A distributed optical fiber sensing defect positioning method based on a spatial defect voting mechanism

Abstract

This invention discloses a distributed fiber optic sensing defect localization method based on a spatial defect voting mechanism, comprising: acquiring abnormal spatiotemporal samples and their spatial starting indices; accumulating the number of anomalies for each spatial starting index based on the abnormal spatiotemporal samples to obtain anomaly count statistics; constructing a coverage count threshold based on the anomaly count statistics and the coverage count threshold; acquiring the potential starting boundary and potential ending boundary of the potential defect region based on the potential starting boundary, potential ending boundary, and spatial window width; acquiring the true starting boundary and true ending boundary of the target defect based on the true starting boundary, true ending boundary, and the spatial resolution of the distributed fiber optic sensor; and obtaining the physical location and physical size of the target defect based on the true starting boundary, true ending boundary, and the spatial resolution of the distributed fiber optic sensor. This invention can improve the accuracy and efficiency of defect localization and can be widely applied in the fields of structural health monitoring and non-destructive testing.

Description

Technical Field

[0001] This invention relates to the field of structural health monitoring and non-destructive testing technology, and in particular to a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism. Background Technology

[0002] When using distributed fiber optic sensors to monitor the health of large composite structures (such as the main beam of wind turbine blades), accurately determining the physical location, boundaries, and dimensions of defects is crucial for subsequent assessment and maintenance decisions. Traditional methods typically rely on manual comparison or simple spatial clustering, which suffers from low efficiency, high subjectivity, and ambiguous boundary positioning. Especially under dynamic load conditions, defect response signals are complex, and the sliding window used in anomaly detection models introduces positioning ambiguity (an anomaly window may only partially cover the actual defect). Summary of the Invention

[0003] In view of this, the main objective of this invention is to provide a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism, in order to solve at least one of the problems in the prior art. This invention can improve the accuracy and efficiency of defect localization.

[0004] To achieve the above objectives, one aspect of the present invention provides a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism, the method comprising: Obtain the abnormal spatiotemporal sample and the spatial starting index of the abnormal spatiotemporal sample; Based on the abnormal spatiotemporal samples, the number of abnormalities is accumulated for each spatial starting index to obtain the statistical results of the number of abnormalities. Based on the anomaly count statistics, a coverage count threshold is constructed. Based on the anomaly count statistics and the coverage count threshold, the potential starting boundary and the potential ending boundary of the potential defect region are obtained. Based on the potential starting boundary, the potential ending boundary, and the spatial window width, obtain the actual starting boundary and the actual ending boundary of the target defect; The physical location and physical size of the target defect are obtained based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor.

[0005] In some embodiments, obtaining the anomalous spatiotemporal sample and the spatial starting index of the anomalous spatiotemporal sample includes the following steps: The original spatiotemporal strain data of the target structure are obtained through the distributed optical fiber sensor. The original spatiotemporal strain data are sampled using the sliding window method to obtain sliding window samples and the spatial starting index of the sliding window samples. Anomaly detection is performed on the sliding window samples using an anomaly detection model to obtain the abnormal spatiotemporal samples and their spatial starting indexes.

[0006] In some embodiments, the step of accumulating the number of anomalies for each spatial starting index based on the abnormal spatiotemporal samples to obtain an anomaly count result includes the following steps: Construct a counting array and initialize the count values ​​of all elements of the counting array to zero; the elements of the counting array correspond to the starting index of the space. Traverse the abnormal spatiotemporal samples, and accumulate the count values ​​of the corresponding elements according to the spatial starting index of the abnormal spatiotemporal samples to obtain the abnormality count result.

[0007] In some embodiments, constructing a coverage threshold based on the anomaly count results includes the following steps: Based on the statistical results of the number of anomalies, obtain the maximum anomaly value; Preset the preset ratio coefficient; The coverage threshold is constructed based on the maximum outlier and the preset ratio coefficient.

[0008] In some embodiments, obtaining the potential starting boundary and the potential ending boundary of the potential defect region based on the anomaly count results and the coverage count threshold includes the following steps: The anomaly count results are sequentially searched, and the first spatial starting index that meets the preset conditions is taken as the potential starting boundary, and the last spatial starting index that meets the preset conditions is taken as the potential ending boundary. The preset condition is that the statistical result of the number of anomalies is greater than the coverage threshold.

[0009] In some embodiments, the formula used to obtain the true starting boundary and the true ending boundary of the target defect based on the potential starting boundary, the potential ending boundary, and the spatial window width includes: ; ; In the formula, Indicates the true starting boundary; Indicates the true end boundary; Indicates the potential starting boundary; Indicates the potential termination boundary; Indicates the width of the space window.

[0010] In some embodiments, the formulas used to obtain the physical location and physical size of the target defect based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor include: ; In the formula, Indicates physical dimensions; Indicates the true end boundary; Indicates the true starting boundary; Indicates spatial resolution.

[0011] To achieve the above objectives, another aspect of this invention proposes a distributed optical fiber sensing defect location device based on a spatial defect voting mechanism, the device comprising: The sample acquisition module is used to acquire abnormal spatiotemporal samples and the spatial starting index of the abnormal spatiotemporal samples. The anomaly statistics module is used to accumulate the number of anomalies for each spatial starting index based on the anomaly spatiotemporal sample, and obtain the anomaly count results. The threshold determination module is used to construct a coverage count threshold based on the anomaly count statistics. The potential defect boundary determination module is used to obtain the potential starting boundary and the potential ending boundary of the potential defect region based on the anomaly count statistics and the coverage count threshold. The target defect boundary determination module is used to obtain the actual starting boundary and the actual ending boundary of the target defect based on the potential starting boundary, the potential ending boundary and the width of the spatial window. The target defect localization module is used to obtain the physical location and physical size of the target defect based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor.

[0012] To achieve the above objectives, another aspect of the present invention provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method described above.

[0013] To achieve the above objectives, another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0014] To achieve the above objectives, another aspect of the present invention provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions to cause the computer device to perform the aforementioned method.

[0015] The embodiments of the present invention include at least the following beneficial effects: The present invention provides a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism. This scheme obtains abnormal spatiotemporal samples and their spatial starting indices, providing accurate input data for subsequent processing; based on the abnormal spatiotemporal samples, the number of abnormalities is accumulated for each spatial starting index to obtain anomaly count statistics, effectively amplifying the signal of the real defect area and suppressing false positives caused by random noise or isolated false detections, making subsequent boundary determination more stable and accurate; based on the anomaly count statistics, a coverage count threshold is constructed, avoiding the high false alarm or high false negative problem that may be caused by using a fixed threshold. This approach improves the universality and automation of the method across different application scenarios. Based on the anomaly count statistics and coverage threshold, it obtains the potential starting and ending boundaries of the potential defect region, defining the core area where the defect is most likely to exist, providing reliable input for the final accurate boundary calculation. Based on the potential starting and ending boundaries and the spatial window width, it obtains the true starting and ending boundaries of the target defect. Based on the true starting and ending boundaries and the spatial resolution of the distributed fiber optic sensor, it obtains the physical location and physical size of the target defect, improving the accuracy and efficiency of defect localization. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. 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 of a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the spatial defect voting statistics process provided in an embodiment of the present invention; Figure 3 This is a defect space coverage statistical histogram and location result diagram generated under a certain working condition, provided in an embodiment of the present invention. Figure 4This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0019] It should be noted that although functional modules are divided in the system diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100" and "second / S200" in the specification, claims, and the foregoing drawings may be used herein to describe various concepts, but unless specifically stated otherwise, these concepts are not limited by these terms. These terms are used only to distinguish one concept from another. For example, first information may also be referred to as second information without departing from the scope of the embodiments of the invention, and similarly, second information may also be referred to as first information. Depending on the context, the words "if" or "when" as used herein may be interpreted as "when," "in response to a determination," or "in the event of a determination."

[0020] The terms “at least one,” “multiple,” “each,” “any,” etc., used in this invention, “at least one” includes one, two, or more than two; “multiple” includes two or more than two; “each” refers to each of the corresponding multiple; and “any” refers to any one of the multiple.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0022] Among related technologies, there are methods that rely on manual comparison or simple spatial clustering for defect location. These methods are inefficient, highly subjective, and have vague boundary positioning.

[0023] In view of this, this embodiment of the invention provides a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism, which can effectively integrate and spatially analyze the discrete anomaly sample information output by the anomaly detection model, automatically and accurately calculate the start and end physical locations and their dimensions of the defect, and realize a precise mapping from data anomaly to physical location.

[0024] Figure 1 This is an optional flowchart of a distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism provided in an embodiment of the present invention. Figure 1 The method may include, but is not limited to, steps S100 to S600: Step S100: Obtain the abnormal spatiotemporal sample and the spatial starting index of the abnormal spatiotemporal sample; Step S200: Based on the abnormal spatiotemporal samples, accumulate the number of abnormalities for each spatial starting index to obtain the statistical results of the number of abnormalities; Step S300: Construct a coverage threshold based on the anomaly count statistics. Step S400: Based on the anomaly count statistics and coverage threshold, obtain the potential starting boundary and the potential ending boundary of the potential defect region. Step S500: Based on the potential starting boundary, the potential ending boundary, and the width of the spatial window, obtain the actual starting boundary and the actual ending boundary of the target defect. Step S600: Based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor, the physical location and physical size of the target defect are obtained.

[0025] In step S100 of some embodiments, obtaining abnormal spatiotemporal samples and their corresponding spatial starting indices provides accurate input data for subsequent processing. By determining the unique spatial starting index of each abnormal sample, complex spatiotemporal abnormal data is transformed into a statistically discretizable sequence, laying the data foundation for the spatial localization of target defects.

[0026] In some embodiments, step S100 may include, but is not limited to, steps S110 to S130: Step S110: Obtain the original spatiotemporal strain data of the target structure through distributed fiber optic sensors; Step S120: Using the sliding window method, samples are constructed from the original spatiotemporal strain data to obtain sliding window samples and the spatial starting index of the sliding window samples. Step S130: Anomaly detection is performed on the sliding window samples using an anomaly detection model to obtain the abnormal spatiotemporal samples and the spatial starting index of the abnormal spatiotemporal samples.

[0027] In step S110 of some embodiments, a distributed optical fiber sensor is embedded or attached to the target structure, and the original spatiotemporal strain data of the target structure can be obtained through the distributed optical fiber sensor.

[0028] In step S120 of some embodiments, a spatial sliding window approach is used to construct samples from the original spatiotemporal strain data, thus obtaining sliding window samples. Each sliding window sample can be uniquely identified by its spatial starting index. For example, suppose the optical fibers are arranged along their length... Using discrete spatial measurement points, a spatial sliding window method is employed to construct samples from the original spatiotemporal strain data. The spatial window width is [missing information]. Then each sliding window sample can be obtained by its spatial starting index. Unique identifier, among which .

[0029] In some optional embodiments, the raw spatiotemporal strain data acquired by distributed optical fiber is represented as a two-dimensional matrix. This two-dimensional matrix is ​​then sampled using a sliding window method to generate sliding window samples and their spatial starting indices. For example, during the sliding window process, each discrete spatial measurement point serves as the starting point of the index. The starting position of the time sliding window Extracting a length of [length] in the time dimension The sequence forms the initial spatiotemporal sub-block; then, in the spatial dimension, a sliding window with a step size of 1 and a spatial window width of... This generates a series of sizes. Two-dimensional sliding window sample And each sliding window sample corresponds to a spatial starting index. .

[0030] In step S130 of some embodiments, anomalies are detected on the sliding window samples using an anomaly detection model to obtain multiple anomalous spatiotemporal samples determined by the anomaly detection model, and the spatial starting index corresponding to each anomalous spatiotemporal sample is recorded. Optionally, the anomalous spatiotemporal samples are obtained by processing the raw spatiotemporal strain data acquired by the distributed fiber optic sensor using any sliding window-based anomaly detection method. Each anomalous spatiotemporal sample is uniquely identified spatially by its corresponding sliding window spatial starting index. One anomalous spatiotemporal sample corresponds to one spatial starting index. For example, if sample 1 covers index [10,42] and sample 2 covers index [11,43], then sample 1 is identified by its starting index. Unique identifier; Sample 2 is determined by the starting index. Unique identifier. Each sliding window sample, upon creation, is spatially located by its starting index. Locked. A single spatial starting index can correspond to multiple anomalous spatiotemporal samples; this is a statistical result along the time dimension. Since monitoring is continuous, at different time points, the same starting index is used... The constructed sliding window samples (i.e., samples covering the same spatial range but at different times) may be identified as anomalies multiple times by the anomaly detection model.

[0031] In step S200 of some embodiments, the spatial voting statistics mechanism aggregates and accumulates the abnormal spatiotemporal samples that may be scattered at different time points in the spatial dimension, which can significantly enhance the abnormal signals generated by real and stable target defects, while suppressing false alarms caused by accidental noise or transient interference.

[0032] In some embodiments, step S200 may include, but is not limited to, steps S210 to S220: Step S210: Construct a counting array and initialize the count values ​​of all elements in the counting array to zero; the elements of the counting array correspond to the starting index of the space. Step S220: Traverse the abnormal spatiotemporal samples, and accumulate the count values ​​of the corresponding elements according to the spatial starting index of the abnormal spatiotemporal samples to obtain the abnormality count statistics.

[0033] In step S210 of some embodiments, a length of A counting array of discrete spatial measurement points, where all elements of the array have a count value of 0. Each element of the counting array corresponds to a starting index in the space, i.e., the index of the first point. The index of each element For example, the first of the counting arrays One element is used to store the starting index of the space. The cumulative number of times.

[0034] In step S220 of some embodiments, all anomalous spatiotemporal samples are traversed, and a count is performed on the dimension of the spatial starting index, that is, for each spatial starting index... The cumulative number of times a sliding window sample starting from this spatial starting index is identified as an anomalous spatiotemporal sample is calculated, forming a spatial starting index statistical function for anomalous spatiotemporal samples. .in, This represents the statistical results of the number of anomalies, i.e., the spatial starting index. The sliding window sample, starting from the anomalous spatiotemporal sample, is used to represent the number of times the sample is considered an anomalous spatiotemporal sample. For example, all anomalous spatiotemporal samples are traversed, and for each sample, its spatial starting index is obtained. and the first in the counting array Increment the count of each element by 1. After traversing all elements, the sequence of values ​​stored in the count array constitutes the anomaly count result. .

[0035] In some optional embodiments, a histogram of the statistical distribution of anomalous spatiotemporal samples is constructed along the spatial starting index dimension to reflect the density of anomalous samples in the spatial direction. For example... Figure 2 As shown, the horizontal axis of the statistical histogram represents the spatial starting index, and the vertical axis represents the cumulative number of times that the sliding window samples constructed starting from that spatial starting index were identified as anomalous spatiotemporal samples. .

[0036] In step S300 of some embodiments, the coverage number threshold is dynamically set based on the characteristics of the data itself (such as the maximum outlier). This can adapt to data under different operating conditions or with different noise levels, avoid the high false alarm or high false negative problem that may be caused by using a fixed threshold, and improve the universality and automation of the method in different application scenarios.

[0037] In some embodiments, step S300 may include, but is not limited to, steps S310 to S330: Step S310: Obtain the maximum outlier value based on the outlier count statistics. Step S320: Preset the preset ratio coefficient; Step S330: Construct a coverage threshold based on the maximum outlier and a preset proportional coefficient.

[0038] In step S310 of some embodiments, based on the anomaly count results, the maximum anomaly count value at the starting position of all sample spaces can be obtained, and the calculation formula is as follows: ,in, This indicates the largest outlier.

[0039] In step S320 of some embodiments, an adjustable preset ratio coefficient is preset. This allows for flexible adaptation to various practical engineering monitoring needs and data conditions, thereby finding the optimal balance between reliably identifying real defects and effectively suppressing false alarms.

[0040] In step S330 of some embodiments, based on the maximum outlier and preset ratio coefficient A coverage threshold was constructed. The expression is Will satisfy The location was identified as a potential defect area.

[0041] In some embodiments, before determining the potential start boundary and potential end boundary of the potential defect region, a minimum noise threshold is set. Anomaly counts less than or equal to the minimum noise threshold in the anomaly count results are set to zero or ignored. Only the spatial start index greater than the minimum noise threshold in the anomaly count results is included in the calculation of the potential defect boundary, thereby reducing the interference of noise false detection.

[0042] In step S400 of some embodiments, by determining the spatial starting index of the first and last anomaly counts that are greater than the coverage threshold, the potential starting boundary and potential ending boundary of the potential defect region are determined. This realizes the transformation from discrete statistical values ​​to continuous spatial regions, and can automatically and accurately identify the intervals where anomalies are significantly clustered in space, thereby defining the core range where the defect is most likely to exist, and providing reliable input for the final accurate boundary calculation.

[0043] In some embodiments, step S400 may include, but is not limited to, step S410: Step S410: Perform a sequential search on the anomaly count results, taking the first spatial starting index that meets the preset condition as the potential starting boundary and the last spatial starting index that meets the preset condition as the potential ending boundary; wherein, the preset condition is that the anomaly count result is greater than the coverage count threshold, i.e. .

[0044] In step S410 of some embodiments, the anomaly count results are searched sequentially, and the first result that satisfies the condition is selected. The spatial starting index is used as the potential starting boundary, denoted as . The last one to be satisfied The spatial start index is used as the potential end boundary, denoted as . Optionally, the spatial starting points for the first and last occurrences of anomalies whose statistical counts exceed the coverage threshold can be directly determined by using a histogram of the statistical distribution of the constructed spatiotemporal samples, and these points can be used as potential starting and ending boundaries, respectively.

[0045] In step S500 of some embodiments, after obtaining the potential start boundary and potential end boundary of the potential defect region, the true start boundary index and true end boundary index of the target defect are calculated using the defect boundary calculation formula, combined with the spatial window width. This corrects the systematic bias introduced by sliding window sampling and accurately restores the statistical results based on the window start index to the actual start and end sample point indices of the defect on the optical fiber. This solves the offset problem between the "window start point" and the "actual edge of the defect," thereby significantly improving the accuracy of defect localization. For example, the formulas used to obtain the true start boundary and true end boundary of the target defect include: ; ; In the formula, Indicates the true starting boundary; Indicates the true end boundary; Indicates the potential starting boundary; Indicates the potential termination boundary; Indicates the width of the space window.

[0046] In step S600 of some embodiments, the spatial resolution of the distributed optical fiber sensor Given known sensor parameters, the actual physical distance between two adjacent spatial measurement points is represented. Based on the true starting and ending boundaries of the target defect, and combined with spatial resolution, the true interval corresponding to the target defect is mapped to the actual physical location interval and physical dimensions of the distributed optical fiber along the structural deployment direction. This completes the mapping from data index space to actual physical space, thereby outputting parameters (defect location and length) that can be directly used in engineering practice and have clear physical meaning. This makes the monitoring results intuitive and operable, facilitating downstream maintenance and decision-making. For example, the formula used to obtain the physical dimensions of the target defect includes: ; In the formula, Indicates physical dimensions; Indicates the true end boundary; Indicates the true starting boundary; This indicates spatial resolution. Combined with the starting reference point for fiber optic deployment, the physical dimensions can be determined as follows: The specific physical location of the target defect on the target structure.

[0047] In some embodiments, the output of the preprocessing module (such as an unsupervised monitoring model used to monitor whether there are defects in the target structure) is received. The spatial window width W=33 and the fiber spatial resolution r=2.6mm are known. Taking an example where the model outputs thousands of anomalous spatiotemporal samples from a set of test data, the distributed fiber optic sensing defect localization process based on a spatial defect voting mechanism includes: Step S1: Extract the spatial measurement point range covered by each abnormal sample. For example, sample 1 covers the index [10,42], sample 2 covers the index [11,43], and so on.

[0048] Step S2: Initialize a counting array with a length equal to the total number of measurement points, with all elements set to 0. Iterate through all abnormal samples and count the corresponding index of each sample within its coverage area. Add 1. Finally, generate a statistical histogram (e.g., Figure 3 As shown in the figure, the count values ​​in the region with indices of approximately 2 to 66 are significantly higher than in other regions.

[0049] Step S3: Find the index of the first count value greater than the threshold from the histogram. The index of the last count value greater than the threshold Substitute into the formula to calculate: ; ; Therefore, the data index range corresponding to the inference defect is [34, 66].

[0050] Step S4: Calculate the physical dimensions of the defect. The formula includes: ; By combining the starting reference point of the fiber optic cable deployment, the specific physical location of the 85.8-meter-long defect in the structure can be determined.

[0051] This invention also provides a distributed optical fiber sensor defect localization device based on a spatial defect voting mechanism, which can implement the above-mentioned distributed optical fiber sensor defect localization method based on a spatial defect voting mechanism. The device includes: The sample acquisition module is used to acquire anomalous spatiotemporal samples and their spatial starting indices. The anomaly statistics module is used to accumulate the number of anomalies for each spatial starting index based on the anomaly spatiotemporal samples, and obtain the anomaly count results. The threshold determination module is used to construct the coverage threshold based on the anomaly count statistics. The potential defect boundary determination module is used to obtain the potential starting boundary and the potential ending boundary of the potential defect region based on the anomaly count statistics and the coverage threshold. The target defect boundary determination module is used to obtain the actual starting boundary and the actual ending boundary of the target defect based on the potential starting boundary, the potential ending boundary, and the width of the spatial window. The target defect localization module is used to obtain the physical location and physical size of the target defect based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor.

[0052] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0053] This invention also provides an electronic device, which includes a processor and a memory. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including a tablet computer, an in-vehicle computer, or similar device.

[0054] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0055] refer to Figure 4 , Figure 4 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0056] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0057] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0058] This invention also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions to cause the computer device to perform the aforementioned method.

[0059] In summary, the distributed optical fiber sensing defect localization method based on a spatial defect voting mechanism according to embodiments of the present invention has the following advantages: 1. The embodiments of the present invention are proposed by way of... The core formula cleverly eliminates the positioning system error introduced by the sliding window width, and can restore the true boundary of sub-window accuracy defects from the window-level detection results.

[0060] 2. The embodiments of the present invention adopt a spatial voting statistics mechanism, which effectively amplifies the signal of the real defect area by integrating information from multiple abnormal windows, suppresses false positive points caused by random noise or isolated false detections, and makes the boundary determination more stable.

[0061] 3. The entire positioning process in this embodiment of the invention does not require manual intervention and is completed automatically based on the algorithm. The output results are objective and repeatable, which greatly improves the efficiency and reliability of defect positioning.

[0062] 4. As a post-processing module, this embodiment of the invention can be flexibly integrated with various front-end anomaly detection models (such as models based on reconstruction error, prediction error, etc.), and has wide applicability.

[0063] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0064] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0065] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0067] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0068] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0069] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0070] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0071] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for locating defects in a distributed optical fiber sensor based on a spatial defect voting mechanism, characterized in that, Includes the following steps: Obtain the abnormal spatiotemporal sample and the spatial starting index of the abnormal spatiotemporal sample; Based on the abnormal spatiotemporal samples, the number of abnormalities is accumulated for each spatial starting index to obtain the statistical results of the number of abnormalities. Based on the anomaly count statistics, a coverage count threshold is constructed. Based on the anomaly count statistics and the coverage count threshold, the potential starting boundary and the potential ending boundary of the potential defect region are obtained. Based on the potential starting boundary, the potential ending boundary, and the spatial window width, obtain the actual starting boundary and the actual ending boundary of the target defect; The physical location and physical size of the target defect are obtained based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor.

2. The method according to claim 1, characterized in that, The process of obtaining the anomalous spatiotemporal sample and its spatial starting index includes the following steps: The original spatiotemporal strain data of the target structure are obtained through the distributed optical fiber sensor. The original spatiotemporal strain data are sampled using the sliding window method to obtain sliding window samples and the spatial starting index of the sliding window samples. Anomaly detection is performed on the sliding window samples using an anomaly detection model to obtain the abnormal spatiotemporal samples and their spatial starting indexes.

3. The method according to claim 1, characterized in that, The step of accumulating the number of anomalies for each spatial starting index based on the abnormal spatiotemporal samples to obtain an anomaly count result includes the following steps: Construct a counting array and initialize the count values ​​of all elements of the counting array to zero; the elements of the counting array correspond to the starting index of the space. Traverse the abnormal spatiotemporal samples, and accumulate the count values ​​of the corresponding elements according to the spatial starting index of the abnormal spatiotemporal samples to obtain the abnormality count result.

4. The method according to claim 1, characterized in that, Constructing a coverage threshold based on the anomaly count results includes the following steps: Based on the statistical results of the number of anomalies, obtain the maximum anomaly value; Preset the preset ratio coefficient; The coverage threshold is constructed based on the maximum outlier and the preset ratio coefficient.

5. The method according to claim 1, characterized in that, The step of obtaining the potential starting boundary and the potential ending boundary of the potential defect region based on the anomaly count results and the coverage count threshold includes the following steps: The anomaly count results are sequentially searched, and the first spatial starting index that meets the preset conditions is taken as the potential starting boundary, and the last spatial starting index that meets the preset conditions is taken as the potential ending boundary. The preset condition is that the statistical result of the number of anomalies is greater than the coverage threshold.

6. The method according to claim 1, characterized in that, The formula used to obtain the true starting boundary and the true ending boundary of the target defect based on the potential starting boundary, the potential ending boundary, and the spatial window width includes: ； ； In the formula, Indicates the true starting boundary; Indicates the true end boundary; Indicates the potential starting boundary; Indicates the potential termination boundary; Indicates the width of the space window.

7. The method according to claim 1, characterized in that, The formulas used to obtain the physical location and physical size of the target defect based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor include: ； In the formula, Indicates physical dimensions; Indicates the true end boundary; Indicates the true starting boundary; Indicates spatial resolution.

8. A distributed optical fiber sensing defect location device based on a spatial defect voting mechanism, characterized in that, include: The sample acquisition module is used to acquire abnormal spatiotemporal samples and the spatial starting index of the abnormal spatiotemporal samples. The anomaly statistics module is used to accumulate the number of anomalies for each spatial starting index based on the anomaly spatiotemporal sample, and obtain the anomaly count results. The threshold determination module is used to construct a coverage count threshold based on the anomaly count statistics. The potential defect boundary determination module is used to obtain the potential starting boundary and the potential ending boundary of the potential defect region based on the anomaly count statistics and the coverage count threshold. The target defect boundary determination module is used to obtain the actual starting boundary and the actual ending boundary of the target defect based on the potential starting boundary, the potential ending boundary and the width of the spatial window. The target defect localization module is used to obtain the physical location and physical size of the target defect based on the true starting boundary, the true ending boundary, and the spatial resolution of the distributed fiber optic sensor.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images