External damage early warning identification method and system based on distributed optical fiber sound wave sensing

Abstract

The invention relates to the field of optical cable operation and maintenance monitoring, in particular to a distributed optical fiber sound wave sensing external damage early warning identification method and system, and the method comprises the steps: obtaining real-time DAS data of a to-be-detected optical cable section and corresponding real-time environment factors; acquiring real-time external damage factor characteristics according to the real-time DAS data and the real-time environmental factors; acquiring a first optical cable section from the to-be-measured optical cable sections; acquiring a second optical cable section closest to the first optical cable section; performing feature enhancement on the real-time external breaking factor feature of the first optical cable section according to the real-time external breaking factor feature of the second optical cable section; and processing the enhanced real-time external damage factor characteristics through an external damage early-warning identification model to obtain an external damage early-warning category of the first optical cable section. Compared with the prior art, the method has the advantages that the characteristics of the real-time DAS data and the characteristics of the real-time environmental factors are integrated to obtain the characteristics of the real-time external damage factors, so that the influence of the real-time DAS data and the environment can be integrated, and the identification of the external damage early warning category of the to-be-detected optical cable section can be accurately realized.

Description

Technical Field

[0001] This invention relates to the field of optical cable maintenance and monitoring, and more specifically, to a method and system for early warning and identification of external damage using distributed optical fiber acoustic wave sensing. Background Technology

[0002] With the popularization of fiber optic technology, fiber optic cables are becoming increasingly prevalent in people's daily lives, and the number of fiber optic cables laid is also constantly increasing. However, the increase in the number of fiber optic cables laid also makes them more susceptible to damage from external factors such as construction or urban redevelopment, which in turn affects the user experience.

[0003] Therefore, it is necessary to identify external damage warnings for optical cables and their impact, and to determine whether an external damage warning actually constitutes an external damage event. Current identification methods primarily involve collecting relevant data about the optical cable using distributed acoustic sensing (DAS) devices, and then using pattern recognition or neural network models based on this data. However, existing neural network models used for external damage warning identification cannot effectively perceive the environment in which the warning is issued, leading to discrepancies between the identified warning and the actual external damage warning. Summary of the Invention

[0004] This invention provides a method and system for identifying external damage early warnings using distributed fiber optic acoustic sensing, which effectively utilizes the environmental impact of external damage early warnings to identify the types of external damage early warnings.

[0005] According to a first aspect of this application, a method for early warning and identification of external damage using distributed fiber optic acoustic sensing is provided, the method comprising: The real-time DAS data of each segment of the optical cable under test and the real-time environmental factors of each segment are obtained; the segments are obtained by dividing the optical cable under test according to a preset length. The real-time external damage characteristics of the optical cable segment under test are obtained based on the real-time DAS data and the real-time environmental factors. The optical cable segment under test that experiences an external damage warning is designated as the first optical cable segment. At both ends of the first optical cable segment, at least one optical cable segment to be tested that is closest to the first optical cable segment is obtained as the second optical cable segment; The real-time external damage factor characteristics of the first optical cable segment are enhanced based on the real-time external damage factor characteristics of the second optical cable segment. The external damage warning identification model is used to process the real-time external damage factor characteristics of the first optical cable segment after enhancement, and the external damage warning category of the first optical cable segment is obtained.

[0006] Optionally, the number of second optical cable segments at both ends of the first optical cable segment is the same; The feature enhancement of the real-time external damage factor characteristics of the first optical cable segment based on the real-time external damage factor characteristics of the second optical cable segment is expressed as follows: In the formula, i is the preset number of the optical cable segment to be tested corresponding to the first optical cable segment in the optical cable to be tested. The real-time external damage characteristics of the first optical cable segment after reinforcement. Indicates the first optical cable segment Feature transfer enhancement formula for layers, The number of second optical cable segments at either end of the first optical cable segment. , This refers to the real-time external damage characteristics of the first optical cable segment before reinforcement. It is the ReLU activation function. For the first Learnable parameters of the layer feature transfer enhancement formula. For splicing symbols, This represents a preset set of numbers for the second optical cable segment that is directly adjacent to the first optical cable segment. This represents the number of preset numbers in the preset number set.

[0007] Optionally, obtaining the real-time external damage factor characteristics of the optical cable segment under test based on the real-time DAS data and the real-time environmental factors includes: The real-time environmental factors are encoded to obtain the real-time environmental code; Extract the real-time environment features from the real-time environment code, and extract the real-time DAS features from the real-time DAS data; The real-time environmental features and the real-time DAS features are fused based on preset weights to obtain the real-time external damage factor features of the optical cable segment under test.

[0008] Optionally, the encoding process for the real-time environmental factors to obtain real-time environmental codes includes: The real-time environmental factors are encoded using a preset encoding logic to obtain the initial environmental code; The initial environment code is converted into standardized data between 0 and 1 using a preset standardization method, and used as the real-time environment code for the real-time environmental factors.

[0009] Optionally, the step of processing the enhanced real-time external damage factor characteristics of the first optical cable segment using the external damage early warning identification model to obtain the external damage early warning category of the first optical cable segment includes: Calculate the distance between each external damage warning feature in the external damage warning feature library of the external damage warning identification model and the real-time external damage factor features; Based on the nearest neighbor hyperparameter of the external damage early warning identification model, select several candidate external damage early warning features that are closest to the real-time external damage factor features from the external damage early warning features; Based on the preset external damage warning category label of the candidate external damage warning features, the external damage warning category of the optical cable under test is obtained.

[0010] Optionally, the construction of the external damage early warning feature database includes: Collect historical DAS data for known external damage warning categories, and the historical environmental factors corresponding to the historical DAS data; Based on the historical DAS data and the historical environmental factors, the characteristics of historical external damage factors are obtained; Based on the known external damage warning categories, add external damage warning category labels to the historical external damage factor characteristics to obtain the external damage factor characteristics; The external damage early warning feature library is constructed based on the external damage factor characteristics.

[0011] Optionally, the acquisition of the nearest neighbor hyperparameters of the external damage early warning identification model includes: Several candidate nearest neighbor hyperparameters are preset; External damage early warning features are selected from the external damage early warning feature library as external damage verification event features; For each of the candidate nearest neighbor hyperparameters: Calculate the distance between the external damage verification event feature and each external damage warning feature in the external damage warning feature library, and based on the candidate nearest neighbor hyperparameter, select several candidate external damage warning features that are closest to the external damage verification event feature from the external damage warning features. Based on the external damage warning category labels of the several candidate external damage warning features, obtain the external damage warning category to be verified for the external damage verification event feature. Based on the external damage warning category to be verified and the external damage verification event feature external damage warning category label, the nearest neighbor hyperparameter is selected from the candidate nearest neighbor hyperparameters.

[0012] According to a second aspect of this application, a distributed fiber optic acoustic sensing-based external damage early warning and identification system is provided, the system comprising: The data acquisition module is used to acquire real-time DAS data of each optical cable segment under test, as well as real-time environmental factors of each optical cable segment under test; the optical cable segments under test are obtained by dividing the optical cable under test according to a preset length. The feature extraction module is used to obtain the real-time external damage factor features of the optical cable segment under test based on the real-time DAS data and the real-time environmental factors. The optical cable segment determination module is used to identify the optical cable segment under test that has experienced an external damage warning as the first optical cable segment, and to identify at least one optical cable segment under test that is closest to the first optical cable segment at each end of the first optical cable segment as the second optical cable segment. The feature enhancement module is used to enhance the real-time external damage factor features of the first optical cable segment based on the real-time external damage factor features of the second optical cable segment. The event recognition module is used to process the real-time external damage factor characteristics of the first optical cable segment after enhancement through the external damage early warning recognition model, and obtain the external damage early warning category of the first optical cable segment.

[0013] According to a third aspect of this application, an electronic device is provided, comprising: Memory, used to store one or more computer programs; A processor, when the one or more computer programs are executed by the processor, implements the external damage early warning and identification method of distributed fiber optic acoustic sensing described in the first aspect above.

[0014] According to a fourth aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the external damage early warning and identification method of distributed fiber optic acoustic sensing described in the first aspect above.

[0015] Based on any of the above aspects, the present application provides a distributed fiber optic acoustic wave sensing method, system, electronic device, and computer storage medium for external damage early warning identification. This method integrates the features of the real-time DAS data with the features of the real-time environmental factors to obtain real-time external damage factor features. It then selects a first optical cable segment and a second optical cable segment adjacent to the first optical cable segment from the optical cable segments to be tested. The real-time external damage factor features of the second optical cable segment are used to enhance the real-time external damage features of the first optical cable segment. This enables the external damage early warning identification model to comprehensively consider the real-time DAS data of the first optical cable segment and the influence of the environment, and to combine the contextual feature information of the adjacent area of ​​the first optical cable segment, thereby achieving accurate identification of the external damage early warning category of the first optical cable segment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the steps of the identification method provided in this embodiment.

[0018] Figure 2 This is a schematic diagram of the steps for real-time external damage factor feature extraction provided in this embodiment.

[0019] Figure 3 This is a flowchart illustrating the steps for obtaining external damage early warning categories provided in this embodiment.

[0020] Figure 4 This is a schematic diagram of the functional modules of the identification system provided in this embodiment.

[0021] Figure 5 This is a schematic diagram of the device structure of the electronic device provided in this embodiment. Detailed Implementation

[0022] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this application. To better illustrate the following embodiments, some components in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product; it is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] With the popularization of fiber optic technology, fiber optic cables are becoming increasingly prevalent in people's daily lives, and the number of fiber optic cables laid is also constantly increasing. However, the increase in the number of fiber optic cables laid also makes them more susceptible to damage from external factors such as construction or urban redevelopment, which in turn affects the user experience.

[0026] When an abnormality occurs in an optical cable, a corresponding external damage warning is usually received. Understandably, an external damage warning can be a pre-existing external damage warning event. Therefore, it is necessary to identify and determine whether the external damage warning constitutes an actual external damage event. Current identification methods primarily involve collecting relevant data about the optical cable using distributed acoustic sensing (DAS) devices, and then using pattern recognition or neural network models based on the collected data.

[0027] Because raw DAS data is based on the disturbance of optical fibers by external sound waves, it is highly susceptible to environmental factors. For example, for buried optical cables, the propagation of sound waves varies depending on the geological conditions, such as whether they are buried in concrete or mud. This results in the same event producing sound with different characteristics after passing through different geological conditions. Therefore, relying solely on raw DAS data for external damage early warning will yield inaccurate results.

[0028] This embodiment provides a technical solution that can solve the above problems. The specific implementation of this application will be described in detail below with reference to the accompanying drawings.

[0029] like Figure 1 As shown in the figure, this embodiment provides a method for early warning and identification of external damage using distributed fiber optic acoustic sensing, which may include the following steps: S1: Obtain real-time DAS data of each optical cable segment under test, as well as real-time environmental factors of each optical cable segment under test. In this embodiment, the optical cable segment to be tested is obtained by dividing the optical cable to be tested according to a preset length. The real-time DAS data of the optical cable segment to be tested mainly includes parameters such as the timestamp of the DAS data, the sound wave intensity and frequency. Through these parameters, features used to identify the external damage warning category of the real-time DAS data can be effectively extracted.

[0030] In this embodiment, the real-time DAS data can be acquired using distributed acoustic sensing technology. Data acquisition is achieved by connecting the DAS device to the optical cable under test. The DAS device connected to the optical cable under test can monitor and record acoustic information along the cable in real time, obtaining the global DAS data of the optical cable under test. Then, based on the segmentation of the optical cable under test, the real-time DAS data of the segment under test can be extracted from the global DAS data.

[0031] In this embodiment, the real-time environmental factors may include at least climate factors, geological factors, and human activity factors. Climate factors may include weather, temperature, and humidity; geological factors may include geological conditions and earthquakes; and human activity factors may include construction site activities and environmental noise.

[0032] Understandably, in this embodiment, geological conditions can be obtained from the latest map data. Preferably, the surrounding housing conditions and urban road or building construction information of the location corresponding to the optical cable segment to be tested can be obtained, which can provide a more sufficient basis for the analysis of external damage early warning categories.

[0033] Climate factors such as weather, temperature, and humidity can be obtained through weather stations or online weather services; in some implementations, temperature and humidity data can also be obtained in real time through sensors installed along the fiber optic cable.

[0034] The collection of earthquake data can rely on records from earthquake monitoring stations, which are crucial for assessing the impact of seismic activity on the safety of optical cables.

[0035] Construction information can be obtained through real-time data on construction permits and progress, as well as through on-site surveys. Environmental noise data can be monitored on-site using equipment such as sound level meters to assess the potential impact of noise levels on the fiber optic cable.

[0036] By comprehensively analyzing these multi-source environmental factors, we can more accurately identify the external damage warning category of the optical cable segment under test, thereby providing a scientific basis for maintenance work.

[0037] S2: Obtain the real-time external damage characteristics of the optical cable segment under test based on the real-time DAS data and the real-time environmental factors; In this embodiment, as Figure 2 As shown, step S2 may include the following steps: S21: Encode the real-time environmental factors to obtain the real-time environmental code; S22: Extract the real-time environment features of the real-time environment code and extract the real-time DAS features of the real-time DAS data; S23: The real-time environmental features and the real-time DAS features are fused based on preset weights to obtain the real-time external damage factor features of the optical cable segment under test.

[0038] Understandably, since real-time environmental factors are all abstract elements, such as weather which includes abstract descriptions like sunny and cloudy, they are difficult to combine with real-time DAS data. Therefore, before actual integration, it is necessary to perform feature processing on the abstract real-time environmental factors, that is, to convert the abstract real-time environmental factors into specific real-time environmental features, so as to facilitate subsequent data integration.

[0039] In order to integrate different real-time environmental factors into a single-dimensional real-time environmental feature, the real-time environmental factors can be encoded. This encoding process can include: The real-time environmental factors are encoded using a preset encoding logic to obtain an initial environmental code; the initial environmental code is then converted into standardized data between 0 and 1 using a preset standardization method, which serves as the real-time environmental code for the real-time environmental factors.

[0040] The initial environment code may include the coding bits and coding values ​​of the real-time environmental factors. The coding bits are used to represent the specific category of the real-time environmental factors, and the coding values ​​represent the specific numerical values ​​of the corresponding category of the real-time environmental factors.

[0041] For example, for the weather factor, the initial environmental code for sunny days can be [1, 1], and the initial environmental code for cloudy days can be [1, 2], where the first bit is the code bit for the real-time environmental factor of the weather, and the second bit is the code value for the real-time environmental factor of the weather. Similarly, the initial environmental code for the temperature factor can be [2, 15], where the first bit is the code bit for the real-time environmental factor of the temperature, and the second bit is the code value for the real-time environmental factor of the temperature, representing the specific temperature value. It should be noted that the above examples are only for ease of understanding and do not represent the actual encoding logic.

[0042] As can be seen from the above, the dimensions of the encoded values ​​are different for different categories of real-time environmental factors. Therefore, after obtaining the initial environmental codes of the real-time environmental factors, it is necessary to standardize the initial environmental codes. In this embodiment, standardization can be achieved through a maximum-minimum normalization method. A corresponding prior range can be pre-set for each category of real-time environmental factors, and the maximum and minimum values ​​of the real-time environmental factors can be determined based on the prior range. The maximum-minimum normalization method can then be expressed as: In the formula, The encoded value representing the real-time environmental factors, This represents the minimum value of the prior range of the corresponding category of the real-time environmental factors. This represents the maximum value of the prior range of the corresponding category of the real-time environmental factor; This represents the encoded value of the real-time environmental factors after standardization.

[0043] After standardizing the encoded value, the encoded bits can be combined with the standardized encoded value to obtain the real-time environment code.

[0044] In this embodiment, the real-time DAS data also needs to undergo feature processing. Specifically, features can be extracted from multiple dimensions of the real-time DAS data, such as acoustic wave amplitude features and acoustic wave frequency features, as real-time DAS features. After obtaining the real-time DAS features, they can be concatenated with real-time environmental features to obtain external damage factor features that include environmental influences.

[0045] During the feature fusion process, since the feature information extracted from DAS data contains multiple dimensions, and the real-time environmental features may also contain multiple features, and different features have different degrees of correlation with the identification of external damage warnings, it is necessary to assign corresponding weights to each feature.

[0046] For example, suppose real-time DAS data includes three factors: amplitude, frequency, and time of arrival, with corresponding weights of 0.8, 0.6, and 0.5, respectively; and environmental factors include three factors: temperature, humidity, and traffic flow, with corresponding weights of 0.4, 0.3, and 0.7, respectively. The weight distributions of real-time DAS features and real-time environment features can then be expressed as follows: DAS characteristics: [Amplitude (0.8), Frequency (0.6), Time to Arrival (0.5)]; Real-time environmental characteristics: [Temperature (0.4), Humidity (0.3), Traffic flow (0.7)]; The real-time external failure factor characteristics obtained after splicing can be expressed as: Real-time external damage factor characteristics: [0.8 * amplitude, 0.6 * frequency, 0.5 * arrival time, 0.4 * temperature, 0.3 * humidity, 0.7 * traffic flow]; The allocation of weights needs to be specifically set according to the impact of specific factor data on the early warning of external damage.

[0047] S3: The optical cable segment under test that has experienced an external damage warning is designated as the first optical cable segment; As mentioned above, the external damage warning can be understood as a warning event of suspected external damage, and further judgment is needed to determine whether the external damage warning is indeed an external damage event.

[0048] In this embodiment, the global DAS data of the optical cable under test can be monitored to detect whether there is abnormal data corresponding to the external damage warning in the global DAS data. The optical cable segment on the optical cable under test that has the external damage warning is obtained as the first optical cable segment based on the location of the abnormal data.

[0049] S4: At both ends of the first optical cable segment, at least one optical cable segment to be tested that is closest to the first optical cable segment is obtained as the second optical cable segment; For example, based on the division of the optical cable segment under test after division, a preset number can be set for each optical cable segment under test along the direction of the optical cable under test. Assuming that the preset number of the first optical cable segment is 4, the optical cable segments under test with preset numbers 2 and 3 at one end of the first optical cable segment can be used as the second optical cable segment, and the optical cable segments under test with preset numbers 5 and 6 at the other end of the first optical cable segment can be used as the second optical cable segment.

[0050] Understandably, since the second optical cable segment is close to the first optical cable segment, any external damage warning occurring on the first optical cable segment will also affect the second optical cable segment. Therefore, the information of external damage warning detected in the second optical cable segment can be used to enhance the information of external damage warning detected in the first optical cable segment.

[0051] S5: Enhance the real-time external damage factor characteristics of the first optical cable segment based on the real-time external damage factor characteristics of the second optical cable segment; Preferably, the number of second optical cable segments at both ends of the first optical cable segment is the same; In this embodiment, step S5 can be represented by the following formula: In the formula, i is the preset number of the optical cable segment to be tested corresponding to the first optical cable segment in the optical cable to be tested. The real-time external damage characteristics of the first optical cable segment after reinforcement. Indicates the first optical cable segment Feature transfer enhancement formula for layers, The number of second optical cable segments at either end of the first optical cable segment. , This refers to the real-time external damage characteristics of the first optical cable segment before reinforcement. It is the ReLU activation function. For the first Learnable parameters of the layer feature transfer enhancement formula. For splicing symbols, This represents a preset set of numbers for the second optical cable segment that is directly adjacent to the first optical cable segment. This represents the number of preset numbers in the preset number set.

[0052] In the above formula, The enhancement features of the optical cable itself and its adjacent test optical cable segment (the second optical cable segment) at layer l-1 are calculated. and (), understandably, the aforementioned first The enhancement features of a layer are obtained by splicing and integrating the enhancement features of the previous layer (layer l-1) and the enhancement features of the layer l-1 corresponding to the second optical cable segment adjacent to the first optical cable segment. Meanwhile, for The preset number j of the second optical cable segment can be further input into... In the formula, the enhanced real-time external damage factor characteristics corresponding to the second optical cable segment are obtained, therefore It is also due to its own and the adjacent optical cable segments under test in the lth The features are calculated recursively from two layers, thus making the entire update process a recursive sequence that starts with l=0 and depends on the output of the previous time step by step.

[0053] Understandably, the above formula is equivalent to constructing a graph neural network based on the first optical cable segment and the corresponding second optical cable segment, and transmitting information from the outermost second optical cable segment of the first optical cable segment to the inner optical cable segment under test step by step. This allows the features of the first optical cable segment at layer l to not only integrate its own historical representation, but also to aggregate contextual information from the spatially adjacent region step by step, ultimately forming an enhanced representation for the collaborative perception of local disturbances and global patterns.

[0054] Understandably, through feature enhancement, the real-time external damage factor features of the first optical cable segment include not only its local real-time DAS data and real-time environmental factors, but also similar information from the adjacent second optical cable segment. Furthermore, since external damage warnings are typically spatially continuous, the resulting acoustic disturbances and environmental responses will simultaneously manifest in multiple neighboring optical cable segments. Therefore, feature enhancement effectively suppresses false positives caused by local DAS anomalies or environmental false alarms, while strengthening the consistent representation of true external damage warnings in DAS signals and environmental context, thus improving the robustness and accuracy of subsequent external damage warning identification models.

[0055] S6: The external damage warning identification model is used to process the real-time external damage factor characteristics of the first optical cable segment after enhancement, and the external damage warning category of the first optical cable segment is obtained.

[0056] In this embodiment, as Figure 3 As shown, step S6 may include the following steps: S61: Calculate the distance between each external damage warning feature in the external damage warning feature library of the external damage warning identification model and the real-time external damage factor feature; S62: Based on the nearest neighbor hyperparameter of the external damage early warning identification model, select several candidate external damage early warning features that are closest to the real-time external damage factor features from the external damage early warning features; S63: Obtain the external damage warning category of the first optical cable segment according to the preset external damage warning category label of the candidate external damage warning features.

[0057] Understandably, in this embodiment, the external damage early warning identification model is implemented based on the k-NN (k-Nearest Neighbors) algorithm. A corresponding external damage early warning feature library is pre-built in the external damage early warning identification model, and the external damage early warning identification model identifies the input real-time external damage factor features based on the external damage early warning feature library.

[0058] In this embodiment, the construction of the external damage early warning feature database may include: Collect historical DAS data for known external damage warning categories and the corresponding historical environmental factors; obtain historical external damage factor features based on the historical DAS data and the historical environmental factors; add external damage warning category labels to the historical external damage factor features according to the known external damage warning categories to obtain the external damage factor features; construct the external damage warning feature library based on the external damage factor features.

[0059] It is understood that the acquisition of the historical DAS data, the historical environmental factors, and the historical external damage factor characteristics can be obtained by referring to the acquisition of the real-time DAS data, the real-time environmental factors, and the real-time external damage factor characteristics, which will not be elaborated further here.

[0060] Understandably, the external damage early warning identification model built based on the k-NN algorithm identifies external damage early warning categories based on the external damage early warning feature library therein. Therefore, the external damage early warning identification model is relatively small in scale, enabling lightweight deployment. At the same time, the external damage early warning identification model built based on k-NN has higher versatility.

[0061] In this embodiment, the acquisition of the nearest neighbor hyperparameters of the external damage early warning identification model includes: Several candidate nearest neighbor hyperparameters are preset; External damage early warning features are selected from the external damage early warning feature library as external damage verification event features; For each of the candidate nearest neighbor hyperparameters: Calculate the distance between the external damage verification event feature and each external damage warning feature in the external damage warning feature library, and based on the candidate nearest neighbor hyperparameter, select several candidate external damage warning features that are closest to the external damage verification event feature from the external damage warning features. Based on the external damage warning category labels of the several candidate external damage warning features, obtain the external damage warning category to be verified for the external damage verification event feature. Based on the external damage warning category to be verified and the external damage verification event feature external damage warning category label, the nearest neighbor hyperparameter is selected from the candidate nearest neighbor hyperparameters.

[0062] Understandably, the nearest neighbor hyperparameter represents the number of nearest neighbor samples referenced when performing identification based on the k-NN algorithm. By adjusting the value of the nearest neighbor hyperparameter, the model complexity of the external damage early warning identification model can be controlled. When the nearest neighbor hyperparameter is small, the external damage early warning identification model is sensitive to local details and easily affected by noise, which may lead to overfitting. When the nearest neighbor hyperparameter is large, the decision boundary of the external damage early warning identification model is smoother and the generalization ability is enhanced, but it may ignore local patterns, resulting in underfitting of the external damage early warning identification model.

[0063] Therefore, by obtaining the optimal nearest neighbor hyperparameters, the performance of the external damage early warning and identification model can be effectively guaranteed.

[0064] In this embodiment, real-time external damage factor features are obtained by integrating the features of the real-time DAS data with the features of the real-time environmental factors. A first optical cable segment and a second optical cable segment adjacent to the first segment are selected from the optical cable segments to be tested. The real-time external damage factor features of the second optical cable segment are used to enhance the real-time external damage features of the first optical cable segment. This allows the external damage warning identification model to comprehensively consider the real-time DAS data and environmental influences of the first optical cable segment, and combine this with contextual feature information from the vicinity of the first optical cable segment, thereby achieving accurate identification of the external damage warning category for the first optical cable segment. Furthermore, the external damage warning identification model built based on k-NN effectively enables lightweight deployment of the model and provides it with higher versatility.

[0065] like Figure 5 As shown in the illustration, this application also provides a distributed fiber optic acoustic sensing-based external damage early warning and identification system. Optionally, the identification system may include... The data acquisition module 11 is used to acquire real-time DAS data of each optical cable segment under test, as well as real-time environmental factors of each optical cable segment under test. In this embodiment, the data acquisition module 11 can be used to perform... Figure 1For a detailed description of the data acquisition module 11 shown in step S1, please refer to the description of step S1.

[0066] Feature extraction module 12 is used to obtain the real-time external damage factor features of the optical cable segment under test based on the real-time DAS data and the real-time environmental factors. In this embodiment, the feature extraction module 12 can be used to perform... Figure 1 For a detailed description of the feature extraction module 12 shown in step S2, please refer to the description of step S2.

[0067] The optical cable segment determination module 13 is used to identify the optical cable segment under test that has experienced an external damage warning as the first optical cable segment, and to identify at least one optical cable segment under test that is closest to the first optical cable segment at each end of the first optical cable segment as the second optical cable segment. In this embodiment, the optical cable segment determination module 13 can be used to perform... Figure 1 For a detailed description of the optical cable segment determination module 13, see steps S3 and S4 shown below. For a detailed description of steps S3 and S4, please refer to the description of steps S3 and S4.

[0068] The feature enhancement module 14 is used to enhance the real-time external damage factor features of the first optical cable segment based on the real-time external damage factor features of the second optical cable segment. In this embodiment, the feature enhancement module 14 can be used to perform... Figure 1 For a detailed description of the feature enhancement module 14, please refer to the description of step S5 shown.

[0069] Event recognition module 15 is used to process the real-time external damage factor characteristics of the first optical cable segment after enhancement through the external damage early warning recognition model, and obtain the external damage early warning category of the first optical cable segment. In this embodiment, the event recognition module 15 can be used to perform... Figure 1 For a detailed description of the event recognition module 15, please refer to the description of step S6 shown.

[0070] This application provides an electronic device with the following structure: Figure 5 As shown.

[0071] The electronic device includes a memory 21, a processor 22, a communication module 23, and an input / output interface 24, etc. Optionally, the memory 21, the processor 22, the communication module 23, and the input / output interface 24 can be connected and communicate with each other through a bus 25.

[0072] The memory 21 is used to store one or more computer programs and transmit the code of the computer programs to the processor 22; when the one or more computer programs are executed by the processor 22, a method for early warning and identification of external damage using distributed fiber optic acoustic sensing in this embodiment of the application is implemented.

[0073] Optionally, the electronic device can be connected to a network via communication module 23 to communicate with other devices, such as terminals or servers, to achieve data interaction. The electronic device can be various forms of digital computers, exemplarily such as desktop computers, servers, workbenches, mainframes, or other types of computers. The electronic device can also be various forms of mobile terminals, exemplarily such as smartphones, tablets, wearable devices (such as helmets, glasses, watches, etc.), and other similar mobile terminals.

[0074] Optionally, the electronic device can connect to required input / output devices, such as a keyboard or display device, via the input / output interface 24. The electronic device itself may have a display device, and other display devices can also be connected externally via the input / output interface 24. Optionally, a storage device, such as a hard disk, can also be connected via the input / output interface 24 to store data from the electronic device, read data from the storage device, or store data from the storage device in the memory 21. It is understood that the input / output interface 24 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 24 can be a component of the electronic device or an external device connected to the electronic device when needed.

[0075] Optionally, the memory 21 may be a volatile memory and / or a non-volatile memory. The volatile memory may be a random access memory, etc., and the non-volatile memory may be a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory, etc.

[0076] Optionally, the computer program stored in the processor 22 can be divided into one or more modules, which are stored in the memory 21 and executed by the processor 22 to perform the method provided in this embodiment. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device.

[0077] Optionally, the processor 22 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 22 include, but are not limited to, a central processing unit, a graphics processing unit, a digital signal processor, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, and can also be any suitable controller, microcontroller, processor, etc. The processor 22 executes the various methods and processes of this embodiment, exemplarily, such as a distributed fiber optic acoustic wave sensing method for external damage early warning and identification according to an embodiment of this application.

[0078] Optionally, the bus 25 may include a path for transmitting information. Depending on its function, the bus 25 may be divided into an address bus, a data bus, a control bus, etc.

[0079] In an optional implementation, this application embodiment also provides a computer storage medium storing a computer program thereon. When executed by a computer, the computer program enables the computer to perform the methods described in the above-described method embodiments. Part or all of the computer program can be loaded and / or installed on the memory 21 of an electronic device. When the computer program is executed by the processor 22, one or more steps of a distributed fiber optic acoustic sensing method for external damage early warning and identification according to this application embodiment can be performed.

[0080] Optionally, the computer-readable storage medium may be a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc.

[0081] Obviously, the above embodiments of this application are merely examples for clearly illustrating the technical solution of this application, and are not intended to limit the specific implementation of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the claims of this application should be included within the protection scope of the claims of this application.

Claims

1. A method for early warning and identification of external damage using distributed fiber optic acoustic sensing, characterized in that, The method includes: The real-time DAS data of each segment of the optical cable under test and the real-time environmental factors of each segment are obtained; the segments are obtained by dividing the optical cable under test according to a preset length. The real-time external damage characteristics of the optical cable segment under test are obtained based on the real-time DAS data and the real-time environmental factors. The optical cable segment under test that experiences an external damage warning is designated as the first optical cable segment. At both ends of the first optical cable segment, at least one optical cable segment to be tested that is closest to the first optical cable segment is obtained as the second optical cable segment; The real-time external damage factor characteristics of the first optical cable segment are enhanced based on the real-time external damage factor characteristics of the second optical cable segment. The external damage warning identification model is used to process the real-time external damage factor characteristics of the first optical cable segment after enhancement, and the external damage warning category of the first optical cable segment is obtained.

2. The method for early warning and identification of external damage using distributed fiber optic acoustic sensing according to claim 1, characterized in that, The number of second optical cable segments at both ends of the first optical cable segment is the same; The feature enhancement of the real-time external damage factor characteristics of the first optical cable segment based on the real-time external damage factor characteristics of the second optical cable segment is expressed as follows: In the formula, i is the preset number of the optical cable segment to be tested corresponding to the first optical cable segment in the optical cable to be tested. The real-time external damage characteristics of the first optical cable segment after reinforcement. Indicates the first optical cable segment Feature transfer enhancement formula for layers, The number of second optical cable segments at either end of the first optical cable segment. , This refers to the real-time external damage characteristics of the first optical cable segment before reinforcement. It is the ReLU activation function. For the first Learnable parameters of the layer feature transfer enhancement formula. For splicing symbols, This represents a preset set of numbers for the second optical cable segment that is directly adjacent to the first optical cable segment. This represents the number of preset numbers in the preset number set.

3. The method for early warning and identification of external damage using distributed fiber optic acoustic sensing according to claim 1, characterized in that, The step of obtaining the real-time external damage factor characteristics of the optical cable segment under test based on the real-time DAS data and the real-time environmental factors includes: The real-time environmental factors are encoded to obtain the real-time environmental code; Extract the real-time environment features from the real-time environment code, and extract the real-time DAS features from the real-time DAS data; The real-time environmental features and the real-time DAS features are fused based on preset weights to obtain the real-time external damage factor features of the optical cable segment under test.

4. The method for early warning and identification of external damage using distributed fiber optic acoustic sensing according to claim 3, characterized in that, The encoding process for the real-time environmental factors to obtain real-time environmental codes includes: The real-time environmental factors are encoded using a preset encoding logic to obtain the initial environmental code; The initial environment code is converted into standardized data between 0 and 1 using a preset standardization method, and used as the real-time environment code for the real-time environmental factors.

5. A method for early warning and identification of external damage using distributed fiber optic acoustic sensing according to any one of claims 1 to 4, characterized in that, The external damage early warning identification model processes the real-time external damage factor characteristics of the enhanced first optical cable segment to obtain the external damage early warning category of the first optical cable segment, including: Calculate the distance between each external damage warning feature in the external damage warning feature library of the external damage warning identification model and the real-time external damage factor features; Based on the nearest neighbor hyperparameter of the external damage early warning identification model, select several candidate external damage early warning features that are closest to the real-time external damage factor features from the external damage early warning features; Based on the preset external damage warning category label of the candidate external damage warning features, the external damage warning category of the first optical cable segment is obtained.

6. The method for early warning and identification of external damage using distributed fiber optic acoustic sensing according to claim 5, characterized in that, The construction of the external damage early warning feature database includes: Collect historical DAS data for known external damage warning categories, and the historical environmental factors corresponding to the historical DAS data; Based on the historical DAS data and the historical environmental factors, the characteristics of historical external damage factors are obtained; Based on the known external damage warning categories, add external damage warning category labels to the historical external damage factor characteristics to obtain the external damage factor characteristics; The external damage early warning feature library is constructed based on the external damage factor characteristics.

7. The method for early warning and identification of external damage using distributed fiber optic acoustic sensing according to claim 5, characterized in that, The acquisition of the nearest neighbor hyperparameters of the external damage early warning identification model includes: Several candidate nearest neighbor hyperparameters are preset; External damage early warning features are selected from the external damage early warning feature library as external damage verification event features; For each of the candidate nearest neighbor hyperparameters: Calculate the distance between the external damage verification event feature and each external damage warning feature in the external damage warning feature library, and based on the candidate nearest neighbor hyperparameter, select several candidate external damage warning features that are closest to the external damage verification event feature from the external damage warning features. Based on the external damage warning category labels of the several candidate external damage warning features, obtain the external damage warning category to be verified for the external damage verification event feature. Based on the external damage warning category to be verified and the external damage verification event feature external damage warning category label, the nearest neighbor hyperparameter is selected from the candidate nearest neighbor hyperparameters.

8. A distributed fiber optic acoustic wave sensing system for early warning and identification of external damage, characterized in that, The system includes: The data acquisition module is used to acquire real-time DAS data of each optical cable segment under test, as well as real-time environmental factors of each optical cable segment under test; the optical cable segments under test are obtained by dividing the optical cable under test according to a preset length. The feature extraction module is used to obtain the real-time external damage factor features of the optical cable segment under test based on the real-time DAS data and the real-time environmental factors. The optical cable segment determination module is used to identify the optical cable segment under test that has experienced an external damage warning as the first optical cable segment, and to identify at least one optical cable segment under test that is closest to the first optical cable segment at each end of the first optical cable segment as the second optical cable segment. The feature enhancement module is used to enhance the real-time external damage factor features of the first optical cable segment based on the real-time external damage factor features of the second optical cable segment. The event recognition module is used to process the real-time external damage factor characteristics of the first optical cable segment after enhancement through the external damage early warning recognition model, and obtain the external damage early warning category of the first optical cable segment.

9. An electronic device, characterized in that, include: Memory, used to store one or more computer programs; A processor, when the one or more computer programs are executed by the processor, implements a distributed fiber optic acoustic wave sensing method for early warning and identification of external damage as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute and implement the external damage early warning and identification method of distributed fiber optic acoustic wave sensing as described in any one of claims 1-7.

Images