A light rail bridge abnormal state identification method, device and equipment and a storage medium

Abstract

This invention discloses a method, device, equipment, and storage medium for identifying abnormal states of light rail bridges. The method includes the following steps: for bridges with the same structural form and span arrangement, monitoring data of each measuring point on the bridge is acquired based on dynamic strain measuring points set at the same control section and spatial location on the bridge; based on the monitoring data, the dynamic strain response when the first train crosses the bridge is determined, and the dynamic strain influence line of the first train crossing the bridge is obtained through the dynamic strain response; based on the dynamic strain influence line, it is determined whether there is an abnormality in the light rail bridge. This application can effectively determine the abnormal state of light rail bridges when trains pass over them, solving the problem of abnormal diagnosis of light rail bridges in actual operation. At the same time, by judging the abnormal state of light rail bridges, the structural safety and health monitoring of light rail bridges is realized, ensuring the smooth operation of the line.

Description

Technical Field

[0001] This invention relates to the field of bridge structural health monitoring technology, and in particular to a method, device, equipment and storage medium for identifying abnormal conditions of light rail bridges. Background Technology

[0002] Urban rail transit has developed rapidly due to its advantages such as large passenger capacity, safety, convenience, and low environmental pollution, gradually becoming the dominant mode of transportation in cities. Light rail, with its characteristics of lower investment, shorter construction period, and less impact on surface traffic, is widely used in urban rail transit. However, during the operation of urban rail transit, adverse factors such as differential settlement of foundations, moving train loads, material aging and deterioration, and drastic environmental changes can all cause changes in the structural condition of light rail bridges, seriously jeopardizing the operational safety of light rail.

[0003] Therefore, how to identify abnormal conditions of light rail bridges is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, equipment, and storage medium for identifying abnormal states of light rail bridges. This method effectively identifies abnormal states of light rail bridges when vehicles pass over them, solving the problem of abnormal bridge diagnosis in actual operation. Furthermore, by identifying abnormal states, it enables monitoring of the structural safety and health of light rail bridges, ensuring stable line operation.

[0005] Firstly, this application provides a method for identifying abnormal states of light rail bridges, the method comprising the following steps:

[0006] Based on bridges with the same structural form and span arrangement, monitoring data of each measuring point on the bridge are obtained according to the dynamic strain measuring points set at the same control section and spatial location on the bridge.

[0007] Based on the monitoring data, the dynamic strain response when the first train crosses the bridge is determined, and the dynamic strain influence line of the first train crossing the bridge is obtained through the dynamic strain response.

[0008] Based on the dynamic strain influence line, determine whether there are any abnormalities in the light rail bridge.

[0009] In conjunction with the first aspect mentioned above, as an optional implementation method, the dynamic strain influence line of the first train crossing the bridge each day at each measuring point is obtained, and the dynamic strain influence line of the first train crossing the bridge at one of the measuring points is selected. The similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day is calculated using the cross-validation method.

[0010] Calculate the average similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge each day at other measuring points, and use the average value as the similarity of the selected dynamic strain influence line.

[0011] When the similarity of the selected dynamic strain influence lines is less than a set threshold, it is determined that the selected bridge measuring points are not abnormal.

[0012] If the similarity of the selected dynamic strain influence lines is greater than a set threshold, it is determined that the selected bridge measuring points are abnormal.

[0013] In conjunction with the first aspect mentioned above, as an optional implementation method, based on the dynamic strain response of the first train crossing the bridge, the peak extraction method is used to obtain the time corresponding to the dynamic strain trough when the first train crosses the bridge.

[0014] Based on the time corresponding to the dynamic strain trough when the first train crosses the bridge, determine the times corresponding to the preceding and following troughs;

[0015] The dynamic strain monitoring data within the time corresponding to the preceding and following troughs are normalized by time and resampled to form the dynamic strain influence line of the first train crossing the bridge.

[0016] In conjunction with the first aspect mentioned above, as an optional implementation method, the peak extraction method is adopted to obtain the moment corresponding to the peak of dynamic strain wave when the first train crosses the bridge;

[0017] The moment corresponding to the peak of the dynamic strain wave when the first train crosses the bridge is taken as the base point. The monitoring data before and after the base point at fixed times are determined and used as the dynamic strain response of the first train crossing the bridge.

[0018] In conjunction with the first aspect mentioned above, as an optional implementation method, strain sensors are installed at the same control section and the same location in the same span of the bridge, based on the bridge with the same structural form and span arrangement selected on the light rail route.

[0019] Based on the strain sensor, dynamic strain monitoring data of each measuring point on the bridge are obtained.

[0020] In conjunction with the first aspect mentioned above, as an optional implementation method, monitoring data from various measuring points on the bridge are selected within a preset time period, and the monitoring data from various measuring points on the bridge selected within the preset time period are analyzed. The monitoring data includes one or more train crossing events, with the first train crossing the bridge being the first train crossing event within the preset time period.

[0021] Secondly, this application provides a light rail bridge abnormal state identification device, the device comprising:

[0022] The acquisition module is used to acquire monitoring data of each measuring point on a bridge with the same structural form and span arrangement, based on the dynamic strain measuring points set at the same control section and spatial position on the bridge.

[0023] The determination module is used to determine the dynamic strain response of the first train crossing the bridge based on the monitoring data, and to obtain the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response;

[0024] The judgment module is used to determine whether there is any abnormality in the light rail bridge based on the dynamic strain influence line.

[0025] In conjunction with the second aspect above, as an optional implementation, the judgment module is further configured to:

[0026] Obtain the dynamic strain influence line of the first train crossing the bridge each day at each measuring point, and select the dynamic strain influence line of the first train crossing the bridge at one of the measuring points. Use the cross-validation method to calculate the similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day.

[0027] Calculate the average similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge each day at other measuring points, and use the average value as the similarity of the selected dynamic strain influence line.

[0028] When the similarity of the selected dynamic strain influence lines is less than a set threshold, it is determined that the selected bridge measuring points are not abnormal.

[0029] If the similarity of the selected dynamic strain influence lines is greater than a set threshold, it is determined that the selected bridge measuring points are abnormal.

[0030] Thirdly, this application also provides an electronic device, the electronic device comprising: a processor; and a memory storing computer-readable instructions, which, when executed by the processor, implement the method described in any one of the first aspects.

[0031] Fourthly, this application also provides a computer-readable storage medium storing computer program instructions that, when executed by a computer, cause the computer to perform the method described in any of the first aspects.

[0032] This application provides a method, apparatus, equipment, and storage medium for identifying abnormal states of light rail bridges. The method includes the following steps: for bridges with the same structural form and span arrangement, monitoring data of each measuring point on the bridge is acquired based on dynamic strain measuring points set at the same control section and spatial location on the bridge; based on the monitoring data, the dynamic strain response when the first train crosses the bridge is determined, and the dynamic strain influence line of the first train crossing the bridge is obtained through the dynamic strain response; based on the dynamic strain influence line, it is determined whether there is an anomaly in the light rail bridge. This application can effectively determine the abnormal state of light rail bridges when trains pass over them, solving the problem of abnormal diagnosis of light rail bridges in actual operation. At the same time, by judging the abnormal state of light rail bridges, the structural safety and health monitoring of light rail bridges is realized, ensuring the smooth operation of the line.

[0033] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0035] Figure 1 This is a flowchart of a method for identifying abnormal states of a light rail bridge provided in an embodiment of this application;

[0036] Figure 2 This is a schematic diagram of a light rail bridge abnormality identification device provided in the embodiments of this application;

[0037] Figure 3 The following are dynamic strain time history curves of different measuring points when the first train crosses the bridge, provided in the embodiments of this application;

[0038] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of this application;

[0039] Figure 5 This is a schematic diagram of a computer-readable program medium provided in an embodiment of this application. Detailed Implementation

[0040] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0041] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings represent functional entities and do not necessarily correspond to physically or logically independent entities.

[0042] This application provides a method, device, equipment, and storage medium for identifying abnormal states of light rail bridges. It effectively determines the abnormal states of light rail bridges when vehicles pass over them, solving the problem of abnormal bridge diagnosis in actual operation. Simultaneously, by determining the abnormal states of light rail bridges, it enables structural safety and health monitoring of the light rail bridges, ensuring stable line operation.

[0043] It should be noted that, unlike highway bridges, light rail bridges have unique structural forms and operational characteristics. Structurally, to ensure smooth operation, light rail bridges often employ simply supported beams, continuous beams, or continuous rigid frames, and many bridges along the entire line share the same structural form and span arrangement. Operationally, fixed-formation trains pass over bridges according to a timetable, traveling on fixed up and down lines. This means the moving train loads on the bridges are similar when trains pass over them. Considering the first train of the day, the moving train loads and load distribution on the bridges are identical. Based on these characteristics, bridges with the same structural form and span arrangement along the light rail line are selected. Dynamic strain sensors are deployed at the same control section and spatial location within the same span to obtain the strain influence line when the first train passes over the bridge. The degree of similarity of the strain influence line of the first train is used to determine the abnormal state of the light rail bridge structure.

[0044] To achieve the aforementioned technical effects, the general concept of this application is as follows:

[0045] A method for identifying abnormal states of light rail bridges, the method comprising the following steps:

[0046] S101: For bridges with the same structural form and span arrangement, the monitoring data of each measuring point on the bridge is obtained based on the dynamic strain measuring points set at the same control section and spatial location on the bridge.

[0047] S102: Based on the monitoring data, determine the dynamic strain response when the first train crosses the bridge, and obtain the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response.

[0048] S103: Based on the dynamic strain influence line, determine whether there is any abnormality in the light rail bridge.

[0049] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0050] Reference Figure 1 , Figure 1 The diagram shown is a flowchart of a light rail bridge abnormality identification method provided by the present invention. Figure 1 As shown, the method includes the following steps:

[0051] Step S101: Based on bridges with the same structural form and span arrangement, obtain monitoring data of each measuring point on the bridge according to the dynamic strain measuring points set at the same control section and spatial location on the bridge.

[0052] Specifically, bridges with the same structural form and span are selected on the light rail line, and strain sensors are installed at the same control section and spatial location in the same span to obtain dynamic strain monitoring data at each measuring point. It should be noted that the dynamic strain monitoring data is strain data collected at a specified frequency, such as strain data collected at a frequency of 100Hz.

[0053] In one embodiment, the dynamic strain monitoring data acquisition method includes the following steps: Step 1: Let Z be the set of bridge clusters along the entire light rail line. Divide the bridge clusters into N groups according to their structural form and span arrangement. The bridges in each group have the same structural form and span arrangement, defined as follows: In the formula, Z k Let N be the set of the k-th group of bridges in the light rail bridge cluster, where 1 ≤ k ≤ N.

[0054] Step 2: For the set Z of the k-th group of bridges in the light rail bridge cluster... k The same control section at the same mid-span and the same spatial location are selected as dynamic strain measurement points, for a total of n. k One, which is defined as: In the formula, Z i Let i be the i-th dynamic strain measurement point in the k-th bridge group, where 1 ≤ i ≤ n k .

[0055] Step 3: Let X be the set of dynamic strain monitoring data for the i-th measuring point in the k-th bridge group. i The dynamic strain monitoring data set for day d is X. i,d Their definitions are as follows: X i ={X i,1 ,X i,2 ,…,X i,d ,…X i,m}; In the formula, m is the total number of days for data collection at the dynamic strain measurement points, and 1 ≤ d ≤ m; Let l be the dynamic strain value of the i-th measuring point at time j on day d; d Let j be the total number of dynamic strain samples taken at the i-th measuring point on day d, where 1 ≤ j ≤ l. d .

[0056] In one embodiment, the dynamic strain monitoring data of each measuring point is selected from the time period from 5:00 am to 6:00 am every day. The monitoring within the preset time period includes one or more train crossing events, and the first train crossing the bridge is regarded as the first train crossing event within the time period.

[0057] Optionally, the dynamic strain monitoring data set X of the i-th measuring point on day d. i,d Set a reasonable time interval, and define the first train crossing the bridge within this time interval as the first train crossing event. Let this time interval be T1. i,d The start and end times are s1 and s2 respectively. i,d and e1 i,d Then the set of dynamic strain monitoring data selected by the i-th measuring point on day d is: Its definition is:

[0058] In the formula, 1≤s1 i,d <e1 i,d ≤l d ;

[0059] Step S102: Based on the monitoring data, determine the dynamic strain response when the first train crosses the bridge, and obtain the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response.

[0060] Specifically, for the monitoring data within a preset time period, the peak extraction method is used to obtain the moment corresponding to the dynamic strain peak when the first train crosses the bridge. This moment is used as a reference point, and monitoring data of a fixed time length before and after this point are taken as the dynamic strain response of the first train crossing the bridge. Based on the obtained dynamic strain response of the first train crossing the bridge, the peak extraction method is used to obtain the moment corresponding to the dynamic strain trough when the first train crosses the bridge. The time period between the preceding and following troughs is then regarded as the time taken for the train to cross the bridge. The dynamic strain monitoring data of this period is normalized by time and resampled to obtain the dynamic strain influence line of the first train crossing the bridge.

[0061] To illustrate this, the peak value extraction method is used to extract the peak point of the dynamic strain wave during the first train's crossing of the bridge. Using this as the center point, the dynamic strain monitoring data within the preceding and following 20-second intervals can be considered as the dynamic strain response of the first train's crossing of the bridge. Based on the obtained dynamic strain response of the first train's crossing of the bridge, the peak value extraction method is used to obtain the time corresponding to the dynamic strain trough when the first train crosses the bridge. The time interval between the preceding and following troughs is taken as the time taken by the train to cross the bridge. The dynamic strain monitoring data during this period is normalized by time and resampled to form the dynamic strain influence line of the first train crossing the bridge (that is, after setting the crossing time of the first train to a preset duration, the dynamic strain influence line of the first train crossing the bridge is re-collected).

[0062] In one embodiment, the method for extracting dynamic strain monitoring data during the first train crossing the bridge includes the following steps: Step 1: Selecting the dynamic strain monitoring data set of the i-th measuring point on day d. The peak extraction method is used to find the first peak point that meets specific conditions. This refers to the maximum dynamic strain response of the i-th measuring point during the first train crossing the bridge on day d, which is defined as: In the formula, findpeak(·) is the function used by the peak extraction method to find the first peak point that meets specific conditions; p height The threshold value for the peak height parameter of the function findpeak(·); p distance The threshold value is the peak spacing parameter for the function findpeak(·).

[0063] Step 2: Let the peak value of the dynamic strain response of the i-th measuring point during the first train crossing the bridge on day d be... Taking the center point of the first train crossing the bridge as the reference point, dynamic strain monitoring data for appropriate time intervals before and after the first train crossing the bridge are taken as the dynamic strain response. Let this time interval be T2. i,d The start and end times are s2 and s2 respectively. i,d and e2 i,d Then, the set of dynamic strain responses of the i-th measuring point during the first train crossing the bridge on day d is: Its definition is: In the formula, s1 i,d ≤s2 i,d <e2 i,d ≤e1 i,d ;

[0064] In one embodiment, the method for calculating the dynamic strain influence line of the first train crossing the bridge includes the following steps: Step 1: The set of dynamic strain responses of the first train crossing the bridge selected at the i-th measuring point on day d is... The peak extraction method was used to determine the two dynamic strain wave troughs before and after the first train crossed the bridge. and previous trough point This can be considered as the characteristic point of the dynamic strain response of the first train crossing the bridge, and the trough point of the subsequent wave. This can be considered as the characteristic point of the dynamic strain response of the first train off the bridge, and it is defined as: In the formula, findtrough(·) is the function used to find the preceding and following trough points that meet specific conditions using the peak extraction method; t height The threshold value for the valley depth parameter of the function findtrough(·); t distance The threshold value is the trough spacing parameter of the function findtrough(·).

[0065] Step 2: Based on Step 1, determine the two dynamic strain wave troughs before and after the first train crosses the bridge. and The time T3 for the first train to cross the bridge at the i-th measuring point on day d can be calculated. i,d Its expression is: To eliminate the difference in the influence line of the train speed on the dynamic strain during the first train crossing the bridge, the dynamic strain response set of the first train crossing the bridge at the i-th measuring point on day d is as follows: Still at the peak point Taking the center point of the first train crossing the bridge as the reference point, take T3 points forward and backward. i,d Time, let the time interval be 2T3. i,d The start and end times are s3 and s3 respectively. i,d and e3 i,d Then, the set of dynamic strain influence lines for the first train crossing the bridge at the i-th measuring point on day d is: Its definition is: In the formula, s3 i,d ≤t1 i,d <p i,d <t2 i,d ≤e3 i ,d ;

[0066] Step 3: Let T be the reference time for the first train to cross the bridge. r The set of dynamic strain influence lines for the first train crossing the bridge at the i-th measuring point on day d, obtained using the resampling method, is as follows: After scaling the time axis, the dynamic strain influence line of the first train crossing the bridge on day d at the i-th measurement point after resampling is: Its expression is: N r =2f s T r In the formula, resample(·) is the data resampling function; N r f is the target data length parameter for the function resample(·); s The frequency for dynamic strain acquisition.

[0067] Step S103: Determine whether there is any abnormality in the light rail bridge based on the dynamic strain influence line.

[0068] Specifically,

[0069] Obtain the dynamic strain influence lines of the first train crossing the bridge each day at each measuring point, and select the dynamic strain influence line of the first train crossing the bridge at one measuring point. Use cross-validation to calculate the similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day. Calculate the average similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day, and use the average value as the similarity of the selected dynamic strain influence line. If the similarity of the selected dynamic strain influence line is less than a set threshold, it is determined that the selected bridge measuring point has no abnormalities; if the similarity of the selected dynamic strain influence line is greater than the set threshold, it is determined that the selected bridge measuring point has an abnormality.

[0070] In one embodiment, based on the obtained dynamic strain influence line of the first train crossing the bridge, the Euclidean distance between the first train crossing the bridge events at different measuring point locations and at different times is calculated using a cross-validation method as a similarity index. An appropriate distance threshold is set as an abnormal state judgment criterion. If the distance is less than or equal to the threshold, there is no abnormal state; otherwise, an abnormal state occurs at the measuring point in the corresponding time period, which needs to be investigated urgently. It should be noted that the threshold needs to be calculated based on the similarity from historical data and selected after statistics.

[0071] To illustrate this, consider three bridges on a light rail line, A, B, and C, with identical structures and span arrangements. Monitoring data for three days is collected. Bridge A has three dynamic strain influence lines for the first train crossing each day, as do bridges B and C, totaling nine. Assuming each influence line has a length of 1×1000, a 1×1000 value is taken from one of the other nine influence lines (including itself) and calculated using a similarity formula. The average of these nine values ​​is then used as the similarity index for the selected influence line. This process is repeated nine times to calculate nine similarity indices. These indices are compared to a set threshold to determine if any anomalies exist. In essence, when the similarity index of one influence line exceeds the set threshold, the bridge with the problem can be accurately identified based on the bridge monitoring points corresponding to that influence line.

[0072] It should also be noted that the threshold is defined as follows: Assuming a known anomaly-free state, and given 1000 similarity indicators (e.g., 10 bridges over 100 days), these 1000 similarity indicators are statistically analyzed. The similarity indicator value corresponding to the 95th percentile is calculated, and this 95th percentile value is multiplied by a guarantee coefficient, such as 1.2. This multiplier represents the set threshold. It's important to understand that the threshold is based on historical statistical results.

[0073] Optionally, there are n bridges with the same structure along the entire line. Strain sensors are installed at the same locations on these bridges and monitored for m days. n*m strain influence lines of the first train of each day are extracted. One of these lines is selected and its similarity is calculated with itself and the other n*m lines. The similarity of the influence lines of the same measuring point on different days is calculated, as well as the similarity of the influence lines of different measuring points on the same day and on different days.

[0074] Optionally, based on the dynamic strain influence line of the first train crossing the bridge, the similarity between each influence line and other influence lines is calculated using the cross-validation method. The average value is taken as the similarity of the dynamic strain influence line of the measuring point on that day, and compared with the threshold to make an abnormal state judgment. Other influence lines can be understood as the influence lines of the same measuring point on different days and / or the influence lines of different measuring points on the same day and different days.

[0075] In one embodiment, the dynamic strain abnormal state judgment method includes the following steps: Step 1: For n bridges in the k-th group... k Dynamic strain monitoring data from m days at various dynamic strain measurement points were processed. The processing method involved determining the dynamic strain response when the first train crossed the bridge based on the monitoring data, and then obtaining the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response, thus obtaining n... k Set of ×m dynamic strain influence lines for the first train crossing the bridge after resampling Its definition is:

[0076] Step 2: Calculate the similarity index between the dynamic strain influence lines of the first train crossing the bridge after resampling and other dynamic strain influence lines using cross-validation. The similarity η of the dynamic strain influence line of the i-th measuring point on day d is used as the criterion. i,d Taking the calculation as an example, firstly, we take the dynamic strain influence line of the first train crossing the bridge at the i-th measuring point on day d. The dynamic strain influence line of the i1th measuring point during the first train crossing the bridge on day d1. Similarity between two dynamic strain influence lines The calculation formula is:

[0077] The set of dynamic strain influence lines of the first train crossing the bridge after resampling is traversed sequentially. n k ×m dynamic strain influence lines are respectively connected to the dynamic strain influence line of the i-th measuring point during the first train crossing the bridge on day d. Similarity calculations are performed to obtain the similarity set η of the dynamic strain influence line of the i-th measuring point on day d. i,d Its definition is: Then the similarity η of the dynamic strain influence line of the i-th measuring point on day d is... i,d The expression is:

[0078]

[0079] Step 3: Set a similarity threshold ξ. If the similarity η of the dynamic strain influence line of the i-th measuring point on day d is... i,d If the value is greater than the threshold ξ, it indicates that the measuring point is in an abnormal state on that day and needs to be investigated urgently; otherwise, there is no abnormal state.

[0080] Understandably, one method for identifying abnormal states of light rail bridges involves selecting bridges with the same structural form and span arrangement on the light rail line, and deploying strain sensors at the same control section and spatial location within the same span to acquire dynamic strain monitoring data at each measuring point. For the acquired dynamic strain monitoring data, a specific time period is selected, including one or more train crossing events, with the first train crossing the bridge considered the first train crossing event within that time period. For the selected monitoring data within the preset time period, a peak extraction method is used to obtain the time corresponding to the dynamic strain peak when the first train crosses the bridge, which is then used as a reference point. Monitoring data of a fixed time length before and after this point are taken as the dynamic strain response during the first train crossing the bridge. Based on the obtained dynamic strain response of the first train crossing the bridge, the peak extraction method was used to obtain the time corresponding to the dynamic strain trough when the first train crossed the bridge. The time period between the preceding and following troughs was then regarded as the time taken for the train to cross the bridge. The dynamic strain monitoring data during this period was normalized by time and resampled to form the dynamic strain influence line of the first train crossing the bridge. For the obtained dynamic strain influence line of the first train crossing the bridge, the Euclidean distance between the first train crossing the bridge events at different measuring point locations and at different times was calculated using the cross-validation method as a similarity index. An appropriate distance threshold was set as an abnormal state judgment criterion. If the distance is less than or equal to the threshold, there is no abnormal state; otherwise, an abnormal state occurs at the measuring point within the corresponding time period, which needs to be investigated urgently.

[0081] Reference Figure 2 , Figure 2 The diagram shown is a schematic of an abnormal state identification device for light rail bridges provided by the present invention. Figure 2 As shown, the device includes:

[0082] Acquisition module 201: It is used to acquire monitoring data of each measuring point on the bridge based on the same structural form and span arrangement of the bridge, according to the dynamic strain measuring points set at the same control section and spatial position on the bridge.

[0083] Determining module 202: It is used to determine the dynamic strain response when the first train crosses the bridge based on the monitoring data, and to obtain the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response.

[0084] Judgment module 203: It is used to determine whether there is an abnormality in the light rail bridge based on the dynamic strain influence line.

[0085] Furthermore, in one possible implementation, the determination module 203 is also used to,

[0086] Obtain the dynamic strain influence line of the first train crossing the bridge each day at each measuring point, and select the dynamic strain influence line of the first train crossing the bridge at one of the measuring points. Use the cross-validation method to calculate the similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day.

[0087] Calculate the average similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge each day at other measuring points, and use the average value as the similarity of the selected dynamic strain influence line.

[0088] When the similarity of the selected dynamic strain influence lines is less than a set threshold, it is determined that the selected bridge measuring points are not abnormal.

[0089] If the similarity of the selected dynamic strain influence lines is greater than a set threshold, it is determined that the selected bridge measuring points are abnormal.

[0090] Furthermore, in one possible implementation, the determining module 202 is also used to,

[0091] Based on the dynamic strain response when the first train crosses the bridge, the peak extraction method is used to obtain the time corresponding to the dynamic strain trough when the first train crosses the bridge.

[0092] Based on the time corresponding to the dynamic strain trough when the first train crosses the bridge, determine the times corresponding to the preceding and following troughs;

[0093] The dynamic strain monitoring data within the time corresponding to the preceding and following troughs are normalized by time and resampled to form the dynamic strain influence line of the first train crossing the bridge.

[0094] Furthermore, in one possible implementation, the determining module 202 is also used to obtain the time corresponding to the peak of the dynamic strain wave when the first train crosses the bridge using the peak extraction method;

[0095] The moment corresponding to the peak of the dynamic strain wave when the first train crosses the bridge is taken as the base point. The monitoring data before and after the base point at fixed times are determined and used as the dynamic strain response of the first train crossing the bridge.

[0096] Furthermore, in one possible implementation, the acquisition module 201 is also used to select bridges with the same structural form and span arrangement on the light rail route, and set strain sensors at the same location and control section in the same span of the bridge.

[0097] Based on the strain sensor, dynamic strain monitoring data of each measuring point on the bridge is acquired. Further, in one possible implementation, an analysis module is included, which is used to select monitoring data from each measuring point on the bridge within a preset time period and analyze the selected monitoring data from each measuring point on the bridge within the preset time period, wherein the monitoring data includes: one or more train crossing events, with the first train crossing the bridge being considered the first train crossing event within the preset time period.

[0098] Reference Figure 3 , Figure 3The figure shown is a dynamic strain time history curve of different measuring points when the first train crosses the bridge, as provided by the present invention. Figure 3 As shown:

[0099] Dynamic strain monitoring data from three points over three days were analyzed. Data from the period between 5:00 AM and 6:00 AM each day was selected, encompassing one or more train crossing events, with the first train crossing being the first such event. Using peak extraction, the peak point of the dynamic strain during the first train crossing was extracted. Using this peak point as the center, 20 seconds were taken forward and backward. The dynamic strain monitoring data within this timeframe can be considered the dynamic strain response of the first train crossing. For the dynamic strain response within this timeframe, the peak extraction method was used to extract the two trough points before and after the first train crossing. The time taken for the first train to cross was calculated, and using the peak point as the center, 20 seconds were taken forward and backward. The dynamic strain response within this timeframe can be considered the dynamic strain influence line of the first train crossing.

[0100] In one embodiment, the dynamic strain influence line of the first train crossing the bridge is scaled up along the time axis using a resampling method to obtain a dynamic strain influence line of fixed length for the first train crossing the bridge. The similarity between each influence line and other influence lines is calculated using a cross-validation method, and the average value is taken as the dynamic strain influence line similarity of the measurement point on that day. This value is then compared with a threshold to determine abnormal states.

[0101] The following reference Figure 4 To describe an electronic device 400 according to this embodiment of the present invention. Figure 4 The electronic device 400 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0102] like Figure 4 As shown, the electronic device 400 is manifested in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including storage unit 420 and processing unit 410).

[0103] The storage unit stores program code that can be executed by the processing unit 410, causing the processing unit 410 to perform the steps described in the "Embodiment Methods" section of this specification according to various exemplary embodiments of the present invention.

[0104] Storage unit 420 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 421 and / or cache memory 422, and may further include a read-only memory (ROM) 423.

[0105] Storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0106] Bus 430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0107] Electronic device 400 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 400, and / or any device that enables electronic device 400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 450. Furthermore, electronic device 400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 460. As shown, network adapter 460 communicates with other modules of electronic device 400 via bus 430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0108] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0109] According to the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0110] refer to Figure 5 As shown, a program product 500 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0111] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0112] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0113] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0114] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0115] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0116] In summary, this application provides a method, apparatus, equipment, and storage medium for identifying abnormal states of light rail bridges. The method includes the following steps: for bridges with identical structural forms and span arrangements, monitoring data is acquired from dynamic strain measuring points located at the same control sections and spatial positions on the bridge; based on the monitoring data, the dynamic strain response when the first train crosses the bridge is determined, and the dynamic strain influence line of the first train crossing the bridge is obtained through the dynamic strain response; based on the dynamic strain influence line, it is determined whether there is an anomaly in the light rail bridge. This application can effectively identify abnormal states of light rail bridges when trains pass over them, solving the problem of abnormal bridge diagnosis in actual operation. Simultaneously, by judging the abnormal states of light rail bridges, it achieves structural safety and health monitoring of light rail bridges, ensuring stable line operation.

[0117] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0118] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

Claims

1. A method for identifying abnormal states of light rail bridges, characterized in that, include: Based on bridges with the same structural form and span arrangement, monitoring data of each measuring point on the bridge are obtained according to the dynamic strain measuring points set at the same control section and spatial location on the bridge. Based on the monitoring data, the dynamic strain response when the first train crosses the bridge is determined, and the dynamic strain influence line of the first train crossing the bridge is obtained through the dynamic strain response. Based on the dynamic strain influence line, determine whether there is any abnormality in the light rail bridge; Among them, the dynamic strain influence line of the first train crossing the bridge each day at each measuring point is obtained, and the dynamic strain influence line of the first train crossing the bridge at one of the measuring points is selected. The similarity of the selected dynamic strain influence line to the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day is calculated by cross-validation. Calculate the average similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge each day at other measuring points, and use the average value as the similarity of the selected dynamic strain influence line. When the similarity of the selected dynamic strain influence lines is less than a set threshold, it is determined that the selected bridge measuring points are not abnormal. If the similarity of the selected dynamic strain influence lines is greater than a set threshold, it is determined that the selected bridge measuring points are abnormal.

2. The method according to claim 1, characterized in that, The process of obtaining the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response includes: Based on the dynamic strain response when the first train crosses the bridge, the peak extraction method is used to obtain the time corresponding to the dynamic strain trough when the first train crosses the bridge. Based on the time corresponding to the dynamic strain trough when the first train crosses the bridge, determine the times corresponding to the preceding and following troughs; The dynamic strain monitoring data within the time corresponding to the preceding and following troughs are normalized by time and resampled to form the dynamic strain influence line of the first train crossing the bridge.

3. The method according to claim 1, characterized in that, Based on the monitoring data, the dynamic strain response of the first train crossing the bridge was determined, including: The peak extraction method was used to obtain the time corresponding to the peak of dynamic strain wave when the first train crossed the bridge; The moment corresponding to the peak of the dynamic strain wave when the first train crosses the bridge is taken as the base point. The monitoring data before and after the base point at fixed times are determined and used as the dynamic strain response of the first train crossing the bridge.

4. The method according to claim 1, characterized in that, Based on the dynamic strain measuring points set at the same control section and spatial location on the bridge, the monitoring data of each measuring point on the bridge are obtained, including: Strain sensors were installed at the control section and at the same location within the same span of the bridge. Based on the strain sensor, dynamic strain monitoring data of each measuring point on the bridge are obtained.

5. The method according to claim 1, characterized in that, Based on the monitoring data, before determining the dynamic strain response of the first train crossing the bridge, the following steps are taken: Monitoring data from various measuring points on the bridge are selected within a preset time period, and the monitoring data from these points are analyzed. The monitoring data includes one or more train crossing events, with the first train crossing the bridge being considered the first train crossing event within the preset time period.

6. A device for identifying abnormal conditions of light rail bridges, characterized in that, include: The acquisition module is used to acquire monitoring data of each measuring point on a bridge with the same structural form and span arrangement, based on the dynamic strain measuring points set at the same control section and spatial position on the bridge. The determination module is used to determine the dynamic strain response of the first train crossing the bridge based on the monitoring data, and to obtain the dynamic strain influence line of the first train crossing the bridge through the dynamic strain response; The judgment module is used to determine whether there is any abnormality in the light rail bridge based on the dynamic strain influence line. Obtain the dynamic strain influence line of the first train crossing the bridge each day at each measuring point, and select the dynamic strain influence line of the first train crossing the bridge at one of the measuring points. Use the cross-validation method to calculate the similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge at other measuring points each day. Calculate the average similarity between the selected dynamic strain influence line and the dynamic strain influence lines of the first train crossing the bridge each day at other measuring points, and use the average value as the similarity of the selected dynamic strain influence line. When the similarity of the selected dynamic strain influence lines is less than a set threshold, it is determined that the selected bridge measuring points are not abnormal. If the similarity of the selected dynamic strain influence lines is greater than a set threshold, it is determined that the selected bridge measuring points are abnormal.

7. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores computer program instructions that, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 5.

Images