Multi-parameter monitoring method and system based on distributed optical fiber sensing

Abstract

The present application relates to the field of optical fiber sensing monitoring, and discloses a multi-parameter monitoring method and system based on distributed optical fiber sensing, which is used to solve the problem that sensor data is interfered and false alarm occurs when optical fiber sensing monitoring is carried out, comprising setting monitoring points, obtaining optical fiber sensing parameter data of each monitoring point, evaluating to obtain an optical fiber abnormality index, setting an initial abnormality threshold, performing a first abnormality judgment according to the optical fiber abnormality index and the initial abnormality threshold, if the judgment is abnormal, obtaining environmental noise data, evaluating to obtain a noise influence degree, setting a noise threshold, performing a noise influence judgment, if it is judged that the optical fiber is greatly influenced by environmental noise, adjusting the initial abnormality threshold to obtain an actual abnormality threshold, performing a second abnormality judgment according to the actual abnormality threshold, if the second abnormality judgment is that the current optical fiber sensing has an abnormality, performing an alarm, effectively improving the dynamic adaptability of multi-parameter monitoring to environmental changes and reducing the probability of false alarm.

Description

Technical Field

[0001] This invention relates to the field of fiber optic sensing and monitoring, and more specifically to a multi-parameter monitoring method and system based on distributed fiber optic sensing. Background Technology

[0002] The multi-parameter monitoring method based on distributed fiber optic sensing is a system that enables real-time monitoring and evaluation of various environmental parameters using fiber optic sensing technology. It continuously collects data on multiple physical quantities such as temperature, strain, pressure, and displacement within a target area using distributed fiber optic sensors. Combined with data analysis and control algorithms, it provides real-time monitoring and feedback on environmental changes to ensure the efficiency and accuracy of the monitoring process.

[0003] Existing multi-parameter monitoring methods based on distributed fiber optic sensing typically employ a single monitoring index or a simple threshold judgment mechanism. By collecting data on a specific physical quantity through a sensor, the system judges whether the data exceeds the normal range based on a set threshold. When the monitored data exceeds the threshold, an alarm is triggered.

[0004] For example, the invention patent with publication number CN118896650A discloses a multi-parameter power optical cable monitoring method and system based on distributed optical fiber sensing. This includes: ultrasonically processing the power optical cable to acquire damage data; performing distributed optical fiber signal sensing analysis on the power optical cable based on the damage data, simultaneously quantifying the aging degree of the power optical cable, to obtain power optical cable damage and aging data; plotting curves of the power optical cable based on the damage and aging data to obtain abnormal capacitance temperature curves; simulating thermal stress on the power optical cable based on the curves to obtain three-dimensional thermal stress deformation data; performing distributed optical fiber pressure sensing analysis on the power optical cable to obtain data-correlated three-dimensional thermal stress deformation data; and performing multi-parameter monitoring processing on the power optical cable to obtain multi-parameter monitoring results. This invention achieves multi-parameter monitoring by sensing and analyzing data from the cable's sheath and surrounding areas.

[0005] For example, a monitoring method for a distributed optical fiber sensing system, as announced in Patent No. CN112033446B, includes: S1, dividing the detection optical fiber into key monitoring areas and non-key monitoring areas based on the object under test; S2, measuring and recording the length of each interval distribution during the deployment of the monitoring optical fiber; S3, inputting the length of each interval distribution as an input parameter into the calculation system; S4, inputting the scanning frequency of each interval distribution into the calculation system, wherein the scanning frequency of the key monitoring area is much higher than that of the non-key monitoring area; S5, the calculation system calculates the time it takes for light to pass through each monitoring area and switches the scanning frequency according to the time; S6, the calculation system outputs the peak value change, thereby measuring the strain and temperature change of the object under test. This invention reasonably adjusts the data acquisition range and data scanning frequency of the distributed optical fiber sensing system, improving data calculation efficiency.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems: However, in practical applications, sensor data may be interfered with due to the complexity of the environment, resulting in drastic data fluctuations and triggering false alarms. Moreover, existing methods mostly rely on fixed alarm thresholds and lack the ability to dynamically adapt to environmental changes, which in turn creates the risk of false alarms and affects the accuracy of alarms. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-parameter monitoring method and system based on distributed optical fiber sensing to solve the problems existing in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: A multi-parameter monitoring method based on distributed optical fiber sensing includes the following steps: Step 1: Set up n monitoring points within the optical fiber, acquire optical fiber sensing parameter data for each monitoring point, including signal transmission data, environmental data, and equipment status data, and evaluate the optical fiber anomaly index based on the optical fiber sensing parameter data for each monitoring point; Step 2: Set an initial anomaly threshold, and perform the first anomaly judgment based on the optical fiber anomaly index and the initial anomaly threshold; Step 3: If the first anomaly judgment indicates that there is an anomaly in the current optical fiber sensing, acquire environmental noise data, evaluate the noise impact degree based on the environmental noise data, and set a noise threshold. The value is determined based on the noise impact level and the noise threshold to assess the impact of noise. Step 4: If the fiber optic sensor is significantly affected by ambient noise, the initial anomaly threshold is adjusted based on the noise impact level and the noise threshold to obtain the actual anomaly threshold. Step 5: A second anomaly assessment is performed based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly assessment indicates that the current fiber optic sensor is abnormal, an early warning is issued. The step of adjusting the initial anomaly threshold based on the noise impact level and the noise threshold is as follows: the ratio of the noise impact level to the noise threshold is calculated to obtain an adjustment factor; the actual anomaly threshold is obtained based on the adjustment factor and the initial anomaly threshold.

[0009] Preferably, the fiber optic anomaly index acquisition step is as follows: real-time acquisition of signal transmission data for each monitoring point, including signal delay, packet loss rate, and distortion rate; evaluation of the signal transmission anomaly coefficient based on the signal transmission data; real-time acquisition of fiber optic temperature data for each monitoring point; calculation of the temperature anomaly coefficient based on the fiber optic temperature data; real-time acquisition of fiber optic equipment status data, including stress data and optical attenuation value; evaluation of the equipment anomaly coefficient based on the equipment status data; normalization of the signal transmission anomaly coefficient, temperature anomaly coefficient, and equipment anomaly coefficient; evaluation of the fiber optic anomaly index based on the normalized signal transmission anomaly coefficient, temperature anomaly coefficient, and equipment anomaly coefficient; specifically, the acquisition steps are: multiplying the signal transmission anomaly coefficient by its weighting coefficient, adding the temperature anomaly coefficient multiplied by its weighting coefficient, and adding the equipment anomaly coefficient multiplied by its weighting coefficient to obtain the fiber optic anomaly index.

[0010] Preferably, the signal transmission anomaly coefficient acquisition step is as follows: acquire the signal delay, packet loss rate, and distortion rate of each monitoring point, and normalize the signal delay, packet loss rate, and distortion rate of each monitoring point; calculate the signal anomaly degree of each monitoring point based on the normalized signal delay, packet loss rate, and distortion rate, specifically by: subtracting the natural exponential function value, where the exponential part of the natural exponent is the negative value of the sum of the signal delay, packet loss rate, and distortion rate to obtain the signal anomaly degree of each monitoring point; performing clustering processing on the signal anomaly degree of each monitoring point; and obtaining the signal transmission anomaly coefficient based on the clustering processing result.

[0011] Preferably, the step of obtaining the temperature anomaly coefficient is as follows: A historical monitoring time period is set; for each monitoring point, the historical average temperature and real-time temperature of the monitoring point within the historical monitoring time period are obtained; the difference between the real-time temperature and the historical average temperature is calculated, and the absolute value is taken to obtain the real-time temperature deviation; the historical temperature of the monitoring point within the historical monitoring time period is obtained; the temperature fluctuation range is obtained based on the historical temperature and the historical average temperature of the monitoring point within the historical monitoring time period; the ratio of the real-time temperature deviation to the temperature fluctuation range is calculated to obtain the temperature anomaly value of the monitoring point; and the average of the temperature anomaly values ​​of each monitoring point is calculated to obtain the temperature anomaly coefficient.

[0012] Preferably, the step of obtaining the equipment anomaly coefficient is as follows: A stress sensor is set at each monitoring point to obtain real-time stress data for each monitoring point; the stress range of the optical fiber is obtained, including the maximum and minimum stresses; the wear value of the monitoring point is calculated based on the real-time stress data and the stress range; the wear degree is calculated by averaging the wear values ​​of each monitoring point; the initial optical attenuation value of the optical fiber is obtained; the real-time optical attenuation value of the optical fiber is obtained using optical time-domain reflectometry; the difference between the real-time optical attenuation value and the initial optical attenuation value is calculated to obtain the optical attenuation increment; the wear degree and the optical attenuation increment are normalized; and the equipment anomaly coefficient is calculated based on the normalized wear degree and the optical attenuation increment.

[0013] Preferably, the step of making the first anomaly judgment based on the fiber anomaly index and the initial anomaly threshold is as follows: compare the fiber anomaly index with the initial anomaly threshold; if the fiber anomaly index is less than the initial anomaly threshold, it is determined that there is no anomaly in the current fiber optic sensing; if the fiber anomaly index is greater than or equal to the initial anomaly threshold, it is determined that there is an anomaly in the current fiber optic sensing.

[0014] Preferably, the noise impact degree acquisition step is as follows: the noise intensity value of each monitoring point is acquired by a noise sensor within a historical monitoring period; for each monitoring point, the maximum and minimum noise intensity values ​​are acquired within the historical monitoring period, and the real-time noise intensity value is acquired; the noise impact value of each monitoring point is calculated based on the maximum and minimum noise intensity values ​​and the real-time noise intensity value; the average of the noise impact values ​​of all monitoring points is calculated to obtain the noise impact degree.

[0015] Preferably, the step of judging the impact of noise based on the degree of noise impact and the noise threshold is as follows: compare the degree of noise impact with the noise threshold; if the degree of noise impact is less than the noise threshold, it is determined that the fiber optic sensor is less affected by environmental noise, and there is an abnormality in the current fiber optic sensor, so an early warning is issued to prompt relevant personnel to repair the fiber optic in time; if the degree of noise impact is greater than or equal to the noise threshold, it is determined that the fiber optic sensor is greatly affected by environmental noise.

[0016] Preferably, the second anomaly judgment step based on the fiber anomaly index and the actual anomaly threshold is as follows: compare the fiber anomaly index with the actual anomaly threshold; if the fiber anomaly index is less than the actual anomaly threshold, it is determined that the current fiber optic sensing is not abnormal; if the fiber anomaly index is greater than or equal to the actual anomaly threshold, it is determined that the current fiber optic sensing is abnormal.

[0017] Preferably, a multi-parameter monitoring system based on distributed optical fiber sensing includes: a data acquisition module, used to set n monitoring points in the distributed optical fiber, acquire optical fiber sensing parameter data at each monitoring point, the optical fiber sensing parameter data including signal transmission data, environmental data, and equipment status data, evaluate an optical fiber anomaly index based on the optical fiber sensing parameter data at each monitoring point, and transmit the optical fiber anomaly index to a first anomaly judgment module and a second anomaly judgment module; a first anomaly judgment module, used to set an initial anomaly threshold, and perform a first anomaly judgment based on the optical fiber anomaly index and the initial anomaly threshold; and a noise judgment module, which, if the first anomaly judgment... If an anomaly is detected in the current fiber optic sensor, environmental noise data is acquired, and the degree of noise impact is assessed based on this data. The impact level is then compared to a noise threshold to determine if the fiber optic sensor is significantly affected by environmental noise. If the anomaly threshold adjustment module determines that the fiber optic sensor is significantly affected by environmental noise, it adjusts the initial anomaly threshold based on the noise impact level and the noise threshold to obtain the actual anomaly threshold. This actual anomaly threshold is then transmitted to the second anomaly detection module. The second anomaly detection module performs a second anomaly detection based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly detection indicates that the current fiber optic sensor is abnormal, an early warning is issued to remind relevant personnel to conduct timely maintenance.

[0018] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. Setting an initial anomaly threshold and performing an initial anomaly assessment based on the fiber optic anomaly index and the initial threshold helps quickly identify potential problems in the fiber optic system. By setting a baseline threshold, normal operation and minor anomalies can be effectively distinguished, thus avoiding premature or excessive responses. In the initial anomaly assessment phase, the system can identify obvious anomalies, reducing unnecessary interference and providing a reference for further refined assessments. This phased assessment method improves system response efficiency, reduces the probability of false alarms, and provides data support for subsequent adjustments and maintenance.

[0019] 2. If the first anomaly is determined to be an anomaly in the current fiber optic sensor, then environmental noise data is acquired, the degree of noise impact is assessed based on the environmental noise data, a noise threshold is set, and the impact of noise is judged based on the degree of noise impact and the noise threshold. Appropriate responses are made for situations with significant noise interference, resource utilization is optimized, unnecessary maintenance or adjustments are reduced, and the stable operation of the fiber optic sensor in complex environments is ensured.

[0020] 3. If the fiber optic sensor is significantly affected by ambient noise, the initial abnormal threshold is adjusted based on the degree of noise impact and the noise threshold to obtain the actual abnormal threshold. By dynamically adjusting the threshold according to the noise impact, the system can respond more flexibly to environmental changes, avoid false alarms or missed alarms caused by noise, and thus improve the accuracy and stability of fiber optic sensing.

[0021] 4. A second anomaly judgment is made based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly judgment indicates that there is an anomaly in the current fiber optic sensing, an early warning is issued. This judgment mechanism avoids overreacting to minor anomalies and ensures that a timely early warning can be issued when a serious problem occurs in the fiber optic sensing system, helping relevant personnel to take necessary measures to prevent the fault from escalating. Attached Figure Description

[0022] Figure 1 A flowchart of a multi-parameter monitoring method based on distributed optical fiber sensing provided in an embodiment of this application.

[0023] Figure 2 This is a schematic diagram illustrating the degree of signal anomaly at the monitoring point in an embodiment of this application.

[0024] Figure 3 This is a structural diagram of a multi-parameter monitoring system based on distributed optical fiber sensing provided in an embodiment of this application. Detailed Implementation

[0025] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The multi-parameter monitoring method and system based on distributed optical fiber sensing involved in the present invention are not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] This invention provides a multi-parameter monitoring method based on distributed optical fiber sensing, such as... Figure 1 As shown, it includes the following steps: Step 1: Set up n monitoring points in the optical fiber and acquire the optical fiber sensing parameter data of each monitoring point. The optical fiber sensing parameter data includes signal transmission data, environmental data and equipment status data. The optical fiber anomaly index is evaluated based on the optical fiber sensing parameter data of each monitoring point. By setting up multiple monitoring points in a distributed optical fiber, fiber optic sensing parameter data for different areas can be acquired from multiple angles. This multi-point acquisition method can comprehensively and accurately reflect anomalies during fiber optic transmission, avoiding misjudgments that might occur with a single monitoring point. Furthermore, a comprehensive assessment combining signal transmission, environmental data, and equipment status helps to fully understand the fiber optic condition under the influence of multiple factors, thereby improving the accuracy and reliability of monitoring.

[0027] In this embodiment, it should be specifically explained that the fiber optic anomaly index acquisition step is as follows: Real-time acquisition of signal transmission data from each monitoring point, including signal delay, packet loss rate, and distortion rate; and evaluation of signal transmission anomaly coefficient based on the signal transmission data. Real-time acquisition of fiber optic temperature data at each monitoring point; and calculation of temperature anomaly coefficient based on fiber optic temperature data. Real-time acquisition of fiber optic equipment status data, including stress data and optical attenuation values, and evaluation of equipment anomaly coefficients based on the equipment status data; The signal transmission anomaly coefficient, temperature anomaly coefficient, and equipment anomaly coefficient are normalized. Based on these normalized coefficients, the fiber optic anomaly index is calculated. The specific steps for obtaining this index are as follows: ; In the formula, Represented as the fiber optic anomaly index, This is represented by the signal transmission anomaly coefficient. Significant anomalies in signal transmission usually indicate some degree of fault or abnormality in the optical fiber, and the severity of this anomaly is directly related to the signal transmission quality. For example, a significant increase in signal delay may indicate damage to the fiber optic path or poor contact at connection points; large packet losses or distortions may indicate fiber optic aging or exposure to strong electromagnetic interference. Therefore, changes in the signal transmission anomaly coefficient can provide important clues about the optical fiber's condition. This is represented as a temperature anomaly coefficient. When the fiber optic temperature is too high, it usually indicates an abnormality in the fiber, leading to signal transmission problems and subsequently, an increase in temperature. This is represented by the equipment anomaly coefficient. Equipment failure or performance degradation directly affects the working status of the optical fiber. When equipment malfunctions, it may cause the optical fiber to bear a greater load during transmission or experience a deterioration in the working environment, thereby increasing the fiber's anomaly index. , , These are the weighting coefficients for the signal transmission anomaly coefficient, the temperature anomaly coefficient, and the equipment anomaly coefficient, respectively. , , , The specific value is determined by professionals based on the actual situation, for example, , , It can be 0.3, 0.3, or 0.4.

[0028] In this embodiment, it should be specifically explained that the step of obtaining the signal transmission anomaly coefficient is as follows: The signal delay, packet loss rate, and distortion rate of each monitoring point are obtained. These values ​​are then normalized. The normalized signal delay, packet loss rate, and distortion rate then take values ​​within the following ranges: The closer the value is to 1, the higher the degree of abnormality of the indicator; the closer it is to 0, the more normal the indicator is. Normalization can eliminate the influence of different dimensions and value ranges of each parameter, so that the values ​​of all parameters are uniform within the same range. like Figure 2 As shown, the signal anomaly level of each monitoring point is calculated based on the normalized signal delay, packet loss rate, and distortion rate. The specific steps for obtaining this information are as follows: ; In the formula, This indicates the degree of signal abnormality. This is represented as signal delay. This is expressed as packet loss rate. The distortion rate is expressed as a nonlinear function to calculate the degree of signal anomaly. This means that when the signal delay, packet loss rate, and distortion rate are small, the degree of anomaly does not change much. However, when the signal delay, packet loss rate, and distortion rate are close to 1, the degree of anomaly increases rapidly. This can effectively highlight serious anomalies while having a good suppressive effect on minor anomalies, thus avoiding being overly sensitive to minor fluctuations. Table 1. Degree of Signal Anomalies at Monitoring Points 1 0.05 0.02 0.01 0.08 2 0.1 0.05 0.03 0.16 3 0.15 0.07 0.05 0.24 4 0.2 0.1 0.07 0.31 5 0.25 0.12 0.1 0.37 As shown in Table 1, in one specific embodiment, differences in signal anomaly levels can be observed by analyzing signal delay, packet loss rate, and distortion rate at different monitoring points. For example, at monitoring point 1, the signal anomaly level is 0.08, indicating good signal quality; while at monitoring point 5, the signal anomaly level is 0.37, indicating poor signal quality due to higher signal delay, packet loss rate, and distortion rate. These changes in signal anomaly levels reflect the differences in signal quality at different monitoring points. By analyzing this data, the operational status of the fiber optic network can be effectively assessed, thereby providing a basis for fault early warning and maintenance decisions.

[0029] The signal anomaly level of each monitoring point is clustered, and the signal transmission anomaly coefficient is obtained based on the clustering results.

[0030] In this embodiment, it should be specifically explained that the clustering process for the signal anomaly degree of each monitoring point is as follows: Step 1.1: Use the degree of signal anomaly as a clustering feature, and use the degree of signal anomaly of all monitoring points as a dataset, with each degree of signal anomaly in the dataset being a data point; Step 1.2: Determine the optimal number of clusters K for the dataset using the silhouette coefficient method; The silhouette coefficient method is used to evaluate clustering effectiveness and determine the optimal number of clusters. It assesses clustering quality by measuring the density of each data point within its own cluster (intra-cluster distance) and its separation from the nearest other clusters (inter-cluster distance). The silhouette coefficient ranges from [value missing in original text]. Between 0 and 1, a value closer to 1 indicates denser clusters and more pronounced separation between clusters, resulting in better clustering. A value closer to 0 indicates a point is on a cluster boundary. A value less than 0 suggests a point may have been incorrectly assigned to a cluster. By calculating the average silhouette coefficient for different K values, the maximum value is selected as the optimal number of clusters.

[0031] Step 1.3: Randomly select K data points from the dataset as initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center. The specific method for obtaining this distance is as follows: ,in Let be the Euclidean distance from a data point to the cluster center, where Represented as data points, The initial cluster centers are represented as K. For each data point, the K initial cluster centers are traversed and assigned to the cluster corresponding to the nearest initial cluster center. Euclidean distance is a metric used to measure the straight-line distance between two points. In space, Euclidean distance represents the shortest path from one point to another, or the "straight-line distance" between two points. In data analysis, it is commonly used to calculate the similarity between data points; a smaller distance indicates that the two points are more similar, while a larger distance indicates that they are more different.

[0032] Step 1.4: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points within it is calculated to obtain the new cluster centers. Step 1.5: Repeat steps 1.3 and 1.4 until the cluster centers no longer change, thus obtaining the final clusters and final cluster centers.

[0033] In this embodiment, it should be specifically explained that the step of obtaining the signal transmission anomaly coefficient based on the clustering processing result is as follows: The weight of each final cluster is calculated by dividing the number of data points in each final cluster by the total number of data points in the dataset. The signal transmission anomaly coefficient is obtained by weighting and summing the weights of each final cluster with the final cluster center.

[0034] In this embodiment, it should be specifically explained that the step of obtaining the temperature anomaly coefficient is as follows: Set a historical monitoring period. For each monitoring point, obtain the historical average temperature and real-time temperature of the monitoring point within the historical monitoring period. Calculate the difference between the real-time temperature and the historical average temperature and take the absolute value to obtain the real-time temperature deviation. To obtain the historical temperature of monitoring points within a historical monitoring period, and to determine the temperature fluctuation range based on the historical temperature and historical average temperature of the monitoring points within the historical monitoring period, the specific steps are as follows: ; In the formula, This is expressed as the temperature fluctuation range. This represents the length of the historical monitoring period. This represents the historical temperature of the monitoring point at time t. Represented as historical average temperature; The temperature anomaly value of the monitoring point is obtained by calculating the ratio of the real-time temperature deviation to the temperature fluctuation range, and the temperature anomaly coefficient is obtained by averaging the temperature anomaly values ​​of each monitoring point.

[0035] In this embodiment, it should be specifically explained that the steps for obtaining the equipment anomaly coefficient are as follows: A stress sensor is installed at each monitoring point to obtain real-time stress data for each monitoring point. The stress range of the optical fiber is obtained, including the maximum and minimum stress. The wear value of the monitoring point is calculated based on the real-time stress data and the stress range. The specific steps are as follows: ; In the formula, This is represented as the wear value at the monitoring point. Represented as real-time stress data, Expressed as minimum stress, This is expressed as the maximum stress; The wear level is calculated by averaging the wear values ​​at each monitoring point. The initial optical attenuation value of the optical fiber is obtained, and the real-time optical attenuation value of the optical fiber is obtained through optical time domain reflection technology. The difference between the real-time optical attenuation value and the initial optical attenuation value is calculated to obtain the optical attenuation increment. Optical time-domain reflectometry (OTDR) is a technique used to detect the condition and faults of optical fibers. ORT obtains information about the fiber by sending pulsed laser light into it and analyzing the reflected signals returning from different locations within the fiber. The reflected signal in the fiber attenuates as fiber loss increases; ORT can calculate the degree of attenuation at each location by measuring the signal intensity and time delay. This technique provides a complete time-domain reflectometry profile of the fiber, helping to detect specific locations of damage and the degree of optical attenuation. It is a widely used technique for fiber optic monitoring and fault diagnosis.

[0036] The wear level and the increase in optical attenuation are normalized. The equipment anomaly coefficient is then calculated based on the normalized wear level and the increase in optical attenuation. The specific steps for obtaining this coefficient are as follows: ; In the formula, This is represented as the equipment anomaly coefficient. Indicated as the degree of wear and tear, It is expressed as the increment of optical attenuation.

[0037] Step 2: Set an initial anomaly threshold and make the first anomaly judgment based on the fiber optic anomaly index and the initial anomaly threshold; By setting an initial anomaly threshold, a benchmark is provided for anomaly detection. This initial assessment can identify potential anomalies in the fiber optic system, avoiding complex secondary assessments or adjustments. This stage of assessment helps to quickly screen potential fault areas, perform preliminary fault location, effectively improve monitoring response speed, and prevent unnecessary resource waste.

[0038] In this embodiment, it should be specifically explained that the first anomaly judgment step based on the fiber anomaly index and the initial anomaly threshold is as follows: The fiber optic anomaly index is compared with the initial anomaly threshold. If the fiber optic anomaly index is less than the initial anomaly threshold, it is determined that there is no anomaly in the current fiber optic sensing. If the fiber optic anomaly index is greater than or equal to the initial anomaly threshold, it is determined that there is an anomaly in the current fiber optic sensing.

[0039] Step 3: If the first anomaly judgment indicates that there is an anomaly in the current fiber optic sensor, then acquire the environmental noise data, assess the degree of noise impact based on the environmental noise data, set a noise threshold, and judge the impact of noise based on the degree of noise impact and the noise threshold. Ambient noise is a significant factor affecting the accuracy of fiber optic sensing, especially in high-noise environments where errors are exacerbated. By acquiring ambient noise data and assessing its impact on signal transmission, it is possible to distinguish noise-induced errors from genuine fault signals. This step helps eliminate noise interference, avoids false alarms caused by noise, and ensures the accuracy of fault diagnosis.

[0040] In this embodiment, it should be specifically explained that the step of obtaining the degree of noise impact is as follows: The noise intensity value of each monitoring point is obtained using noise sensors during the historical monitoring period; For each monitoring point, the maximum and minimum noise intensity values ​​are obtained within the historical monitoring period, along with the real-time noise intensity value. The noise impact value for each monitoring point is then calculated based on these values ​​and the real-time noise intensity value. The specific steps for obtaining this information are as follows: ; In the formula, Expressed as noise impact value, Represented as real-time noise intensity value, This is represented as the minimum noise intensity. This is represented as the maximum noise intensity. The noise impact value of all monitoring points is averaged to obtain the degree of noise impact.

[0041] In this embodiment, it should be specifically explained that the step of determining the impact of noise based on the degree of noise influence and the noise threshold is as follows: The noise impact level is compared with the noise threshold. If the noise impact level is less than the noise threshold, it is determined that the fiber optic sensor is less affected by environmental noise, and there is an anomaly in the current fiber optic sensor. An early warning is issued to prompt relevant personnel to repair the fiber optic cable in a timely manner. If the noise impact level is greater than or equal to the noise threshold, it is determined that the fiber optic sensor is more affected by environmental noise, and step 4 is performed.

[0042] Step 4: If the fiber optic sensor is significantly affected by ambient noise, adjust the initial anomaly threshold according to the degree of noise impact and the noise threshold to obtain the actual anomaly threshold. In situations where noise has a significant impact, the system can dynamically adapt to environmental changes by adjusting the initial anomaly threshold, thereby avoiding false alarms caused by environmental factors. This dynamic adjustment mechanism allows the system to more accurately assess the degree of fiber optic anomalies based on actual environmental conditions, improving the system's adaptability and intelligence. Furthermore, the adjusted actual anomaly threshold can better distinguish between noise interference and genuine faults, avoiding frequent false alarms or missed alarms.

[0043] In this embodiment, it should be specifically explained that the step of adjusting the initial anomaly threshold according to the degree of noise impact and the noise threshold is as follows: The adjustment factor is calculated by dividing the noise impact level by the noise threshold. The actual anomaly threshold is obtained by adjusting the factor and the initial anomaly threshold. The specific steps are as follows: ; In the formula, This represents the actual anomaly threshold. This is represented as the initial anomaly threshold. This is represented as an adjustment factor.

[0044] Step 5: Make a second anomaly judgment based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly judgment indicates that there is an anomaly in the current fiber optic sensor, issue an early warning to remind relevant personnel to carry out timely maintenance.

[0045] By conducting a second anomaly assessment, the system can reconfirm the abnormal state of the optical fiber after adjusting the threshold. This phased assessment mechanism allows the system to further improve accuracy and avoid erroneously triggering alarms in complex environments. After confirming the anomaly, the early warning system will promptly notify relevant personnel to conduct necessary inspections and repairs, preventing further deterioration of the fault and ensuring the stable operation of the optical fiber sensing system.

[0046] In this embodiment, it should be specifically explained that the second anomaly judgment step based on the fiber anomaly index and the actual anomaly threshold is as follows: The fiber optic anomaly index is compared with the actual anomaly threshold. If the fiber optic anomaly index is less than the actual anomaly threshold, it is determined that there is no anomaly in the current fiber optic sensing. If the fiber optic anomaly index is greater than or equal to the actual anomaly threshold, it is determined that there is an anomaly in the current fiber optic sensing.

[0047] In this embodiment, it should be specifically explained that, as Figure 3 As shown, a multi-parameter monitoring system based on distributed optical fiber sensing includes: The data acquisition module is used to set up n monitoring points in the distributed optical fiber, acquire the optical fiber sensing parameter data of each monitoring point, including signal transmission data, environmental data and equipment status data, evaluate the optical fiber anomaly index based on the optical fiber sensing parameter data of each monitoring point, and transmit the optical fiber anomaly index to the first anomaly judgment module and the second anomaly judgment module. The first anomaly detection module is used to set the initial anomaly threshold and perform the first anomaly detection based on the fiber optic anomaly index and the initial anomaly threshold. The noise detection module, if the first anomaly detection indicates an anomaly in the current fiber optic sensor, acquires environmental noise data, assesses the degree of noise impact based on the environmental noise data, and determines the impact of noise based on the degree of noise impact and the noise threshold. If the abnormal threshold adjustment module determines that the fiber optic sensor is significantly affected by environmental noise, it adjusts the initial abnormal threshold according to the degree of noise impact and the noise threshold to obtain the actual abnormal threshold, and then transmits the actual abnormal threshold to the second abnormal judgment module. The second anomaly detection module is used to make a second anomaly detection based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly detection indicates that there is an anomaly in the current fiber optic sensor, an early warning will be issued to remind relevant personnel to carry out timely maintenance.

[0048] In conclusion, 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, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0049] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that cannot be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A multi-parameter monitoring method based on distributed optical fiber sensing, characterized in that, Includes the following steps: Step 1: Set up n monitoring points in the optical fiber and acquire the optical fiber sensing parameter data of each monitoring point. The optical fiber sensing parameter data includes signal transmission data, environmental data and equipment status data. The optical fiber anomaly index is evaluated based on the optical fiber sensing parameter data of each monitoring point. The steps for obtaining the fiber optic anomaly index are as follows: Real-time acquisition of signal transmission data from each monitoring point, including signal delay, packet loss rate, and distortion rate; and evaluation of signal transmission anomaly coefficient based on the signal transmission data. Real-time acquisition of fiber optic temperature data at each monitoring point; and calculation of temperature anomaly coefficient based on fiber optic temperature data. The steps for obtaining the temperature anomaly coefficient are as follows: Set a historical monitoring period. For each monitoring point, obtain the historical average temperature and real-time temperature of the monitoring point within the historical monitoring period. Calculate the difference between the real-time temperature and the historical average temperature and take the absolute value to obtain the real-time temperature deviation. Obtain the historical temperature of the monitoring points within the historical monitoring period, and obtain the temperature fluctuation range based on the historical temperature of the monitoring points within the historical monitoring period and the historical average temperature. The temperature anomaly value of the monitoring point is obtained by calculating the ratio of the real-time temperature deviation to the temperature fluctuation range, and the temperature anomaly coefficient is obtained by averaging the temperature anomaly values ​​of each monitoring point. Real-time acquisition of fiber optic equipment status data, including stress data and optical attenuation values, and evaluation of equipment anomaly coefficients based on the equipment status data. The signal transmission anomaly coefficient, temperature anomaly coefficient, and equipment anomaly coefficient are normalized. Based on these normalized coefficients, the fiber optic anomaly index is calculated. The specific steps for obtaining this index are as follows: The fiber optic anomaly index is obtained by multiplying the signal transmission anomaly coefficient by its weighting coefficient, adding the temperature anomaly coefficient by its weighting coefficient, and adding the equipment anomaly coefficient by its weighting coefficient. The step for obtaining the signal transmission anomaly coefficient is as follows: The signal delay, packet loss rate, and distortion rate of each monitoring point are obtained, and the signal delay, packet loss rate, and distortion rate of each monitoring point are normalized. The degree of signal anomaly at each monitoring point is calculated based on the normalized signal delay, packet loss rate, and distortion rate. The specific steps are as follows: Subtract the value of the natural exponential function from the natural exponential function. The exponential part of the natural exponent is the negative value of the sum of the signal delay, packet loss rate and distortion rate to obtain the signal anomaly level of each monitoring point. The signal anomaly level of each monitoring point is clustered, and the signal transmission anomaly coefficient is obtained based on the clustering results. The steps for obtaining the equipment anomaly coefficient are as follows: A stress sensor is installed at each monitoring point to obtain real-time stress data for each monitoring point. The stress range of the optical fiber is obtained, including the maximum and minimum stress. The wear value of the monitoring point is calculated based on the real-time stress data and the stress range. The wear level is calculated by averaging the wear values ​​at each monitoring point. The initial optical attenuation value of the optical fiber is obtained, and the real-time optical attenuation value of the optical fiber is obtained through optical time domain reflection technology. The difference between the real-time optical attenuation value and the initial optical attenuation value is calculated to obtain the optical attenuation increment. The wear degree and the light attenuation increment are normalized, and the equipment anomaly coefficient is calculated based on the normalized wear degree and the light attenuation increment. Step 2: Set an initial anomaly threshold and make the first anomaly judgment based on the fiber optic anomaly index and the initial anomaly threshold; Step 3: If the first anomaly judgment indicates that there is an anomaly in the current fiber optic sensor, then acquire the environmental noise data, assess the degree of noise impact based on the environmental noise data, set a noise threshold, and judge the impact of noise based on the degree of noise impact and the noise threshold. The steps for obtaining the degree of noise impact are as follows: The noise intensity value of each monitoring point is obtained using noise sensors during the historical monitoring period; For each monitoring point, the maximum and minimum noise intensity values ​​are obtained within the historical monitoring period, and the real-time noise intensity value is obtained. The noise impact value of each monitoring point is calculated based on the maximum and minimum noise intensity values ​​and the real-time noise intensity value. The noise impact level is obtained by averaging the noise impact values ​​at all monitoring points. The steps for determining the impact of noise based on the degree of noise influence and the noise threshold are as follows: The noise impact level is compared with the noise threshold. If the noise impact level is less than the noise threshold, it is determined that the fiber optic sensor is less affected by environmental noise. The current fiber optic sensor is abnormal and an early warning is issued to prompt relevant personnel to repair the fiber optic cable in a timely manner. If the noise impact level is greater than or equal to the noise threshold, it is determined that the fiber optic sensor is greatly affected by environmental noise. Step 4: If the fiber optic sensor is significantly affected by ambient noise, adjust the initial anomaly threshold according to the degree of noise impact and the noise threshold to obtain the actual anomaly threshold. Step 5: Perform a second anomaly judgment based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly judgment indicates that there is an anomaly in the current fiber optic sensing, then issue an early warning. The step of adjusting the initial anomaly threshold based on the degree of noise impact and the noise threshold is as follows: The adjustment factor is calculated by dividing the noise impact level by the noise threshold. The actual anomaly threshold is obtained by adjusting the factor and the initial anomaly threshold.

2. The multi-parameter monitoring method based on distributed optical fiber sensing according to claim 1, characterized in that: The step of making the first anomaly judgment based on the fiber optic anomaly index and the initial anomaly threshold is as follows: The fiber optic anomaly index is compared with the initial anomaly threshold. If the fiber optic anomaly index is less than the initial anomaly threshold, it is determined that there is no anomaly in the current fiber optic sensing. If the fiber optic anomaly index is greater than or equal to the initial anomaly threshold, then the current fiber optic sensing is determined to be abnormal.

3. The multi-parameter monitoring method based on distributed optical fiber sensing according to claim 1, characterized in that: The second anomaly judgment step based on the fiber optic anomaly index and the actual anomaly threshold is as follows: The fiber optic anomaly index is compared with the actual anomaly threshold. If the fiber optic anomaly index is less than the actual anomaly threshold, it is determined that there is no anomaly in the current fiber optic sensor. If the fiber optic anomaly index is greater than or equal to the actual anomaly threshold, then the current fiber optic sensing is considered to be abnormal.

4. A multi-parameter monitoring system based on distributed optical fiber sensing, used to implement the multi-parameter monitoring method based on distributed optical fiber sensing as described in any one of claims 1-3, characterized in that: The system includes: The data acquisition module is used to set up n monitoring points in the distributed optical fiber, acquire the optical fiber sensing parameter data of each monitoring point, including signal transmission data, environmental data and equipment status data, evaluate the optical fiber anomaly index based on the optical fiber sensing parameter data of each monitoring point, and transmit the optical fiber anomaly index to the first anomaly judgment module and the second anomaly judgment module. The first anomaly detection module is used to set the initial anomaly threshold and perform the first anomaly detection based on the fiber optic anomaly index and the initial anomaly threshold. The noise detection module, if the first anomaly detection indicates an anomaly in the current fiber optic sensor, acquires environmental noise data, assesses the degree of noise impact based on the environmental noise data, and determines the impact of noise based on the degree of noise impact and the noise threshold. If the abnormal threshold adjustment module determines that the fiber optic sensor is greatly affected by environmental noise, it adjusts the initial abnormal threshold according to the degree of noise impact and the noise threshold to obtain the actual abnormal threshold, and then transmits the actual abnormal threshold to the second abnormal judgment module. The second anomaly detection module is used to make a second anomaly detection based on the fiber optic anomaly index and the actual anomaly threshold. If the second anomaly detection indicates that there is an anomaly in the current fiber optic sensor, an early warning will be issued to remind relevant personnel to carry out timely maintenance.

Images