Method and system for judging major structural abnormal event of traffic road

Abstract

The invention discloses a method and a system for judging a major abnormal event of a traffic road structure, and the method comprises the following steps: 1, collecting the original health monitoring data of the traffic road structure through an optical fiber sensor; 3, continuously monitoring the data obtained after preprocessing according to a time domain, presetting a set theta by using known energy of an abnormal event as a parameter, and judging whether the abnormal event exists or not by comparing the data obtained after preprocessing with the set theta, and 4, transmitting a judgment result to a target in real time in a communication manner. An alarm is triggered when the occurrence of the abnormal event is judged; through the implementation of the method, the false alarm rate and the omission ratio of major abnormal events are reduced, more accurate data support is provided, and a more scientific and effective maintenance strategy can be formulated, so that unnecessary maintenance expenditure is reduced, and the method has certain use value and popularization value.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic road data analysis, and in particular to a method and system for determining major structural abnormal events on traffic roads. Background Art

[0002] As an important part of the transportation network in modern society, the structural safety of traffic roads is directly related to the safety of life and property of the public and the efficient operation of the transportation system. Major structural anomalies of traffic roads, such as road collapse and bridge fracture, are often the result of the long-term effects of multiple factors. If these abnormal events are not discovered and handled in time, they may lead to serious traffic accidents and economic losses.

[0003] Therefore, it is particularly important to develop effective methods for determining major abnormal events in traffic road structures. These methods need to be able to accurately identify and predict abnormal changes in traffic road structures and provide a scientific basis for maintenance and repair work. With the development of technologies such as fiber optic sensing technology, the Internet of Things (IoT), big data analysis, and artificial intelligence (AI), traffic road structure health monitoring has become more intelligent and accurate.

[0004] Traditional methods of monitoring traffic road structures, such as regular manual inspections or the use of simple sensors, have problems such as large detection blind spots, insufficient data continuity, and poor real-time performance.

[0005] In summary, a method and system for determining major structural abnormal events on traffic roads are needed to solve the problems existing in the prior art. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a method for determining major structural abnormal events on traffic roads, aiming to solve the problems of large detection blind spots, insufficient data continuity and poor real-time performance in regular manual inspections or the use of simple sensors.

[0007] To achieve the above object, the present invention provides the following technical solution: a method for determining a major structural abnormal event on a traffic road, comprising the following steps: Step 1: Collect raw health monitoring data of traffic road structure through optical fiber sensors; Step 2: Preprocess the original health monitoring data; Step 3: Continuously monitor the data obtained after preprocessing in the time domain, use the energy of known abnormal events as parameters, preset a set θ, and determine whether there is an abnormal event by comparing the data obtained after preprocessing with the set θ; Step 4: The judgment result is transmitted to the target in real time, and an alarm is triggered when an abnormal event is judged to occur. By preprocessing the data collected by the optical fiber sensor, noise can be removed to a large extent, data can be enhanced, and the signal-to-noise ratio of the data can be improved. By setting a reasonable set θ, normal fluctuations and real abnormal events can be accurately distinguished, reducing the false alarm rate and missed detection rate, providing more accurate data support, and helping to formulate more scientific and effective maintenance strategies, thereby reducing unnecessary maintenance expenses, and being able to detect and deal with potential safety issues such as road collapse and bridge fractures early, helping to prevent traffic accidents and protect the lives and property of the public.

[0008] Furthermore, in step 1, the optical fiber sensor is first laid on the traffic road structure, and the response of the optical pulse to the real-time vibration when propagating along the optical fiber sensor is used to form a corresponding vibration signal for sustainable monitoring, and this vibration signal reflecting the state of the traffic road structure is used as the original health monitoring data.

[0009] Furthermore, in step 2, preprocessing the original health monitoring data includes the following steps: Step A1: First, in order to make the useful signal components more obvious, the data segments in the original health monitoring data are signal enhanced; Step A2: Then, the enhanced signal is input into the FK filter, and the random noise is removed by the FK filter; Step A3: Finally, the data processed by the FK filter is subjected to a curvelet transform to improve the signal-to-noise ratio of the data and form the data obtained after preprocessing.

[0010] Furthermore, in step 3, the method for continuously monitoring the data obtained after preprocessing according to the time domain includes the following steps: Step B1: Calculate the average value STA of the absolute value of the signal in a short-time window centered at time t; Step B2: Calculate the average LTA of the absolute value of the signal in the long-term window centered at time t; Step B3: Calculate the ratio of STA to LTA; Step B4: When the ratio of STA to LTA does not belong to the preset set θ, it is determined that an abnormal event occurs.

[0011] Furthermore, in step B1, the formula for calculating the average value STA of the absolute value of the signal in a short-time window centered at time t is as follows: , Among them, t is the current target time point, X(τ) is the input signal, ω STA is the size of the short-term window; In step B2, the formula for calculating the average LTA of the absolute value of the signal in the long-term window centered at time t is as follows: , Among them, t is the current target time point, X(τ) is the input signal, ω LTA is the size of the long-term window; In step B3, the formula for calculating the ratio of STA to LTA is as follows: .

[0012] Furthermore, the method for selecting the set θ comprises the following steps: Step C1: observe the energy of the ratio curve of STA to LTA under normal conditions and the energy when an abnormal event occurs, and divide the abnormal events into two upper threshold types and lower threshold types. The average value of the energy of each abnormal event of the same type is used as the calculation parameter of the corresponding threshold for evaluation; Step C2: according to the result of step C1, set the corresponding threshold range; In step 3, if the data obtained after preprocessing If it does not belong to the set θ, there is an abnormal event, and the data obtained after preprocessing is The corresponding time point t in is the time point when the abnormal event is triggered.

[0013] Furthermore, in step C2, the preset upper threshold type corresponds to abnormal events such as road collapse and bridge fracture, and the preset lower threshold type corresponds to abnormal events such as fiber optic sensor fracture. The set between the upper threshold and the lower threshold is the set θ.

[0014] Furthermore, other sets θ' for calculating anomalies may be subsequently added to the set θ, and there is no intersection between the set θ' and the upper threshold and the lower threshold.

[0015] Furthermore, in order to make the useful signal components more obvious, the signal enhancement method of the data segments in the original health monitoring data includes: a data repeated superposition enhancement step and a basic data differentiation enhancement step. In the step of repeated data superposition and enhancement, when selecting data segments from the original health monitoring data, the data segments are selected in a manner with a repetition degree of at least 50%. After the data segments are selected, the data are superimposed by means of phase shift adjustment to enhance the characteristic data in the data segments. In the basic data differentiation enhancement step, the basic data is used as the comparison data, the difference value is calculated between the data after the data enhancement step and the comparison data, and the feature data in the difference value is enhanced.

[0016] On the other hand, a traffic road structural major abnormal event determination system is provided, comprising an optical fiber sensor, a DAS device, a server and a central monitoring platform, wherein the optical fiber sensor is connected to the DAS device, the DAS device is connected to the server, the DAS device is connected to the central monitoring platform via the server, the optical fiber sensor is laid on the traffic road structure and is used to detect vibration signals that can reflect the state of the traffic road structure and propagated along the optical fiber sensor, and the central monitoring platform is used to visually monitor the state of the traffic road structure in real time; The server is used to execute the following method: Step 1: Collect raw health monitoring data of traffic road structure through optical fiber sensors; Step 2: Preprocess the original health monitoring data; Step 3: Continuously monitor the data obtained after preprocessing in the time domain, use the energy of known abnormal events as parameters, preset a set θ, and determine whether there is an abnormal event by comparing the data obtained after preprocessing with the set θ; Step 4: The judgment result is transmitted to the target in real time, and an alarm is triggered when an abnormal event is detected.

[0017] Substantial effects of the present invention: 1. In the present invention, by preprocessing the data collected by the optical fiber sensor, noise can be removed to a large extent, data can be enhanced, and the signal-to-noise ratio of the data can be improved. By setting a reasonable set θ, normal fluctuations and real abnormal events can be accurately distinguished, thereby reducing the false alarm rate and missed detection rate, providing more accurate data support, and helping to formulate more scientific and effective maintenance strategies, thereby reducing unnecessary maintenance expenses, and being able to detect and deal with potential safety issues such as road collapse and bridge fractures early, helping to prevent traffic accidents and protect the lives and property of the public; 2. In the present invention, the laid optical fiber sensors cooperate with DAS equipment to achieve long-distance, high-spatial-resolution continuous monitoring of traffic road structures, which helps to discover potential safety hazards early, such as road collapse or bridge rupture, thereby reducing the risk of traffic accidents caused by these problems; 3. In the present invention, the traffic road structural major abnormal event determination system can transmit the collected data to the central monitoring platform in real time, so that the relevant departments can be informed of the occurrence of abnormal situations in the first time and take necessary measures to deal with them, providing support for rapid response to abnormal events; 4. In the present invention, by calculating the ratio of STA to LTA, the system can effectively distinguish between background noise and actual major abnormal events. The data is more comprehensive and accurate, which helps to optimize the maintenance strategy and invest resources only where they are really needed, thereby reducing the overall maintenance cost and the possibility of false alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the process of the present invention.

[0019] Figure 2 This is a diagram showing the denoising effect of preprocessing the original health monitoring data of the present invention.

[0020] Figure 3 It is a time series diagram of the traffic road under normal conditions of the present invention.

[0021] Figure 4 It is a time series diagram of abnormal traffic road events of the present invention.

[0022] Figure 5 It is a schematic diagram of traffic optical fiber sensor data comparison of the present invention.

[0023] Figure 6 It is a schematic diagram of the spatial distribution of traffic optical fiber sensor data at different times of the present invention.

[0024] Figure 7 It is a system principle block diagram of the present invention. DETAILED DESCRIPTION

[0025] In order to facilitate the understanding of the present invention, the present invention is described in more detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that when an element is described as "fixed to" another element, it can be directly on the other element, or there can be one or more centered elements therebetween. When an element is described as "connected to" another element, it can be directly connected to the other element, or there can be one or more centered elements therebetween. The terms "vertical", "horizontal", "left", "right" and similar expressions used in this specification are for illustrative purposes only.

[0026] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items. Embodiment 1:

[0027] like Figure 1 As shown, a method for determining a major structural abnormal event on a traffic road comprises the following steps: Step 1: Collect raw health monitoring data of traffic road structure through optical fiber sensors; Step 2: Preprocess the original health monitoring data; Step 3: Continuously monitor the preprocessed data in the time domain, and preset a set θ to determine whether there is an abnormal event; Step 4: The analysis results are transmitted to the target in real time, and an alarm is triggered when an abnormal event is detected. By preprocessing the data collected by the optical fiber sensor, noise can be removed to a large extent, data can be enhanced, and the signal-to-noise ratio of the data can be improved. By setting a reasonable set θ, normal fluctuations and real abnormal events can be accurately distinguished, reducing the false alarm rate and missed detection rate, providing more accurate data support, and helping to formulate more scientific and effective maintenance strategies, thereby reducing unnecessary maintenance expenses, and being able to detect and deal with potential safety issues such as road collapse and bridge fractures early, helping to prevent traffic accidents and protect the lives and property of the public.

[0028] Furthermore, in step 1, the optical fiber sensor is first laid on the traffic road structure, and the response of the optical pulse to the real-time vibration when propagating along the optical fiber sensor is used to form a corresponding vibration signal for sustainable monitoring, and the vibration signal reflecting the state of the traffic road structure is used as the original health monitoring data; the traffic road structure health monitoring data is collected through the optical fiber sensor, specifically, these data are the vibration signals captured by the optical fiber sensor laid on the traffic road structure, and in order to improve the quality of these original vibration signals and make them more suitable for subsequent abnormal event detection, a series of preprocessing operations need to be performed on them; Fiber optic sensor vibration signal: First, fiber optic sensors are laid at key locations of the traffic road structure. The fiber optic sensors can capture the vibration signals of the traffic road structure and reflect the current state of the traffic road structure through the captured vibration signals; Data collection: The vibration signals collected by the optical fiber sensor will be recorded by the distributed sensing equipment to form raw data; Data preprocessing: The raw data undergo a series of preprocessing steps, including superposition, Fk filter and curvelet transform. The main purpose of these steps is to improve the quality of the data, reduce the impact of noise, and make subsequent analysis more accurate.

[0029] Further, such as Figure 2 As shown, in step 2, preprocessing the original health monitoring data includes the following steps: Step A1: First, in order to make the useful signal components more obvious, the data segments in the original health monitoring data are signal enhanced; Step A2: Then, the enhanced signal is input into the FK filter, and the random noise is removed by the FK filter; Step A3: Finally, the data processed by the FK filter is subjected to a curvelet transform to improve the signal-to-noise ratio of the data and form the data obtained after preprocessing.

[0030] Furthermore, in step 3, the method for continuously monitoring the preprocessed data in the time domain includes the following steps: Step B1: Calculate the average value STA of the absolute value of the signal in a short-time window centered at time t; Step B2: Calculate the average LTA of the absolute value of the signal in the long-term window centered at time t; Step B3: Calculate the ratio of STA to LTA; Step B4: When the ratio of STA to LTA does not belong to the preset set θ, it is determined that an abnormal event occurs.

[0031] Furthermore, in step B1, the formula for calculating the average value STA of the absolute value of the signal in a short-time window centered at time t is as follows: , Among them, t is the current target time point, X(τ) is the input signal, ω STA is the size of the short-term window; In step B2, the formula for calculating the average LTA of the absolute value of the signal in the long-term window centered at time t is as follows: , Among them, t is the current target time point, X(τ) is the input signal, ω LTA is the size of the long-term window; In step B3, the formula for calculating the ratio of STA to LTA is as follows: .

[0032] Furthermore, in step 3, the method for selecting the set θ includes the following steps: Step C1: observe the energy of the ratio curve of STA to LTA under normal conditions and the energy when an abnormal event occurs, and divide the abnormal events into two upper threshold types and lower threshold types. The average value of the energy of each abnormal event of the same type is used as the calculation parameter of the corresponding threshold for evaluation; Step C2: according to the result of step C1, set the corresponding threshold range; In step 3, if the data obtained after preprocessing If it does not belong to the set θ, there is an abnormal event, and the data obtained after preprocessing is The corresponding time point t in is the time point when the abnormal event is triggered.

[0033] Furthermore, in step C2, the preset upper threshold type corresponds to abnormal events such as road collapse and bridge fracture, and the preset lower threshold type corresponds to abnormal events such as fiber optic sensor fracture. The set between the upper threshold and the lower threshold is the set θ.

[0034] Furthermore, other sets θ' for calculating anomalies may be subsequently added to the set θ, and there is no intersection between the set θ' and the upper threshold and the lower threshold.

[0035] Furthermore, corresponding upper and lower thresholds are set for different abnormal event types (such as road collapse, bridge breakage, and optical cable breakage). When the STA / LTA ratio does not belong to the preset set θ, it is considered that an abnormal event is detected.

[0036] Furthermore, abnormal event determination: through the STA / LTA algorithm and the range setting of the upper threshold and the lower threshold, it can be determined whether an abnormal event such as road collapse, bridge breakage or optical cable breakage has occurred.

[0037] like Figure 3 As shown, under normal circumstances, the intensity fluctuates within a certain range, such as Figure 4 As shown, when abnormal events such as road collapse and bridge rupture occur, the intensity will suddenly increase significantly. By setting the upper threshold range to three times the normal value of 2000 (6000), when the upper threshold range is exceeded, an early warning will be issued for such events, and such abnormal events will be handled in a timely manner.

[0038] like Figure 5 As shown in the figure, the traffic fiber sensor data after denoising, the straight lines in the figure represent the passing vehicles. Figure 5 The above data is normal. Figure 5 The data below disappears after a certain distance, indicating that the optical fiber sensor at that location is broken and no data is received.

[0039] like Figure 6 As shown in the figure, through the data at different times, it can be seen that the intensity is greatly reduced in the second half of the distance, which indicates that an abnormal event of optical fiber sensor breakage has occurred. By setting a lower lower threshold range (600) to detect abnormal events of optical fiber sensor breakage, the optical fiber sensor can be repaired after the event occurs without affecting subsequent applications.

[0040] Furthermore, in order to make the useful signal components more obvious, the signal enhancement method of the data segments in the original health monitoring data includes: a data repeated superposition enhancement step and a basic data differential enhancement step; In the step of repeated data superposition and enhancement, when selecting data segments from the original health monitoring data, the data segments are selected in a manner of at least 50% repetition. After the data segments are selected, the data are superimposed by means of phase shift adjustment to enhance the characteristic data in the data segments; In the basic data differentiation enhancement step, the basic data is used as the comparison data, the difference value is calculated between the data after the data enhancement step and the comparison data, and the feature data in the difference value is enhanced.

[0041] On the other hand, refer to Figure 7 , providing a traffic road structural major abnormal event determination system, including optical fiber sensors, DAS equipment, servers and central monitoring platform, the optical fiber sensors are connected to the DAS equipment, the DAS equipment is connected to the server, the DAS equipment is connected to the central monitoring platform through the server, the optical fiber sensors are laid on the traffic road structure and used to detect vibration signals that can reflect the state of the traffic road structure propagating along the optical fiber sensors, and the central monitoring platform is used to visualize and monitor the state of the traffic road structure in real time; The server is used to execute the following methods: Collect raw health monitoring data of traffic road structures through fiber optic sensors; Preprocess the raw health monitoring data; The data obtained after preprocessing is continuously monitored in the time domain, and the energy of the known abnormal event is used as a parameter. A set θ is preset, and the presence of an abnormal event is determined by comparing the data obtained after preprocessing with the set θ. The judgment results are transmitted to the target in real time, and an alarm is triggered when an abnormal event is detected.

[0042] Furthermore, the central monitoring module includes a visual warning unit, which is used to automatically issue an alarm prompt when an abnormal event is detected. Once an abnormal event is detected, the system will trigger the visual warning unit to issue an alarm to relevant personnel, reminding them to pay attention to the health of the traffic road structure.

[0043] Ultimately, these data and analysis results can be used to support decision-making in traffic road maintenance and management, helping relevant agencies take necessary measures to ensure the safety and smooth flow of traffic roads.

[0044] The entire workflow forms a closed loop, starting from data collection, through processing and analysis, to the determination and early warning of abnormal events, and finally to feedback to decision makers, repeating this cycle to continuously monitor the health of traffic road structures.

[0045] Substantive effects of this embodiment: 1. Preprocessing the data collected by the optical fiber sensor can largely remove noise, enhance data, and improve the signal-to-noise ratio of the data. By setting a reasonable set θ, normal fluctuations and real abnormal events can be accurately distinguished, reducing the false alarm rate and missed detection rate, providing more accurate data support, and helping to formulate more scientific and effective maintenance strategies, thereby reducing unnecessary maintenance expenses, and can early detect and deal with potential safety issues such as road collapse and bridge fracture, which helps prevent traffic accidents and protect the lives and property of the public; 2. The fiber optic sensors installed in conjunction with DAS equipment enable continuous monitoring of traffic road structures over long distances and with high spatial resolution, which helps to detect potential safety hazards early, such as road collapse or bridge rupture, thereby reducing the risk of traffic accidents caused by these problems; 3. The traffic road structural major abnormal event determination system can transmit the collected data to the central monitoring platform in real time, so that the relevant departments can be informed of the occurrence of abnormal situations at the first time and take necessary measures to deal with them, providing support for rapid response to abnormal events; 4. By calculating the ratio of STA to LTA, the system can effectively distinguish between background noise and actual major abnormal events. The more comprehensive and accurate data support helps to optimize maintenance strategies and invest resources only where they are really needed, thereby reducing overall maintenance costs and the possibility of false alarms. Embodiment 2:

[0046] This embodiment is basically the same as Embodiment 1, except that the following steps are adopted in this embodiment: In step 2, in order to make the useful signal components more obvious, the signal enhancement of the data segments in the original health monitoring data includes: a data repeated superposition enhancement step and a basic data differentiation enhancement step. In the step of data repetition superposition and enhancement, when selecting data segments in the original health monitoring data, the data segments are selected in a manner with a repetition rate of at least 50%. After the data segments are selected, the data are superimposed by phase shift adjustment to enhance the characteristic data in the data segments. In this embodiment, the length and repetition rate of the data segments can be freely selected according to the needs of customers. When the calculation examples are sufficient, the length of the data segments can be reduced, and the repetition rate of adjacent data segments can be increased. The lower the data length and the higher the repetition rate, the more obvious the characteristics of the data, the higher the accuracy when calculating subsequent data, and the faster the feedback response. Correspondingly, the repetition rate and data segments of adjacent data segments can also be reduced when the calculation is relatively insufficient. However, it is generally required that we keep the repetition rate of adjacent data segments above 50%. Through this scheme, adjacent data segments can be used as a verification method when abnormal data appears. We can obtain two complete and continuous data bands by splicing data segments, which can be used as redundant backups for each other and for subsequent measures such as mutual verification. It is also helpful to correct error alarm data, and even two sets of completely isolated independent monitoring algorithms can be used to perform independent real-time monitoring of current vibration data.

[0047] Further, the data repetition and superposition enhancement step can be directly applied. If the above data can be further analyzed in order to further improve the accuracy of the data, the basic data differentiation enhancement step can be performed, that is, the basic data determined by the current target is used as the comparison data. The basic data at this time can be the average value of normal data accumulated over a long period of time. Generally, the average value of the vibration data confirmed to be normal in a certain period of time after the equipment is newly laid is used as the basic data. When using this basic data as the comparison data, the data after the data repetition and superposition enhancement step is compared with the comparison data to obtain the difference value. At this time, since the basic data is removed, the characteristic data shown in the difference value is extremely obvious. However, when using this method, it is necessary to perform secondary calibration on each difference value. Because the basic data is removed, any small fluctuation will have a large feedback. Therefore, the previous calibration method cannot be applied, and the algorithm calibration needs to be further adjusted to adapt to the enhancement method. In this embodiment, only this feasible method is given, and it is recommended to use data repetition and superposition enhancement as a means of data enhancement. Embodiment 3:

[0048] This embodiment is basically the same as the embodiment 1, except that, since the set θ adopted in this embodiment is only a safety alarm when some upper and lower thresholds are determined, in actual applications, there are still other possible waveforms that are abnormal event waveforms. The waveforms of such abnormal events can also be feature extracted when the features are clear. Therefore, it is allowed to subsequently supplement and insert other sets θ' for calculating abnormalities in the set θ. As long as the user can determine that at this time, as long as it is ensured that there is no intersection between the set θ' and the upper threshold and the lower threshold, that is, the boundary value of the set θ' and the boundary value of the set θ are clear and distinguishable, then the subsequent Subsequent use can still be carried out on the basis of Example 1 and Example 2. For example, by comparing the data obtained after preprocessing with the set θ to determine whether there is an abnormal event, if it is directly determined that there is an abnormality, it is basically the same as the processing method of Example 1. If the comparison between the data obtained after preprocessing and the set θ determines that there is no abnormal event, it is also possible to compare the data obtained after preprocessing with the set θ'. If the data obtained after preprocessing falls within the set θ', it means that at this time, an abnormal event other than road collapse, bridge break or optical fiber sensor break has occurred, and the abnormal event is verified, determined and feasible by the user.

[0049] Furthermore, in this embodiment, in addition to inserting the set θ' for judging other unexpected events, there may also be other features of the data fragment or the original health monitoring data to extract and judge whether there is an abnormality. For example, after preprocessing the data fragment or the original health monitoring data and comparing it with the set θ, the envelope is selected as a case of feature comparison, and then the feature is used to judge whether there is an abnormal state. All of these are not limited in this embodiment, and are feasible solutions based on this embodiment. In this embodiment, only the situation when a new set θ' is inserted is further described.

[0050] It should be noted that the preferred embodiments of the present invention are given in the specification and drawings of the present invention. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. These embodiments are not intended to be additional limitations on the content of the present invention. The purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. In addition, the above-mentioned technical features continue to be combined with each other to form various embodiments not listed above, which are all considered to be within the scope of the present invention; further, for ordinary technicians in this field, they can be improved or transformed according to the above description, and all these improvements and transformations should belong to the scope of protection of the claims attached to the present invention.

Claims

1. A method for determining major structural abnormal events on a traffic road, characterized in that: The following steps are involved: Step 1: Collect raw health monitoring data of traffic road structure through optical fiber sensors; Step 2: Preprocess the original health monitoring data; Step 3: Continuously monitor the data obtained after preprocessing in the time domain, use the energy of known abnormal events as parameters, preset a set θ, and determine whether there is an abnormal event by comparing the data obtained after preprocessing with the set θ; Step 4: The judgment result is transmitted to the target in real time, and an alarm is triggered when an abnormal event is detected.

2. A method for determining a major structural abnormal event on a traffic road according to claim 1, characterized in that: In step 1, the optical fiber sensor is first laid on the traffic road structure, and the response of the optical pulse to the real-time vibration when propagating along the optical fiber sensor is used to form a corresponding vibration signal for sustainable monitoring, and this vibration signal reflecting the state of the traffic road structure is used as the original health monitoring data.

3. A method for determining a major structural abnormal event on a traffic road according to claim 2, characterized in that: In step 2, preprocessing the original health monitoring data includes the following steps: Step A1: First, in order to make the useful signal components more obvious, the data segments in the original health monitoring data are signal enhanced; Step A2: Then, the enhanced signal is input into the FK filter, and the random noise is removed by the FK filter; Step A3: Finally, the data processed by the FK filter is subjected to a curvelet transform to improve the signal-to-noise ratio of the data and form the data obtained after preprocessing.

4. A method for determining a major structural abnormal event on a traffic road according to claim 3, characterized in that: In step 3, the method for continuously monitoring the data obtained after preprocessing according to the time domain includes the following steps: Step B1: Calculate the average value STA of the absolute value of the signal in a short-time window centered at time t; Step B2: Calculate the average LTA of the absolute value of the signal in the long-term window centered at time t; Step B3: Calculate the ratio of STA to LTA; Step B4: When the ratio of STA to LTA does not belong to the preset set θ, it is determined that an abnormal event occurs.

5. A method for determining a major structural abnormal event on a traffic road according to claim 4, characterized in that: In step B1, the formula for calculating the average value STA of the absolute value of the signal in a short-time window centered at time t is as follows: ， Among them, t is the current target time point, X(τ) is the input signal, ω STA is the size of the short-term window; In step B2, the formula for calculating the average LTA of the absolute value of the signal in the long-term window centered at time t is as follows: ， Among them, t is the current target time point, X(τ) is the input signal, ω LTA is the size of the long-term window; In step B3, the formula for calculating the ratio of STA to LTA is as follows: 。 6. A method for determining a major structural abnormal event on a traffic road according to claim 5, characterized in that: The method for selecting the set θ comprises the following steps: Step C1: observe the energy of the ratio curve of STA to LTA under normal conditions and the energy when an abnormal event occurs, and divide the abnormal events into two upper threshold types and lower threshold types. The average value of the energy of each abnormal event of the same type is used as the calculation parameter of the corresponding threshold for evaluation; Step C2: according to the result of step C1, set the corresponding threshold range; In step 3, if the data obtained after preprocessing If it does not belong to the set θ, there is an abnormal event, and the data obtained after preprocessing is The corresponding time point t in is the time point when the abnormal event is triggered.

7. A method for determining a major structural abnormal event on a traffic road according to claim 6, characterized in that: In step C2, the preset upper threshold type corresponds to abnormal events such as road collapse and bridge fracture, and the preset lower threshold type corresponds to abnormal events such as fiber optic sensor fracture. The set between the upper threshold and the lower threshold is the set θ.

8. A method for determining a major structural abnormal event on a traffic road according to claim 7, characterized in that: The set θ is allowed to be subsequently supplemented with other sets θ' for calculating anomalies, and there is no intersection between the set θ' and the upper threshold and the lower threshold.

9. A method for determining a major structural abnormal event on a traffic road according to claim 8, characterized in that: In order to make the useful signal components more obvious, the signal enhancement method of the data segments in the original health monitoring data includes: data repeated superposition enhancement step and basic data differential enhancement step; In the step of repeated data superposition and enhancement, when selecting data segments from the original health monitoring data, the data segments are selected in a manner of at least 50% repetition. After the data segments are selected, the data are superimposed by means of phase shift adjustment to enhance the characteristic data in the data segments; In the basic data differentiation enhancement step, the basic data is used as the comparison data, the difference value is calculated between the data after the data enhancement step and the comparison data, and the feature data in the difference value is enhanced.

10. A system for determining major structural abnormal events on traffic roads, characterized in that: It includes an optical fiber sensor, a DAS device, a server and a central monitoring platform, wherein the optical fiber sensor is connected to the DAS device, the DAS device is connected to the server, the DAS device is connected to the central monitoring platform through the server, the optical fiber sensor is laid on the traffic road structure and is used to detect vibration signals that can reflect the state of the traffic road structure and propagate along the optical fiber sensor, and the central monitoring platform is used to visually monitor the state of the traffic road structure in real time; The server is used to execute the following method: Step 1: Collect raw health monitoring data of traffic road structure through optical fiber sensors; Step 2: Preprocess the original health monitoring data; Step 3: Continuously monitor the data obtained after preprocessing in the time domain, use the energy of known abnormal events as parameters, preset a set θ, and determine whether there is an abnormal event by comparing the data obtained after preprocessing with the set θ; Step 4: The judgment result is transmitted to the target in real time, and an alarm is triggered when an abnormal event is detected.

Images