Tunnel monitoring method and system based on distributed optical fiber sensors

Abstract

The invention relates to the technical field of tunnel monitoring, and discloses a tunnel monitoring method and method based on a distributed optical fiber sensor, and the method comprises the steps: collecting the real-time monitoring data of the optical fiber sensor, building a monitoring data group according to the real-time monitoring data, the monitoring data set comprises monitoring data of the optical fiber sensor at the current moment and monitoring data of the optical fiber sensor at the previous moment, and obtaining a monitoring data fluctuation value according to the monitoring data set; comparing and screening the monitoring data fluctuation value and the monitoring data fluctuation threshold value, performing anomaly calculation on the screened monitoring data to determine abnormal monitoring data, and constructing an abnormal monitoring data set based on the time sequence; calculating a correlation coefficient between every two abnormal monitoring data one by one, constructing a correlation coefficient set, and calculating a comprehensive correlation coefficient according to the correlation coefficient set; judging whether to perform monitoring and early warning on the to-be-monitored tunnel based on the comprehensive correlation coefficient; and performing early warning level division according to the monitoring quantity of the abnormal monitoring data. According to the invention, the accuracy and reliability of tunnel monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel monitoring. Specifically, it relates to a tunnel monitoring method and system based on distributed optical fiber sensors. Background Art

[0002] With the rapid development of the transportation industry, tunnels, as important transportation infrastructure, their safety and stability have attracted more and more attention. Traditional tunnel monitoring methods mainly rely on manual inspections and fixed-point sensor monitoring. These methods have problems such as limited monitoring range, poor real-time performance, and inaccurate data.

[0003] Therefore, it is necessary to design a tunnel monitoring method and system based on distributed optical fiber sensors to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a tunnel monitoring method and system based on distributed optical fiber sensors, aiming to solve the problems in the current technology that mainly rely on manual inspections and fixed-point sensor monitoring, such as limited monitoring range, poor real-time performance, and inaccurate data.

[0005] On the one hand, the present invention proposes a tunnel monitoring method based on distributed optical fiber sensors, including the following steps:

[0006] S100: Determine the tunnel to be monitored, divide the tunnel to be monitored into several monitoring areas, and deploy optical fiber sensors in each monitoring area;

[0007] S200: Extract the historical monitoring data of each optical fiber sensor at each historical moment, and construct a historical monitoring data set, which includes a historical normal monitoring data set and a historical abnormal monitoring data set;

[0008] S300: Collect the real-time monitoring data of the optical fiber sensors, establish a monitoring data group according to the real-time monitoring data, the monitoring data group includes the monitoring data of the optical fiber sensors at the current moment and the monitoring data of the optical fiber sensors at the previous moment, and obtain a monitoring data fluctuation value according to the monitoring data group;

[0009] S400: Compare and screen the monitoring data fluctuation value with a monitoring data fluctuation threshold, calculate the abnormal monitoring data for the screened monitoring data, and construct an abnormal monitoring data set based on the time series;

[0010] S500: Calculate the correlation coefficient between every two pieces of the abnormal monitoring data in the abnormal monitoring dataset one by one, and construct a correlation coefficient set. Calculate the comprehensive correlation coefficient according to the correlation coefficient set; Judge whether to conduct monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient;

[0011] S600: When it is determined to conduct monitoring and early warning on the tunnel to be monitored, divide the early warning levels according to the monitoring quantity of the abnormal monitoring data.

[0012] Further, the historical monitoring data includes historical temperature data, historical strain data, and historical vibration data.

[0013] Further, the monitoring data fluctuation threshold is obtained by the following formula:

[0014] Y = μ + α·σ;

[0015] where, Y represents the monitoring data fluctuation threshold; μ represents the average value of the historical monitoring data; σ represents the standard deviation of the historical monitoring data; α represents the fluctuation coefficient of the historical monitoring data.

[0016] Further, the monitoring data fluctuation value is obtained by the following formula:

[0017] D = |D t -D t-1 |;

[0018] where, D represents the monitoring data fluctuation value; D t represents the monitoring data at the current moment; D t-1 represents the monitoring data at the previous moment.

[0019] Further, when comparing and screening the monitoring data fluctuation value with the monitoring data fluctuation threshold, it also includes:

[0020] Compare the monitoring data fluctuation value with the monitoring data fluctuation threshold, and eliminate the small fluctuation data;

[0021] When the monitoring data fluctuation value is greater than the monitoring data fluctuation threshold, retain the fluctuation data;

[0022] When the monitoring data fluctuation value is less than or equal to the monitoring data fluctuation threshold, eliminate the fluctuation data.

[0023] Further, when determining the abnormal monitoring data by performing abnormal calculation on the screened monitoring data, it includes:

[0024] Calculate the abnormal value of each screened monitoring data based on the Z-Score method:

[0025]

[0026] Wherein, Z represents the outlier of the monitoring data; X represents the value of the filtered monitoring data; μ represents the average value of the historical monitoring data; σ represents the standard deviation of the historical monitoring data;

[0027] Compare the outlier with the outlier threshold, and determine whether the monitoring data is abnormal monitoring data according to the comparison result;

[0028] When the outlier is greater than the outlier threshold, it is determined that the monitoring data is abnormal monitoring data;

[0029] When the outlier is less than or equal to the outlier threshold, it is determined that the monitoring data is not abnormal monitoring data.

[0030] Further, when calculating the correlation coefficient between every two of the abnormal monitoring data in the abnormal monitoring data set one by one and constructing a correlation coefficient set, and calculating the comprehensive correlation coefficient according to the correlation coefficient set, it includes:

[0031] The correlation coefficient is obtained by the following formula:

[0032]

[0033] Wherein, r i,i+1 represents the correlation coefficient between the i-th abnormal monitoring data and the (i + 1)-th abnormal monitoring data; Xi represents the i-th abnormal monitoring data in the abnormal monitoring data set; Xi+1 represents the (i + 1)-th abnormal monitoring data in the abnormal monitoring data set; Xp represents the mean value of the abnormal monitoring data set;

[0034] The comprehensive correlation coefficient is obtained by weighted average calculation of the correlation coefficient set.

[0035] Further, when judging whether to carry out monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient, it includes:

[0036] Compare the comprehensive correlation coefficient with the comprehensive correlation coefficient threshold, and judge whether to carry out monitoring and early warning on the tunnel to be monitored according to the comparison result;

[0037] When the comprehensive correlation coefficient is less than or equal to the comprehensive correlation coefficient threshold, it is determined not to carry out monitoring and early warning on the tunnel to be monitored;

[0038] When the comprehensive correlation coefficient is greater than the comprehensive correlation coefficient threshold, it is determined to carry out monitoring and early warning on the tunnel to be monitored.

[0039] Further, when dividing the early warning level according to the monitoring quantity of the abnormal monitoring data, it includes:

[0040] Compare the monitored quantity with the first monitored quantity and the second monitored quantity, and divide the warning level according to the comparison result; wherein, the first monitored quantity is less than the second monitored quantity.

[0041] When the monitored quantity is less than or equal to the first monitored quantity, determine that the warning level is the first level.

[0042] When the monitored quantity is greater than the first monitored quantity and less than or equal to the second monitored quantity, determine that the warning level is the second level.

[0043] When the monitored quantity is greater than the second monitored quantity, determine that the warning level is the third level.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows: The tunnel monitoring method based on distributed optical fiber sensors provided by the present invention can realize real-time monitoring of the tunnel structure, timely detect abnormal conditions in the tunnel structure, and improve the safety and stability of the tunnel structure. By using distributed optical fiber sensors, a large number of sensors can be deployed inside the tunnel to achieve comprehensive monitoring of the tunnel structure. At the same time, by analyzing and processing historical monitoring data, accurate monitoring data fluctuation thresholds and abnormal value thresholds can be established to improve the accuracy and reliability of monitoring.

[0045] On the other hand, the present invention also proposes a tunnel monitoring system based on distributed optical fiber sensors, including:

[0046] A determination module, configured to determine a tunnel to be monitored, divide the tunnel to be monitored into several monitoring areas, and deploy optical fiber sensors in each of the monitoring areas;

[0047] A data set construction module, configured to extract historical monitoring data of each optical fiber sensor at each historical moment, and construct a historical monitoring data set, where the historical monitoring data set includes a historical normal monitoring data set and a historical abnormal monitoring data set;

[0048] A calculation module, configured to collect real-time monitoring data of the optical fiber sensors, establish a monitoring data group according to the real-time monitoring data, where the monitoring data group includes the monitoring data of the optical fiber sensors at the current moment and the monitoring data of the optical fiber sensors at the previous moment, and obtain a monitoring data fluctuation value according to the monitoring data group; compare and screen the monitoring data fluctuation value with a monitoring data fluctuation threshold, perform abnormal calculation on the screened monitoring data to determine abnormal monitoring data, and construct an abnormal monitoring data set based on time series;

[0049] The monitoring and early warning module is configured to calculate the correlation coefficient between every two pieces of the abnormal monitoring data in the abnormal monitoring dataset one by one, construct a correlation coefficient set, and calculate a comprehensive correlation coefficient according to the correlation coefficient set; determine whether to perform monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient; when it is determined to perform monitoring and early warning on the tunnel to be monitored, divide the early warning level according to the monitoring quantity of the abnormal monitoring data.

[0050] It can be understood that the above-mentioned tunnel monitoring method and system based on distributed optical fiber sensors have the same beneficial effects and will not be elaborated here. Description of the Drawings

[0051] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered as limiting the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0052] Figure 1 It is a flowchart of the tunnel monitoring method based on distributed optical fiber sensors provided by an embodiment of the present invention;

[0053] Figure 2 It is a structural block diagram of the tunnel monitoring system based on distributed optical fiber sensors provided by an embodiment of the present invention. Detailed Embodiments

[0054] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0055] Refer to Figure 1 As shown, in some embodiments of the present application, this embodiment provides a tunnel monitoring method based on distributed optical fiber sensors, including the following steps:

[0056] S100: Determine the tunnel to be monitored, divide the tunnel to be monitored into several monitoring areas, and deploy optical fiber sensors in each monitoring area;

[0057] S200: Extract the historical monitoring data of each of the fiber optic sensors at each historical moment, and construct a historical monitoring data set, where the historical monitoring data set includes a historical normal monitoring data set and a historical abnormal monitoring data set;

[0058] S300: Collect the real-time monitoring data of the fiber optic sensors, establish a monitoring data group according to the real-time monitoring data, where the monitoring data group includes the monitoring data of the fiber optic sensors at the current moment and the monitoring data of the fiber optic sensors at the previous moment, and obtain a monitoring data fluctuation value according to the monitoring data group;

[0059] S400: Compare and screen the monitoring data fluctuation value with a monitoring data fluctuation threshold, perform abnormal calculation on the screened monitoring data to determine abnormal monitoring data, and construct an abnormal monitoring data set based on the time series;

[0060] S500: Calculate the correlation coefficient between every two of the abnormal monitoring data in the abnormal monitoring data set one by one, and construct a correlation coefficient set, and calculate a comprehensive correlation coefficient according to the correlation coefficient set; Judge whether to carry out monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient;

[0061] S600: When it is determined to carry out monitoring and early warning on the tunnel to be monitored, divide the early warning level according to the monitoring quantity of the abnormal monitoring data.

[0062] It can be seen that the tunnel monitoring method based on distributed fiber optic sensors provided in this embodiment can realize the real-time monitoring of the tunnel structure, timely discover abnormal situations in the tunnel structure, and improve the safety and stability of the tunnel structure. By adopting distributed fiber optic sensors, a large number of sensors can be deployed inside the tunnel to achieve comprehensive monitoring of the tunnel structure. At the same time, through the analysis and processing of historical monitoring data, accurate monitoring data fluctuation thresholds and abnormal value thresholds can be established to improve the accuracy and reliability of monitoring.

[0063] Specifically, the historical monitoring data includes historical temperature data, historical strain data, and historical vibration data.

[0064] Specifically, the monitoring data fluctuation threshold is obtained by the following formula:

[0065] Y = μ + α·σ;

[0066] Among them, Y represents the monitoring data fluctuation threshold; μ represents the average value of the historical monitoring data; σ represents the standard deviation of the historical monitoring data; α represents the fluctuation coefficient of the historical monitoring data.

[0067] Specifically, the monitoring data fluctuation value is obtained by the following formula:

[0068] D = |Dt -D t-1 |;

[0069] wherein, D represents the monitoring data fluctuation value; D t represents the monitoring data at the current moment; D t-1 represents the monitoring data at the previous moment.

[0070] It can be understood that by calculating the monitoring data fluctuation value, the dynamic analysis of the real-time monitoring data of the fiber optic sensor can be realized, so as to timely capture the minute changes in the tunnel structure. Such changes may be caused by factors such as temperature, strain or vibration inside the tunnel. By real-time monitoring and analyzing these factors, a comprehensive assessment of the health status of the tunnel structure can be realized.

[0071] Specifically, when comparing and screening the monitoring data fluctuation value with the monitoring data fluctuation threshold, it further includes:

[0072] Comparing the monitoring data fluctuation value with the monitoring data fluctuation threshold to eliminate small fluctuation data;

[0073] When the monitoring data fluctuation value is greater than the monitoring data fluctuation threshold, retain the fluctuation data;

[0074] When the monitoring data fluctuation value is less than or equal to the monitoring data fluctuation threshold, eliminate the fluctuation data.

[0075] It can be understood that in this way, some minute fluctuations caused by accidental factors can be excluded, so as to more accurately identify the real abnormal data. This is crucial for subsequent abnormal calculation and the calculation of the comprehensive correlation coefficient, and can ensure the accuracy and reliability of the early warning system.

[0076] Specifically, when performing abnormal calculation on the screened monitoring data to determine abnormal monitoring data, it includes:

[0077] Calculating the abnormal value of each screened monitoring data based on the Z-Score method:

[0078]

[0079] wherein, Z represents the abnormal value of the monitoring data; X represents the value of the screened monitoring data; μ represents the average value of the historical monitoring data; σ represents the standard deviation of the historical monitoring data;

[0080] Comparing the abnormal value with the abnormal value threshold, and judging whether the monitoring data is abnormal monitoring data according to the comparison result;

[0081] When the abnormal value is greater than the abnormal value threshold, judge that the monitoring data is abnormal monitoring data;

[0082] When the outlier is less than or equal to the outlier threshold, it is determined that the monitored data is not abnormal monitored data.

[0083] It can be understood that by calculating the outliers of the filtered monitored data, it is possible to further determine which data truly reflect the anomalies of the tunnel structure. This method is based on statistical principles. By comparing the mean and standard deviation of the monitored data with historical data, it can quantitatively evaluate the degree of anomaly of the data. When the outlier exceeds the set threshold, it is considered that this data point represents an anomaly of the tunnel structure and further attention and early warning are required. This method not only improves the monitoring accuracy but also enhances the sensitivity and reliability of the early warning system.

[0084] Specifically, when calculating the correlation coefficient between every two of the abnormal monitored data in the abnormal monitored data set one by one and constructing a correlation coefficient set, and calculating the comprehensive correlation coefficient according to the correlation coefficient set, it includes:

[0085] The correlation coefficient is obtained by the following formula:

[0086]

[0087] where \(r_{i,i + 1}\) represents the correlation coefficient between the \(i\)-th abnormal monitored data and the \((i + 1)\)-th abnormal monitored data; \(X_i\) represents the \(i\)-th abnormal monitored data in the abnormal monitored data set; \(X_{i + 1}\) represents the \((i + 1)\)-th abnormal monitored data in the abnormal monitored data set; \(X_p\) represents the mean of the abnormal monitored data set;

[0088] The comprehensive correlation coefficient is obtained by performing a weighted average calculation on the correlation coefficient set.

[0089] It can be understood that by calculating the correlation coefficient between every two abnormal monitored data and constructing a correlation coefficient set, the correlation between abnormal data can be further analyzed. This correlation reflects the mutual influence between different positions or different monitoring points in the tunnel structure. When the data of certain monitoring points are abnormal, it may affect the data of other monitoring points. By calculating the comprehensive correlation coefficient, the degree and scope of this influence can be quantitatively evaluated. This is of great significance for understanding the overall health status of the tunnel structure and the response mechanism of the early warning system. When the comprehensive correlation coefficient exceeds a certain threshold, it is considered that there is a relatively serious anomaly in the tunnel structure and immediate measures need to be taken for intervention and repair. This tunnel monitoring method based on distributed fiber optic sensors not only improves the monitoring accuracy and reliability but also provides strong technical support for the safety maintenance of the tunnel structure. By real-time monitoring and analyzing data such as temperature, strain, and vibration in the tunnel structure, potential safety hazards can be discovered in a timely manner, providing strong guarantee for the safe operation of the tunnel.

[0090] Specifically, when determining whether to monitor and give an early warning to the tunnel to be monitored based on the comprehensive correlation coefficient, it includes:

[0091] Compare the comprehensive correlation coefficient with the comprehensive correlation coefficient threshold, and determine whether to monitor and give an early warning to the tunnel to be monitored according to the comparison result;

[0092] When the comprehensive correlation coefficient is less than or equal to the comprehensive correlation coefficient threshold, it is determined not to monitor and give an early warning to the tunnel to be monitored;

[0093] When the comprehensive correlation coefficient is greater than the comprehensive correlation coefficient threshold, it is determined to monitor and give an early warning to the tunnel to be monitored.

[0094] It can be understood that the comprehensive correlation coefficient threshold is preset according to historical monitoring data and the characteristics of the tunnel structure. This threshold represents a reasonable range of data correlation between monitoring points under normal circumstances for the tunnel structure. When the comprehensive correlation coefficient exceeds this threshold, it means that a significant change has occurred in the data correlation within the tunnel structure, which is usually caused by some abnormal condition inside the tunnel. Therefore, by comparing the comprehensive correlation coefficient with the comprehensive correlation coefficient threshold, it is possible to accurately determine whether there are potential safety hazards in the tunnel structure, and thus issue an early warning signal in a timely manner.

[0095] Specifically, when dividing the early warning level according to the monitoring quantity of the abnormal monitoring data, it includes:

[0096] Compare the monitoring quantity with the first monitoring quantity and the second monitoring quantity, and divide the early warning level according to the comparison result; wherein, the first monitoring quantity is less than the second monitoring quantity;

[0097] When the monitoring quantity is less than or equal to the first monitoring quantity, determine that the early warning level is the first level;

[0098] When the monitoring quantity is greater than the first monitoring quantity and less than or equal to the second monitoring quantity, determine that the early warning level is the second level;

[0099] When the monitoring quantity is greater than the second monitoring quantity, determine that the early warning level is the third level.

[0100] It can be understood that by grading the number of monitored abnormal monitoring data, a graded response to the abnormal conditions of the tunnel structure can be achieved. This graded response mechanism helps to reasonably allocate maintenance resources and ensure that appropriate measures can be taken promptly in case of emergencies. The first-level warning usually indicates that there are minor abnormal conditions in the tunnel structure, and immediate action may not be required, but close attention is still needed. The second-level warning indicates that the abnormal conditions in the tunnel structure are already relatively obvious, and inspections and evaluations need to be carried out as soon as possible to formulate appropriate repair plans. The third-level warning means that there are serious abnormal conditions in the tunnel structure, which may threaten the safe operation of the tunnel, and immediate measures need to be taken for intervention and repair. Through this graded warning mechanism, refined management of the health status of the tunnel structure can be achieved, improving the safety and stability of the tunnel.

[0101] Refer to Figure 2 As shown, in some embodiments of the present application, this embodiment provides a tunnel monitoring system based on a distributed fiber optic sensor, including:

[0102] A determination module, configured to determine a tunnel to be monitored, divide the tunnel to be monitored into several monitoring areas, and deploy fiber optic sensors in each of the monitoring areas;

[0103] A data set construction module, configured to extract the historical monitoring data of each fiber optic sensor at each historical moment and construct a historical monitoring data set, where the historical monitoring data set includes a historical normal monitoring data set and a historical abnormal monitoring data set;

[0104] A calculation module, configured to collect the real-time monitoring data of the fiber optic sensors, establish a monitoring data group according to the real-time monitoring data, where the monitoring data group includes the monitoring data of the fiber optic sensors at the current moment and the monitoring data of the fiber optic sensors at the previous moment, and obtain a monitoring data fluctuation value according to the monitoring data group; compare and screen the monitoring data fluctuation value with a monitoring data fluctuation threshold, perform abnormal calculation on the screened monitoring data to determine abnormal monitoring data, and construct an abnormal monitoring data set based on time series;

[0105] A monitoring and warning module, configured to calculate the correlation coefficient between every two abnormal monitoring data in the abnormal monitoring data set one by one and construct a correlation coefficient set, and calculate a comprehensive correlation coefficient according to the correlation coefficient set; determine whether to perform monitoring and warning on the tunnel to be monitored based on the comprehensive correlation coefficient; when it is determined to perform monitoring and warning on the tunnel to be monitored, divide the warning level according to the number of monitored abnormal monitoring data.

[0106] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0108] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still modifications or equivalent replacements can be made to the specific embodiments of the present invention, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A tunnel monitoring method based on distributed optical fiber sensors, characterized in that: include: Determine a tunnel to be monitored, divide the tunnel to be monitored into a plurality of monitoring areas, and deploy a fiber optic sensor in each of the monitoring areas; Extracting historical monitoring data of each of the optical fiber sensors at each historical moment, and constructing a historical monitoring data set, wherein the historical monitoring data set includes a historical normal monitoring data set and a historical abnormal monitoring data set; Collecting real-time monitoring data of the optical fiber sensor, establishing a monitoring data group according to the real-time monitoring data, wherein the monitoring data group includes the monitoring data of the optical fiber sensor at the current moment and the monitoring data of the optical fiber sensor at the previous moment, and obtaining a monitoring data fluctuation value according to the monitoring data group; The monitoring data fluctuation value is compared and screened with the monitoring data fluctuation threshold, and abnormal calculation is performed on the screened monitoring data to determine abnormal monitoring data, and an abnormal monitoring data set is constructed based on the time series; Calculating the correlation coefficient between every two abnormal monitoring data in the abnormal monitoring data set one by one, and constructing a correlation coefficient set, and calculating a comprehensive correlation coefficient according to the correlation coefficient set; Determining whether to perform monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient; When it is determined to perform monitoring and early warning on the tunnel to be monitored, early warning levels are divided according to the monitored quantity of the abnormal monitoring data.

2. The tunnel monitoring method based on distributed optical fiber sensors according to claim 1 is characterized in that: The historical monitoring data includes historical temperature data, historical strain data, and historical vibration data.

3. The tunnel monitoring method based on distributed optical fiber sensors according to claim 1 is characterized in that: The monitoring data fluctuation threshold is obtained by the following formula: Y = μ + α·σ; Among them, Y represents the fluctuation threshold of monitoring data; μ represents the average value of historical monitoring data; σ represents the standard deviation of historical monitoring data; α represents the fluctuation coefficient of historical monitoring data.

4. The tunnel monitoring method based on distributed optical fiber sensors according to claim 3 is characterized in that: The monitoring data fluctuation value is obtained by the following formula: D=|D t -D t-1 |; Where D represents the fluctuation value of monitoring data; D t Indicates the monitoring data at the current moment; D t-1 Indicates the monitoring data at the previous moment.

5. The tunnel monitoring method based on distributed optical fiber sensors according to claim 4 is characterized in that: When comparing and screening the monitoring data fluctuation value with the monitoring data fluctuation threshold, it also includes: Compare the monitoring data fluctuation value with the monitoring data fluctuation threshold value, and eliminate small fluctuation data; When the monitoring data fluctuation value is greater than the monitoring data fluctuation threshold, retaining the fluctuation data; When the monitoring data fluctuation value is less than or equal to the monitoring data fluctuation threshold, the fluctuation data is eliminated.

6. The tunnel monitoring method based on distributed optical fiber sensors according to claim 5 is characterized in that: When performing abnormal calculation on the screened monitoring data to determine abnormal monitoring data, it includes: Calculate the outlier value of each screened monitoring data based on the Z-Score method: Among them, Z represents the abnormal value of the monitoring data; X represents the value of the monitoring data after screening; μ represents the average value of the historical monitoring data; σ represents the standard deviation of the historical monitoring data; Compare the abnormal value with the abnormal value threshold, and determine whether the monitoring data is abnormal monitoring data according to the comparison result; When the abnormal value is greater than the abnormal value threshold, determining that the monitoring data is abnormal monitoring data; When the abnormal value is less than or equal to the abnormal value threshold, it is determined that the monitoring data is not abnormal monitoring data.

7. The tunnel monitoring method based on distributed optical fiber sensors according to claim 1 is characterized in that: Calculating the correlation coefficient between every two abnormal monitoring data in the abnormal monitoring data set one by one, and constructing a correlation coefficient set, and calculating the comprehensive correlation coefficient according to the correlation coefficient set, including: The correlation coefficient is obtained by the following formula: Among them, ri,i+1 represents the correlation coefficient between the i-th abnormal monitoring data and the i+1-th abnormal monitoring data; Xi represents the i-th abnormal monitoring data of the abnormal monitoring data set; Xi+1 represents the i+1-th abnormal monitoring data of the abnormal monitoring data set; Xp represents the mean of the abnormal monitoring data set; The comprehensive correlation coefficient is obtained by performing weighted average calculation on the correlation coefficient set.

8. The tunnel monitoring method based on distributed optical fiber sensors according to claim 1, characterized in that: When judging whether to perform monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient, the method includes: Comparing the comprehensive correlation coefficient with the comprehensive correlation coefficient threshold, and judging whether to perform monitoring and early warning on the tunnel to be monitored according to the comparison result; When the comprehensive correlation coefficient is less than or equal to the comprehensive correlation coefficient threshold, it is determined that no monitoring and early warning is performed on the tunnel to be monitored; When the comprehensive correlation coefficient is greater than the comprehensive correlation coefficient threshold, it is determined that monitoring and early warning are performed on the tunnel to be monitored.

9. The tunnel monitoring method based on distributed optical fiber sensors according to claim 1, characterized in that: When the warning level is divided according to the monitoring quantity of the abnormal monitoring data, it includes: Comparing the monitored quantity with the first monitored quantity and the second monitored quantity, and dividing the warning level according to the comparison result; wherein the first monitored quantity is smaller than the second monitored quantity; When the monitored quantity is less than or equal to the first monitored quantity, determining that the warning level is the first level; When the monitored quantity is greater than the first monitored quantity and less than or equal to the second monitored quantity, determining that the warning level is the second level; When the monitored quantity is greater than the second monitored quantity, the warning level is determined to be the third level.

10. A tunnel monitoring system based on distributed optical fiber sensors, applied to the tunnel monitoring method based on distributed optical fiber sensors as claimed in any one of claims 1 to 9, characterized in that: include: A determination module is configured to determine a tunnel to be monitored, divide the tunnel to be monitored into a plurality of monitoring areas, and deploy an optical fiber sensor in each of the monitoring areas; A data set construction module is configured to extract the historical monitoring data of each of the optical fiber sensors at each historical moment and construct a historical monitoring data set, wherein the historical monitoring data set includes a historical normal monitoring data set and a historical abnormal monitoring data set; A calculation module is configured to collect real-time monitoring data of the optical fiber sensor, establish a monitoring data group according to the real-time monitoring data, wherein the monitoring data group includes the monitoring data of the optical fiber sensor at a current moment and the monitoring data of the optical fiber sensor at a previous moment, and obtain a monitoring data fluctuation value according to the monitoring data group; The monitoring data fluctuation value is compared and screened with the monitoring data fluctuation threshold, and abnormal calculation is performed on the screened monitoring data to determine abnormal monitoring data, and an abnormal monitoring data set is constructed based on the time series; A monitoring and early warning module is configured to calculate the correlation coefficient between every two abnormal monitoring data in the abnormal monitoring data set one by one, and to construct a correlation coefficient set, and to calculate a comprehensive correlation coefficient according to the correlation coefficient set; Determining whether to perform monitoring and early warning on the tunnel to be monitored based on the comprehensive correlation coefficient; When it is determined to carry out monitoring and early warning on the tunnel to be monitored, early warning levels are divided according to the monitored quantity of the abnormal monitoring data.

Images