, in formula (2), the conditional function The value of includes the following two cases, when satisfying When the condition is met, it means that the temperature is within the normal range, and the value of the condition function is 1. When the condition is met, it means that the temperature is not within the normal range, and the value of the condition function is , , Can be set to -20 degrees Celsius, Can be set to 40 degrees Celsius, is the ratio of the absolute value of the historical temperature data at the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period to the average value of the first preset temperature threshold and the second preset temperature threshold. The larger the ratio, the greater the deviation of the historical temperature data from the normal temperature range. is the ratio of the historical humidity data of the rth historical preset position of the eth other bridge in the jth historical time period to the preset humidity threshold. The larger the ratio, the greater the historical humidity data. The preset humidity threshold can be set to 80%. The ratio of the historical wind data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period to the preset wind data threshold. The larger the ratio, the greater the historical wind data. The preset wind data threshold can be set to 20m / s. It indicates that the degree of deviation of historical temperature data from the normal temperature range, historical humidity data and historical wind data are negatively correlated with the size of the sample predicted fault occurrence time. For example, when the temperature is higher than 40 degrees Celsius, the elastic modulus of steel decreases at high temperature, resulting in an increase in vibration amplitude, which increases the possibility of fault occurrence and reduces the sample predicted fault occurrence time. When the temperature is lower than 20 degrees Celsius, the brittleness of steel and concrete increases, and the possibility of brittle fracture caused by vibration is higher, resulting in an increase in the possibility of fault occurrence and reduces the sample predicted fault occurrence time. When the humidity is higher, the corrosion rate of steel metal increases, resulting in an increase in the possibility of fault occurrence and reduces the sample predicted fault occurrence time. When the wind is stronger, it may cause aerodynamic instability, which increases the possibility of fault occurrence and reduces the sample predicted fault occurrence time. Therefore, the items related to historical temperature data, historical humidity data and historical wind data are placed in the denominator to indicate 、 and The larger the value of , the shorter the sample prediction failure time.

[0131] According to one embodiment of the present invention, The relative error between the predicted fault occurrence time and the most recent historical repair time for the sample at the rth historical preset position of the eth other bridge in the jth historical time period is calculated using and The relative errors of the sample predicted fault occurrence time are weighted averaged to obtain the training loss function. During the training process, the above training loss function is reduced, thereby reducing the error between the sample predicted fault occurrence time and the historical most recent maintenance time, and improving the accuracy of the fault occurrence time prediction model in predicting the fault occurrence time, thereby improving the accuracy of the fault occurrence time prediction model.

[0132] In this way, the training loss function of the fault occurrence time prediction model can be determined based on the historical most recent maintenance time, sample predicted fault occurrence time, historical vibration pattern abnormal results, historical vibration intensity coefficient and historical environmental data. The influence of vibration intensity, vibration pattern and environmental data on the sample predicted fault occurrence time can be determined, and the training loss function can be set based on the influence and the relative error of the sample predicted fault occurrence time. This will reduce the training loss function of the fault occurrence time prediction model during the training process, and improve the accuracy of the fault occurrence time prediction model in a more targeted manner.

[0133] According to an embodiment of the present invention, in step S7, early warning information is generated according to the vibration source and the predicted fault occurrence time.

[0134] Figure 4 A schematic diagram of generating early warning information according to an embodiment of the present invention is exemplarily shown.

[0135] According to one embodiment of the present invention, step S7 includes:

[0136] Step S71, determining a preset first time threshold and a preset second time threshold;

[0137] Step S72, determining the warning level at each preset location based on the predicted fault occurrence time at each preset location, the preset first time threshold, and the preset second time threshold;

[0138] Step S73 : generating warning information according to the vibration source, the location category of each preset location, and the warning degree at each preset location.

[0139] For example, the preset first time threshold is set to 10 days, and the preset second time threshold is set to 100 days; the warning level at each preset location is evaluated based on the predicted fault occurrence time, the preset first time threshold and the preset second time threshold at each preset location; specific warning information is generated based on the vibration source, the location category of each preset location and the warning level at each preset location, such as a high-level warning caused by a vehicle at the pier of a bridge.

[0140] According to one embodiment of the present invention, step S72 includes:

[0141] Step S721: When the predicted fault occurrence time at the k-th preset position is less than the preset first time threshold, the warning level at the k-th preset position is a high warning;

[0142] Step S721: When the predicted fault occurrence time at the k-th preset location is greater than or equal to the preset first time threshold and less than or equal to the preset second time threshold, the warning level at the k-th preset location is a medium warning;

[0143] Step S723: When the predicted fault occurrence time at the k-th preset position is greater than the preset second time threshold, the warning level at the k-th preset position is a low-level warning.

[0144] For example, when the predicted failure occurrence time at the k-th preset position is less than 10 days, it means that there is a serious safety hazard at this position under vibration, and the warning level is a high-level warning; when the predicted failure occurrence time at the k-th preset position is greater than 10 days and less than 100 days, it means that there is a certain safety hazard at this position under vibration, and the warning level is a medium-level warning; when the predicted failure occurrence time at the k-th preset position is greater than 100 days, it means that there may be a safety hazard at this position under vibration, and the warning level is a low-level warning.

[0145] According to the bridge vibration monitoring and early warning method of an embodiment of the present invention, vibration data can be accurately collected and processed, and the vibration source, vibration mode and vibration intensity coefficient can be accurately analyzed based on the processed vibration data. Furthermore, based on the environmental data, vibration mode and vibration intensity coefficient, the time of occurrence of failure at each preset position of the bridge is predicted, and early warning information is generated based on the vibration source and the predicted time of occurrence of the failure, thereby improving the accuracy of bridge vibration monitoring and early warning. When determining the vibration intensity coefficient, the vibration intensity coefficient can be determined based on the measured damping ratio, design damping ratio, natural frequency, vibration acceleration, vibration displacement, vibration frequency, acceleration limit and displacement limit. During the calculation process, the impact intensity of the vibration can be evaluated based on the three aspects of resonant risk condition, sudden instability risk condition and displacement condition, thereby improving the comprehensiveness and accuracy of the vibration intensity coefficient. When determining the training loss function, the training loss function of the fault occurrence time prediction model can be determined based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormal results, the historical vibration intensity coefficient and the historical environmental data. The influence of vibration intensity, vibration pattern and environmental data on the sample predicted fault occurrence time can be determined, and the training loss function can be set based on the influence and the relative error of the sample predicted fault occurrence time, so that the training loss function of the fault occurrence time prediction model can be reduced during the training process, and the accuracy of the fault occurrence time prediction model can be improved in a more targeted manner.

[0146] Figure 5 A block diagram of a bridge vibration monitoring and early warning system according to an embodiment of the present invention is exemplarily shown. The system includes:

[0147] A vibration data module is used to obtain vibration data to be processed through a combination of sensors set at preset positions at multiple moments in the monitoring cycle;

[0148] a data processing module, configured to obtain processed vibration data based on the vibration data to be processed;

[0149] a vibration pattern module, configured to determine a vibration source, a vibration pattern, and a vibration intensity coefficient based on the processed vibration data;

[0150] A pattern abnormality module, configured to determine a vibration pattern abnormality result based on the vibration pattern;

[0151] An environmental data module is used to obtain environmental data at multiple moments in a monitoring period through environmental sensors set at preset positions, wherein the environmental data includes: temperature data, humidity data and wind speed data;

[0152] a time prediction module, configured to input the vibration pattern abnormality result, the vibration intensity coefficient, and the environmental data into a trained fault occurrence time prediction model to determine a predicted fault occurrence time;

[0153] The early warning information module is used to generate early warning information according to the vibration source and the predicted fault occurrence time.

[0154] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0155] Those skilled in the art will appreciate that the embodiments of the present invention described above and shown in the accompanying drawings are intended to be illustrative only and are not intended to limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and illustrated in the embodiments. Any variations or modifications may be made to the embodiments of the present invention without departing from the principles described.

Claims

1. A bridge vibration monitoring and early warning method, characterized in that: include: At multiple moments in the monitoring cycle, vibration data to be processed is obtained through a combination of sensors set at preset positions; acquiring processed vibration data according to the vibration data to be processed; determining a vibration source, a vibration mode, and a vibration intensity coefficient based on the processed vibration data; determining a vibration pattern abnormality result based on the vibration pattern; At multiple moments in the monitoring cycle, environmental data is acquired through environmental sensors disposed at preset locations, wherein the environmental data includes: temperature data, humidity data, and wind speed data; Inputting the vibration pattern abnormality result, the vibration intensity coefficient and the environmental data into a trained fault occurrence time prediction model to determine a predicted fault occurrence time; generating early warning information according to the vibration source and the predicted fault occurrence time; The training steps of the fault occurrence time prediction model include: Acquire historical processed vibration data and historical environmental data of historical preset positions of other bridges in a historical time period, wherein the historical environmental data includes: historical temperature data, historical wind data, and historical humidity data; determining a historical vibration pattern and a historical vibration intensity coefficient based on the historical processed vibration data; determining an abnormal result of the historical vibration pattern based on the historical vibration pattern; Inputting the historical vibration pattern abnormal results, the historical vibration intensity coefficient and the historical environmental data into a fault occurrence time prediction model to determine a sample predicted fault occurrence time; Obtain historical maintenance records for other bridges; Determine the most recent historical maintenance time based on the historical maintenance records; Determining a training loss function for a fault occurrence time prediction model based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormality result, the historical vibration intensity coefficient, and the historical environmental data; Training the fault occurrence time prediction model according to the training loss function of the fault occurrence time prediction model to obtain a trained fault occurrence time prediction model; Determining a training loss function of a fault occurrence time prediction model based on the historical most recent maintenance time, the sample predicted fault occurrence time, the historical vibration pattern abnormality result, the historical vibration intensity coefficient, and the historical environmental data includes: According to the formula Determine the training loss function of the failure time prediction model , where if is a conditional function, is the most recent historical maintenance time of the rth historical preset position of the eth other bridge in the jth historical time period, For the sample prediction failure time of the rth historical preset position of the eth other bridge in the jth historical time period, is the historical vibration intensity coefficient of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, To preset the vibration intensity coefficient threshold, is the historical temperature data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, is the first preset temperature threshold, is the second preset temperature threshold, is the historical humidity data of the rth historical preset position of the eth other bridge in the jth historical time period, is the preset humidity threshold, is the historical wind force data of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, To preset the wind data threshold, is the abnormal vibration pattern result of the rth historical preset position of the eth other bridge at the tth moment in the jth historical time period, , n is the number of historical time periods, j≤n, E is the number of other bridges, e≤E, S is the number of moments in the historical time period, t≤S, R is the number of historical preset positions, r≤R, n, j, E, e, S, t, r and R are all positive integers.

2. The bridge vibration monitoring and early warning method according to claim 1 is characterized in that: Determining a vibration source, a vibration mode, and a vibration intensity coefficient based on the processed vibration data includes: obtaining an original vibration signal and a time-frequency spectrum diagram according to the processed vibration data; Inputting the original vibration signal and the time-frequency spectrum into a vibration pattern recognition model to determine the vibration pattern; Inputting the original vibration signal and the time-frequency spectrum into a vibration source identification model to determine the vibration source; determining vibration displacement, vibration acceleration, and vibration frequency based on the original vibration signal; A vibration intensity coefficient is determined according to the vibration displacement, the vibration acceleration, and the vibration frequency.

3. The bridge vibration monitoring and early warning method according to claim 2 is characterized in that: Determining a vibration intensity coefficient according to the vibration displacement, the vibration acceleration, and the vibration frequency includes: Obtain the measured damping ratio, designed damping ratio and natural frequency of the bridge; Determine acceleration limits and displacement limits; A vibration intensity coefficient is determined according to the measured damping ratio, the designed damping ratio, the natural frequency, the vibration acceleration, the vibration displacement, the vibration frequency, the acceleration limit, and the displacement limit.

4. The bridge vibration monitoring and early warning method according to claim 3 is characterized in that: Determining a vibration intensity coefficient according to the measured damping ratio, the designed damping ratio, the natural frequency, the vibration acceleration, the vibration displacement, the vibration frequency, the acceleration limit, and the displacement limit includes: According to the formula Determine the vibration intensity coefficient of the kth preset position at the i-th moment in the monitoring cycle , where if is a conditional function, 、 and is the preset weight, is the vibration frequency of the kth preset position at the i-th moment in the monitoring period, is the natural frequency, is the vibration acceleration of the k-th preset position at the i-th moment in the monitoring cycle, is the acceleration limit, is the measured damping ratio of the kth preset position at the i-th moment in the monitoring period, To design the damping ratio, is the vibration displacement of the k-th preset position at the i-th moment in the monitoring period, is the displacement limit.

5. The bridge vibration monitoring and early warning method according to claim 1 is characterized in that: Determining a vibration pattern abnormality result according to the vibration pattern includes: Get the location category of each preset location; determining a regular vibration pattern based on the location category; A vibration pattern abnormality result is determined based on the vibration pattern and the normal vibration pattern.

6. The bridge vibration monitoring and early warning method according to claim 5, characterized in that: Generate warning information based on the vibration source and the predicted fault occurrence time, including: Determining a preset first time threshold and a preset second time threshold; Determining the warning level at each preset location based on the predicted fault occurrence time at each preset location, the preset first time threshold, and the preset second time threshold; Warning information is generated according to the vibration source, the location category of each preset location, and the warning level at each preset location.

7. The bridge vibration monitoring and early warning method according to claim 6 is characterized in that: Determining the warning level at each preset location based on the predicted fault occurrence time at each preset location, the preset first time threshold, and the preset second time threshold includes: When the predicted fault occurrence time at the k-th preset position is less than the preset first time threshold, the warning level at the k-th preset position is a high warning; When the predicted fault occurrence time at the k-th preset position is greater than or equal to the preset first time threshold and less than or equal to the preset second time threshold, the warning level at the k-th preset position is a medium warning; When the predicted fault occurrence time at the k-th preset position is greater than the preset second time threshold, the warning level at the k-th preset position is a low-level warning.

8. A bridge vibration monitoring and early warning system for executing the method according to any one of claims 1 to 7, characterized in that: include: A vibration data module is used to obtain vibration data to be processed through a combination of sensors set at preset positions at multiple moments in the monitoring cycle; a data processing module, configured to obtain processed vibration data based on the vibration data to be processed; a vibration pattern module, configured to determine a vibration source, a vibration pattern, and a vibration intensity coefficient based on the processed vibration data; A pattern abnormality module, configured to determine a vibration pattern abnormality result based on the vibration pattern; An environmental data module is used to obtain environmental data at multiple moments in a monitoring period through environmental sensors set at preset positions, wherein the environmental data includes: temperature data, humidity data and wind speed data; a time prediction module, configured to input the vibration pattern abnormality result, the vibration intensity coefficient, and the environmental data into a trained fault occurrence time prediction model to determine a predicted fault occurrence time; The early warning information module is used to generate early warning information according to the vibration source and the predicted fault occurrence time.

Images