A method, system, and equipment for early warning and identification of bridge structural risk status based on correlation network graphs.

Abstract

This invention relates to the field of bridge monitoring technology, specifically disclosing a method, system, and device for early warning and discrimination of bridge structural risk status based on correlation network diagrams. The invention first constructs a correlation network diagram of measuring points in the bridge structure under a baseline state using preprocessed benchmark monitoring data. When a risk measuring point triggers an over-limit alarm during real-time monitoring, a risk correlation sub-network diagram is extracted centered on that risk measuring point and compared with the benchmark correlation network diagram. By analyzing the linkage anomaly characteristics of node data and changes in the correlation degree between nodes in the sub-network diagram, a true early warning (abnormal structural state) is distinguished from a false alarm (equipment failure, environmental interference, etc.). This invention significantly improves the accuracy and reliability of early warning of bridge structural risk status through multi-measuring point correlation linkage analysis.

Description

Technical Field

[0001] This invention relates to the field of bridge monitoring technology, and specifically discloses a method, system and equipment for early warning and judgment of bridge structural risk status based on correlation network diagrams. Background Technology

[0002] Bridges are typically situated in complex and variable environments. Factors such as environmental noise, unstable voltage, strong electromagnetic interference, and equipment malfunctions can cause sudden changes in monitoring data. Most existing monitoring systems rely on whether data from a single measuring point exceeds a preset threshold to trigger an alarm. While this approach directly correlates abnormal data from a single measuring point with the safety status of the bridge structure and can quickly identify and trigger alarms for exceeding limits, it suffers from a high false alarm rate because the system struggles to distinguish whether the data anomaly is caused by changes in structural condition, equipment failure, or environmental factors. This increases the workload of maintenance personnel.

[0003] Therefore, there is an urgent need for a new early warning discrimination method, system, and equipment that can effectively reduce false alarms caused by non-structural factors and improve the accuracy and reliability of early warnings by analyzing the interrelationships between monitoring data from different measurement points. Summary of the Invention

[0004] The purpose of this invention is to overcome the problem of high false alarm rates in bridge early warning systems in the prior art, and to provide a method, system and device for early warning and discrimination of bridge structural risk status based on correlation network graphs.

[0005] To achieve the above-mentioned objectives, the present invention provides the following technical solution:

[0006] A method for early warning and discrimination of bridge structural risk status based on correlation network graphs includes the following steps:

[0007] S1: Acquire monitoring data of each measuring point of the bridge structure to be warned when it is in the baseline state, and output the baseline monitoring data after preprocessing; wherein, the preprocessing includes resampling and data length matching;

[0008] S2: Based on the benchmark monitoring data, calculate the correlation coefficient between different measuring points of the bridge structure to be warned, and construct an initial correlation coefficient matrix; then, according to the preset correlation degree discrimination standard, transform the initial correlation coefficient matrix into a benchmark correlation network diagram.

[0009] S3: Real-time monitoring of bridge structures to be warned; when there are risk measurement points with monitoring data exceeding the limit alarm, obtain the risk correlation sub-network diagram of each risk measurement point; and compare each risk correlation sub-network diagram with the benchmark correlation network diagram in turn.

[0010] S4: Based on the comparison results of S3, output the risk warning judgment result.

[0011] As a preferred embodiment of the present invention, the comparison of each risk-related sub-network diagram in S3 includes the following steps:

[0012] S31: Based on the benchmark correlation network diagram, other measurement points that have a moderate or strong correlation with the current risk measurement point are selected to form associated measurement points;

[0013] S32: Obtain real-time monitoring data of the risk measurement points and related measurement points, construct a risk correlation coefficient matrix, and generate a risk correlation sub-network diagram centered on the risk measurement points;

[0014] S33: Compare the risk correlation sub-network diagram of the risk measurement point with the corresponding benchmark correlation sub-network diagram in the benchmark correlation network diagram, and analyze the number of nodes where the correlation between nodes changes by leaps; wherein, the benchmark correlation sub-network diagram is a sub-network diagram composed of the current risk measurement point and its associated measurement points extracted from the benchmark correlation network diagram.

[0015] As a preferred embodiment of the present invention, the risk warning judgment result in S4 includes:

[0016] If only a single risk measurement point exceeds the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding baseline correlation sub-network diagram is greater than or equal to the set threshold, the judgment result is output: the current limit alarm is a false alarm, and the bridge structure status is normal.

[0017] If only a single risk measurement point exceeds the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding baseline correlation sub-network diagram is less than the set threshold, the judgment result is output: the current limit alarm is likely a real warning, and the structure state awaiting warning is slightly abnormal.

[0018] If a risk measurement point and a small number of related measurement points exceed the limit and trigger an alarm, and the number of nodes whose correlation degree changes by leaps and bounds in the risk correlation sub-network diagram is less than the set threshold compared with the corresponding baseline correlation sub-network diagram, the following judgment result is output: the current limit alarm is likely a real warning, and the structure status pending warning is moderately abnormal.

[0019] If the data of a certain risk measurement point and its associated measurement points all exceed the limit and trigger an alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding baseline correlation sub-network diagram is greater than or equal to the set threshold, the judgment result is output: the current limit alarm is likely a real warning, and the structure state awaiting warning is seriously abnormal.

[0020] As a preferred embodiment of the present invention, the preset correlation discrimination criterion in S2 is:

[0021] When 0 ≤ |r| < 0.3, the correlation is no.

[0022] When 0.3 ≤ |r| < 0.5, the correlation is weak.

[0023] When 0.5 ≤ |r| < 0.8, the correlation is moderate.

[0024] When 0.8 ≤ |r| ≤ 1.0, the correlation is strong.

[0025] Where r is the correlation coefficient between nodes.

[0026] As a preferred embodiment of the present invention, the correlation coefficient in step S2 is calculated using the Pearson correlation coefficient, Spearman rank correlation coefficient, or Kendall rank correlation coefficient.

[0027] As a preferred embodiment of the present invention, the acquisition of the benchmark monitoring data in S1 includes:

[0028] During the period when the bridge structure under warning has no obvious damage, no extreme loads, and stable operation, data is continuously collected for a set time period and output as benchmark monitoring data after preprocessing.

[0029] As a preferred embodiment of the present invention, the over-limit alarm in S3 is the real-time monitoring data exceeding the preset safety threshold range.

[0030] As a preferred embodiment of the present invention, the monitoring data includes any one or more of the following: ambient temperature, structural temperature, main beam deflection, longitudinal displacement of beam end, fixed pier rotation angle, cable force, relevant section strain, and cracks.

[0031] A bridge structural risk status early warning and discrimination system based on correlation network graphs, wherein the early warning and discrimination system is used to execute any of the bridge structural risk status early warning and discrimination methods based on correlation network graphs described above, and includes a data acquisition module, a preprocessing module, a network graph construction module, an early warning analysis module, and a storage and display module that are interconnected:

[0032] The data acquisition module includes several sensors deployed at the monitoring locations of the bridge structure to be warned, used to collect baseline status and real-time monitoring data;

[0033] The preprocessing module is used to resample and perform length matching processing on the collected monitoring data;

[0034] The network graph construction module is used to construct a baseline correlation network graph and a risk correlation sub-network graph;

[0035] The early warning analysis module is used to compare and analyze the benchmark correlation network diagram and the risk correlation sub-network diagram, and output the early warning judgment result.

[0036] The storage and display module is used to store monitoring data, network diagrams and early warning results, and to visualize the early warning information.

[0037] A bridge structure risk status early warning and discrimination device based on correlation network graph includes at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to execute any of the bridge structure risk status early warning and discrimination methods based on correlation network graph described above.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] This invention first obtains unified monitoring data through preprocessing. Then, based on the correlation matrix, it obtains a correlation network diagram of different categories of monitoring data under the bridge's baseline state. Next, based on the baseline state correlation network diagram, it quickly establishes a risk correlation sub-network diagram centered on the over-limit alarm monitoring points. By analyzing the linkage changes of data at different nodes in the sub-network diagram and the changes in the degree of correlation between different nodes, it accurately distinguishes between true early warnings and false alarms regarding structural risk status, significantly improving the accuracy of structural risk status early warnings. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating a bridge structure risk status early warning and discrimination method based on correlation network graphs as described in Embodiment 1 of the present invention.

[0041] Figure 2 This is an example of monitoring data after downsampling preprocessing in the bridge structure risk status early warning and discrimination method based on correlation network graph described in Embodiment 2 of the present invention;

[0042] Figure 3 This is an example of monitoring data after upsampling preprocessing in the bridge structure risk status early warning and discrimination method based on correlation network graph described in Embodiment 2 of the present invention;

[0043] Figure 4 This is a correlation coefficient matrix diagram of a bridge under a baseline state in a bridge structure risk state early warning and discrimination method based on correlation network graph described in Embodiment 2 of the present invention.

[0044] Figure 5 This is a correlation network diagram of a bridge under a baseline state in the bridge structural risk state early warning and discrimination method based on correlation network diagram described in Embodiment 2 of the present invention.

[0045] Figure 6 This refers to the sub-network diagram of the benchmark network diagram measuring point 7 and its associated measuring points in the bridge structure risk status early warning and discrimination method based on correlation network diagram described in Embodiment 2 of the present invention.

[0046] Figure 7 This is a time history diagram of the data of an over-limit alarm at a certain measuring point in the bridge structure risk status early warning and discrimination method based on correlation network graph described in Embodiment 2 of the present invention;

[0047] Figure 8 This is the risk correlation sub-network diagram under the condition of only a single measuring point exceeding the limit alarm and large changes in correlation rules in the bridge structure risk status early warning and discrimination method based on correlation network diagram described in Embodiment 2 of the present invention;

[0048] Figure 9 This is the risk correlation sub-network diagram under the condition of only a single measuring point exceeding the limit alarm and the correlation rule changing little in the bridge structure risk status early warning and discrimination method based on correlation network diagram described in Embodiment 2 of the present invention;

[0049] Figure 10 This is a risk correlation sub-network diagram under the condition of a small number of measuring points exceeding the limit and the correlation rules changing little in the bridge structure risk status early warning and discrimination method based on correlation network diagram described in Embodiment 2 of the present invention.

[0050] Figure 11 This is a risk correlation sub-network diagram under the condition of multiple measuring points exceeding the limit and the correlation rules changing greatly in the bridge structure risk status early warning and discrimination method based on correlation network diagram described in Embodiment 2 of the present invention.

[0051] Figure 12 This is a schematic diagram of a structural risk status early warning device based on correlation graphs as described in Embodiment 4 of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Example 1

[0054] like Figure 1 As shown, a method for early warning and discrimination of bridge structural risk status based on correlation network graphs includes the following steps:

[0055] S1: Obtain the monitoring data of each measuring point of the bridge structure to be warned when it is in the baseline state, and output the baseline monitoring data after preprocessing; wherein, the preprocessing includes resampling and data length matching.

[0056] S2: Based on the benchmark monitoring data, calculate the correlation coefficient between different measuring points of the bridge structure to be warned, and construct an initial correlation coefficient matrix; then, according to the preset correlation degree discrimination standard, transform the initial correlation coefficient matrix into a benchmark correlation network diagram.

[0057] S3: Real-time monitoring of bridge structures to be warned. When there are risk measurement points with monitoring data exceeding the limit alarm, obtain the risk correlation sub-network diagram of each risk measurement point; and compare each risk correlation sub-network diagram with the benchmark correlation network diagram in turn.

[0058] S4: Based on the comparison results of S3, output the risk warning judgment result.

[0059] Furthermore, the risk warning judgment results include:

[0060] If only a single risk measurement point exceeds the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding baseline correlation sub-network diagram is greater than or equal to the set threshold, the judgment result is output: the current limit alarm is a false alarm, and the bridge structure status is normal.

[0061] If only a single risk measurement point exceeds the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding baseline correlation sub-network diagram is less than the set threshold, the judgment result is output: the current limit alarm is likely a real warning, and the structure state awaiting warning is slightly abnormal.

[0062] If a risk measurement point and a small number of related measurement points exceed the limit and trigger an alarm, and the number of nodes whose correlation degree changes by leaps and bounds in the risk correlation sub-network diagram is less than the set threshold compared with the corresponding baseline correlation sub-network diagram, the following judgment result is output: the current limit alarm is likely a real warning, and the structure status pending warning is moderately abnormal.

[0063] If the data of a certain risk measurement point and its associated measurement points all exceed the limit and trigger an alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding baseline correlation sub-network diagram is greater than or equal to the set threshold, the judgment result is output: the current limit alarm is likely a real warning, and the structure state awaiting warning is seriously abnormal.

[0064] Example 2

[0065] This embodiment is a specific implementation of the bridge structure risk status early warning and discrimination method based on correlation network graph described in Embodiment 1, including the following steps:

[0066] S1: Acquire the monitoring data of each measuring point of the bridge structure to be warned when it is in the baseline state, and output the baseline monitoring data after preprocessing.

[0067] The monitoring data collected continuously during the period when the bridge structure to be warned is free from obvious damage, extreme loads (such as strong winds, earthquakes, etc.) and the operation status is stable is collected and used as the baseline monitoring data after preprocessing.

[0068] The monitoring data includes, but is not limited to: ambient temperature, structural temperature, main beam deflection, longitudinal displacement at beam ends, fixed pier rotation angle, cable force, strain of relevant sections, and cracks.

[0069] Furthermore, this embodiment uses monitoring data of ambient temperature, structural temperature, main beam deflection, longitudinal displacement at beam end, and cable force as examples for demonstration. The specific measuring point numbers and monitoring parameters are shown in Table 1.

[0070] Table 1. Schematic diagram of measuring point number and monitoring parameters in this embodiment.

[0071]

[0072] Because different types of sensors have different sampling frequencies, the monitoring data from each measuring point needs to be resampled and standardized in length. An example of the downsampling preprocessed data is shown below. Figure 2 See the example of data after upsampling preprocessing. Figure 3 .

[0073] Furthermore, the preprocessing includes resampling and data length matching.

[0074] S2: Based on the benchmark monitoring data, calculate the correlation coefficient between different measuring points of the bridge structure to be warned, and construct an initial correlation coefficient matrix; then, according to the preset correlation degree discrimination standard, transform the initial correlation coefficient matrix into a benchmark correlation network diagram.

[0075] This step calculates the Pearson correlation coefficient between different measuring points based on the baseline monitoring data, constructing an initial correlation coefficient matrix heatmap, as shown below. Figure 4 As shown. Furthermore, based on the correlation coefficient matrix, a data correlation network diagram of the bridge under the baseline state is obtained, as shown... Figure 5 As shown in the diagram. Nodes represent measurement points, connecting lines represent the correlation between measurement points, and the weights or attributes of the connecting lines represent the correlation strength.

[0076] Furthermore, the correlation coefficient can be calculated using Pearson correlation coefficient, Spearman rank correlation coefficient, or Kendall rank correlation coefficient; here, Pearson correlation coefficient is used.

[0077] In the correlation network diagram, each node represents a corresponding measurement point, and the thickness and color of the connecting lines between nodes are related to the degree of correlation. The degree of correlation between nodes is divided into four levels: no correlation, weak correlation, moderate correlation, and strong correlation, determined by the magnitude of the correlation coefficient. The preset criteria for judging the degree of correlation are as follows:

[0078] When 0 ≤ |r| < 0.3, the correlation is no.

[0079] When 0.3 ≤ |r| < 0.5, the correlation is weak.

[0080] When 0.5 ≤ |r| < 0.8, the correlation is moderate.

[0081] When 0.8 ≤ |r| ≤ 1.0, the correlation is strong.

[0082] Where r is the correlation coefficient between nodes.

[0083] S3: Real-time monitoring of bridge structures to be warned. When there are risk measurement points with monitoring data exceeding the limit alarm, obtain the risk correlation sub-network diagram of each risk measurement point; and compare each risk correlation sub-network diagram with the benchmark correlation network diagram in turn.

[0084] During bridge monitoring, when a risk monitoring point triggers an alarm indicating that the monitoring data exceeds the limit, all risk monitoring points are traversed to obtain a risk correlation sub-network diagram for each risk monitoring point. Each risk correlation sub-network diagram is then compared sequentially with a baseline correlation network diagram. The alarm indicating that the real-time monitoring data exceeds a preset safety threshold range is considered an alarm.

[0085] Specifically, the comparison of each risk-related sub-network diagram includes the following steps:

[0086] S31: Based on the aforementioned benchmark correlation network diagram, select other measurement points that have a moderate to strong correlation with the current risk measurement point to form associated measurement points, such as... Figure 5 As shown.

[0087] S32: Obtain real-time monitoring data of the risk measurement points and related measurement points, construct a risk correlation coefficient matrix, and generate a risk correlation sub-network diagram centered on the risk measurement points, such as... Figure 6 As shown.

[0088] S33: Compare the risk correlation sub-network diagram with the corresponding benchmark correlation sub-network diagram (i.e., the sub-network diagram composed of the current risk measurement point and its associated measurement points in the benchmark correlation network diagram) and analyze the number of nodes whose correlation between nodes changes by leaps.

[0089] S4: Based on the comparison results of S3, output the risk warning judgment result.

[0090] The risk warning and judgment results specifically include:

[0091] (1) If only a single risk measurement point data exceeds the limit alarm, and the number of nodes whose correlation degree changes by a level greater than or equal to the set threshold is greater than or equal to the risk correlation sub-network diagram compared with the corresponding benchmark correlation sub-network diagram, it is determined to be a false alarm and the bridge structure status is normal.

[0092] For example, when the sensor device corresponding to a certain measuring point malfunctions and causes abnormal data, such as Figure 7 As shown, the correlation between this measurement point data and other measurement point data often decreases, leading to significant variations in the correlation between many nodes. Figure 8 As shown, this is determined to be a false alarm caused by equipment failure or environmental interference, and the structural status is normal.

[0093] (2) If only a single risk measurement point data exceeds the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds compared with the corresponding benchmark correlation sub-network diagram is less than the set threshold, then the probability of a real warning is high, and the bridge structure condition to be warned is slightly abnormal.

[0094] For example, such as Figure 9 As shown, when measuring point 7 triggers an over-limit alarm, the data of its associated measuring points change accordingly. Since the changes are synchronous, the correlation between the measuring points generally does not exceed the level. In addition, since only a single risk measuring point triggers an over-limit alarm, based on the over-limit alarm measuring point and its association rules, it can be judged that the probability of a real warning is high and the structural state is slightly abnormal.

[0095] (3) If a certain risk measurement point and a small number of related measurement points exceed the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds in the risk correlation sub-network diagram is less than the set threshold compared with the corresponding benchmark correlation sub-network diagram, then according to the over-limit alarm measurement point and its correlation rules, it is determined that the probability of a real warning is high and the bridge structure status to be warned is moderately abnormal.

[0096] For example, such as Figure 10 As shown, measuring points 4, 5, and 7 all exceeded the limit and triggered alarms. Compared with the baseline correlation network diagram, the number of nodes with changes in correlation degree is less than the set threshold, which indicates a high probability of a real warning and a moderately abnormal structural state.

[0097] (4) If the data of a certain risk measuring point and its associated measuring points both exceed the limit alarm, and the number of nodes whose correlation degree changes by leaps and bounds is greater than the set threshold compared with the corresponding baseline correlation sub-network diagram, then based on the changes in the over-limit alarm measuring points and their associated rules, it is likely to be a real warning, and the bridge structure condition to be warned is seriously abnormal.

[0098] like Figure 11 As shown, the monitoring data of vertical displacement of the main beam of a certain bridge, ambient temperature at the bridge site, internal temperature of the main beam, cable force of the stay cables, longitudinal displacement of the main beam, and longitudinal displacement of the beam end all exceed the limits. The probability of this situation being caused by equipment failure or environmental interference is extremely low. Based on the changes in the over-limit alarm measuring points and their associated rules, it is determined that the probability of a real warning is high, and the structural condition is seriously abnormal.

[0099] In summary, by using the correlation network diagram method proposed in this invention to analyze the linkage changes and correlation changes of monitoring data between different measuring points, the proportion of false alarms and false alarms can be significantly reduced, and the accuracy and reliability of structural risk status early warning can be improved.

[0100] Example 3

[0101] A bridge structure risk status early warning and discrimination system based on correlation network graphs, wherein the early warning and discrimination system is used to execute the bridge structure risk status early warning and discrimination method based on correlation network graphs described in any of the above embodiments, and includes a data acquisition module, a preprocessing module, a network graph construction module, an early warning analysis module, and a storage and display module that are interconnected:

[0102] The data acquisition module includes several sensors deployed at the monitoring locations of the bridge structure to be warned, used to collect baseline status and real-time monitoring data.

[0103] The preprocessing module is used to resample and perform length matching processing on the collected monitoring data.

[0104] The network graph construction module is used to construct a baseline correlation network graph and a risk correlation sub-network graph.

[0105] The early warning analysis module is used to compare and analyze the benchmark correlation network diagram and the risk correlation sub-network diagram, and output the early warning judgment result.

[0106] The storage and display module is used to store monitoring data, network diagrams and early warning results, and to visualize the early warning information.

[0107] Example 4

[0108] like Figure 12As shown, a bridge structure risk status early warning and discrimination device based on a correlation network graph includes at least one processor, a memory communicatively connected to the at least one processor, and at least one input / output interface communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enables the at least one processor to perform the bridge structure risk status early warning and discrimination method based on a correlation network graph as described in the foregoing embodiments. The input / output interface may include a display, keyboard, mouse, and USB interface for inputting and outputting data.

[0109] Furthermore, the bridge structure risk status early warning and identification device based on correlation network graphs can be a desktop computer, mobile phone, tablet computer, wearable bridge structure risk status early warning and identification device based on correlation network graphs, etc., capable of deep information recognition.

[0110] Furthermore, the processor may include one or more processing cores. The processor connects various parts within the bridge structure risk status early warning and judgment device based on the correlation network graph using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory, and by calling data stored in memory. Optionally, the processor may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor and may be implemented separately through a communication chip.

[0111] The memory may include random access memory (RAM) or read-only memory (ROM). The memory can be used to store instructions, programs, code, code sets, or instruction sets, such as instructions or code sets used to implement the bridge structure risk status early warning and discrimination method based on correlation network graphs provided in this application. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc. The data storage area may also store data created during the use of the bridge structure risk status early warning and discrimination device based on correlation network graphs (such as a mapping table of modulation sequence and depth, image data, spectrogram data, etc.).

[0112] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0113] When the integrated units of the present invention are implemented as software functional units and sold or used as independent products, they can also be stored in a computer-readable storage medium. The computer-readable storage medium stores program code, which can be called by a processor to execute the methods described in the above method embodiments. Based on this understanding, the technical solution of the embodiments of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code that executes any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in an appropriate form.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A bridge structure risk state early warning discrimination method based on a correlation network diagram, characterized in that, The method comprises the following steps: S1: obtaining monitoring data of each measuring point of a bridge structure to be prewarned in a reference state, and outputting the preprocessed data as reference monitoring data; wherein the preprocessing comprises resampling and data length matching; S2: calculating correlation coefficients between different measuring points of the bridge structure to be prewarned based on the reference monitoring data, and constructing an initial correlation coefficient matrix; and then converting the initial correlation coefficient matrix into a reference correlation network graph according to a preset correlation degree discrimination standard; S3: real-time monitoring of the bridge structure to be prewarned, and obtaining a risk correlation sub-network graph of each risk measuring point when there is a risk measuring point with monitoring data exceeding the limit alarm; and comparing each risk correlation sub-network graph with the reference correlation network graph in turn; S4: outputting a risk prewarning discrimination result according to the comparison result of S3; The comparison of each risk correlation sub-network graph in S3 comprises the following steps: S31: screening other measuring points having moderate and strong correlation with the current risk measuring point based on the reference correlation network graph to form associated measuring points; S32: obtaining real-time monitoring data of the risk measuring point and the associated measuring points, constructing a risk correlation coefficient matrix, and generating a risk correlation sub-network graph with the risk measuring point as the center; S33: comparing the risk correlation sub-network graph of the risk measuring point with the corresponding reference correlation sub-network graph in the reference correlation network graph, and analyzing the number of nodes with correlation degree overstep change; wherein the reference correlation sub-network graph is a sub-network graph composed of the current risk measuring point and its associated measuring points in the reference correlation network graph; The risk prewarning discrimination result in S4 comprises: If only a single risk measuring point exceeds the limit alarm, and the number of nodes with correlation degree overstep change in the risk correlation sub-network graph compared with the corresponding reference correlation sub-network graph is greater than or equal to a set threshold, the output discrimination result is that the current limit alarm is a false alarm, and the state of the bridge structure to be prewarned is normal; If only a single risk measuring point exceeds the limit alarm, and the number of nodes with correlation degree overstep change in the risk correlation sub-network graph compared with the corresponding reference correlation sub-network graph is less than a set threshold, the output discrimination result is that the current limit alarm is a real prewarning with a high probability, and the state of the bridge structure to be prewarned is slightly abnormal; If data of a risk measuring point and a small number of associated measuring points thereof exceed the limit alarm, and the number of nodes with correlation degree overstep change in the risk correlation sub-network graph compared with the corresponding reference correlation sub-network graph is less than a set threshold, the output discrimination result is that the current limit alarm is a real prewarning with a high probability, and the state of the bridge structure to be prewarned is moderately abnormal; If data of a risk measuring point and its associated measuring points all exceed the limit alarm, and the number of nodes with correlation degree overstep change in the risk correlation sub-network graph compared with the corresponding reference correlation sub-network graph is greater than or equal to a set threshold, the output discrimination result is that the current limit alarm is a real prewarning with a high probability, and the state of the bridge structure to be prewarned is seriously abnormal.

2. The bridge structure risk state early warning discrimination method based on the correlation network diagram according to claim 1, characterized in that, The preset correlation degree discrimination standard in S2 is: When 0≤|r|<0.3, the correlation degree is not correlated; When 0.3≤|r|<0.5, the correlation degree is weakly correlated; When 0.5≤|r|<0.8, the correlation degree is moderate correlation; When 0.8≤|r|≤1.0, the correlation degree is strong correlation; Wherein, r is the correlation coefficient between nodes.

3. The bridge structure risk state early warning discrimination method based on the correlation network diagram according to claim 2, characterized in that, The calculation of the correlation coefficient in S2 adopts Pearson correlation coefficient, Spearman rank correlation coefficient or Kendall rank correlation coefficient.

4. The bridge structure risk state early warning discrimination method based on the correlation network diagram according to claim 1, characterized in that, The acquisition of the reference monitoring data in S1 includes: In the period when the bridge structure to be warned has no obvious damage, no extreme load and stable operation state, data of a set time length are continuously collected, and after the pretreatment, the output is the reference monitoring data.

5. The bridge structure risk state early warning discrimination method based on the correlation network diagram according to claim 1, characterized in that, The over-limit alarm in S3 is that the real-time monitoring data exceeds the preset safety threshold range.

6. The bridge structure risk state early warning discrimination method based on the correlation network diagram according to claim 1, characterized in that, The monitoring data includes any one or more of environmental temperature, structure temperature, main girder deflection, beam end longitudinal displacement, consolidation pier rotation angle, cable force, related cross-section strain and crack.

7. A bridge structure risk state early warning discrimination system based on a correlation network diagram, characterized in that, The early warning discrimination system is used to execute the bridge structure risk state early warning discrimination method based on correlation network graph in any one of claims 1 to 6, including data acquisition module, pretreatment module, network graph construction module, early warning analysis module and storage and display module which are connected with each other: The data acquisition module includes a plurality of sensors deployed at the monitoring position of the bridge structure to be warned, for collecting reference state and real-time monitoring data; The pretreatment module is used to resample and length match the collected monitoring data; The network graph construction module is used to construct reference correlation network graph and risk correlation sub-network graph; The early warning analysis module is used to compare and analyze the reference correlation network graph and the risk correlation sub-network graph, and output early warning judgment result; The storage and display module is used to store monitoring data, network graph and early warning result, and can visually display early warning information.

8. A bridge structure risk state early warning discrimination device based on a correlation network graph, characterized by, The system includes at least one processor, and a memory connected with the at least one processor in communication; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the bridge structure risk state early warning discrimination method based on correlation network graph in any one of claims 1 to 6.

Images