Distributed optical fiber vibration event detection method and device

Abstract

The invention relates to a distributed optical fiber vibration event detection method and device, and belongs to the technical field of distributed optical fiber sensing, and the method comprises the steps: obtaining an optical fiber vibration data set, carrying out the parallel processing of the optical fiber vibration data in the optical fiber vibration data set according to a preset operation filtering model, and filtering out the data which does not meet the requirements, therefore, the detection efficiency of the optical fiber vibration data can be improved. The optical fiber vibration waterfall plot can be segmented and adjusted to obtain a color plot, and target detection is performed on the color plot according to the image target detection model to obtain a target frame, so that the detection accuracy can be improved through the image detection process; in addition, the center position and the duration time can be obtained through the target frame, and when the duration time is longer than the alarm limit time, positioning can be performed according to the center position, so that the positioning precision of optical fiber vibration data detection can be improved.

Description

Technical Field

[0001] The present invention relates to the field of distributed optical fiber sensing technology, and in particular to a distributed optical fiber vibration event detection method and device. Background Art

[0002] Distributed optical fiber is widely used in the field of pipeline early warning monitoring and security. The current traditional method for detecting distributed optical fiber vibration events is to preprocess the optical fiber vibration signal to generate an optical fiber vibration waterfall diagram, and then artificially design the interval duration, duration, and spatial impact range of the event excitation based on the regularity of the excitation signal in the optical fiber vibration waterfall diagram to judge the regularity of the excitation signal.

[0003] In the prior art, the fiber optic waterfall diagram calculation and event analysis in the traditional distributed fiber optic vibration event detection method adopt an inefficient sequential execution method. In addition, different pipeline project sites have differences in optical cable burial depth, soil quality, etc., the conduction performance of optical fiber vibration excitation is different, and there are great differences in the artificially designed signal excitation characteristics. As a result, it is difficult to further improve the accuracy, efficiency and positioning accuracy of the traditional distributed fiber optic vibration event detection method.

[0004] Therefore, it is urgent to propose a distributed optical fiber vibration event detection method and device to solve the technical problems that the distributed optical fiber vibration event detection method in the prior art adopts an inefficient sequential execution method, and the differences in optical cable burial depth, soil quality, etc. make it difficult to further improve the accuracy, efficiency and positioning accuracy of the traditional distributed optical fiber vibration event detection method. Summary of the invention

[0005] In view of this, it is necessary to provide a distributed optical fiber vibration event detection method and device to solve the technical problems that the distributed optical fiber vibration event detection method in the prior art adopts an inefficient sequential execution method, and the differences in optical cable burial depth, soil quality, etc. make it difficult to further improve the accuracy, efficiency and positioning accuracy of the traditional distributed optical fiber vibration event detection method.

[0006] In order to solve the above problems, the present invention provides a distributed optical fiber vibration event detection method, comprising: Acquire an optical fiber vibration data set, and perform parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram; Segmenting and adjusting the optical fiber vibration waterfall diagram to obtain a color diagram; Performing target detection on the color image according to an image target detection model to obtain a target frame; According to the target frame, a center position and a duration are obtained; When the duration is greater than the alarm limit time, positioning is performed based on the central position.

[0007] In a possible implementation, the performing parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram includes: Performing parallel bandpass filtering on the optical fiber vibration data in the optical fiber vibration data set according to the preset running filter model to obtain filtered optical fiber vibration data; Merging the filtered optical fiber vibration data of each pulse period to obtain merged optical fiber vibration data; The combined optical fiber vibration data is subjected to frequency reduction processing to obtain an optical fiber vibration waterfall diagram.

[0008] In a possible implementation, the down-conversion processing is performed on the combined optical fiber vibration data to obtain an optical fiber vibration waterfall diagram, including: The maximum value of the optical fiber vibration data of each preset number of cycles in the combined optical fiber vibration data is used as the corresponding vibration value after frequency reduction; Based on all vibration values, the fiber vibration waterfall diagram of the target frequency is obtained.

[0009] In a possible implementation, segmenting and adjusting the optical fiber vibration waterfall diagram to obtain a color diagram includes: Segmenting the optical fiber vibration waterfall diagram to obtain a segmentation matrix; The segmentation matrix is ​​subjected to contrast adaptive enhancement adjustment according to all the vibration values ​​to obtain a color image.

[0010] In a possible implementation, performing contrast adaptive enhancement adjustment on the segmentation matrix according to all the vibration values ​​to obtain a color image includes: Determine the maximum vibration value and the minimum vibration value according to all the vibration values; Obtaining a preset number interval according to the maximum vibration value and the minimum vibration value; According to the preset number intervals, determine the target interval corresponding to each vibration value; According to the calculation formula corresponding to the target interval, the RGB value of each vibration value is obtained; Performing contrast adaptive enhancement adjustment on the segmentation matrix according to the RGB values ​​to obtain a target segmentation matrix; According to the target segmentation matrix, a color map is obtained.

[0011] In a possible implementation, the signal in the target frame is a mining signal; and obtaining the center position and duration according to the target frame includes: Performing centroid processing on the target frame to obtain the center position of the mining signal; According to the upper and lower boundaries of the target box, the start time and the end time of the mining signal are obtained; The duration of the excavation signal is obtained according to the start time and the end time.

[0012] In a possible implementation, performing centroid processing on the target frame to obtain the center position of the mining signal includes: According to the color image, determine the upper left corner coordinates, lower right corner coordinates, the starting position of the grayscale image, and the grayscale value corresponding to the RGB value of each pixel of the target frame; The grayscale value of each pixel is accumulated along the vertical axis to obtain the accumulated grayscale values ​​of all vertical axes; the abscissa of the coordinate of the upper left corner is greater than the number of the accumulated grayscale values ​​of all vertical axes that is greater than the abscissa of the coordinate of the lower right corner; The center position of the mining signal is obtained according to the starting position and the accumulated gray values ​​of all the vertical axes.

[0013] In a possible implementation, obtaining the duration of the mining signal according to the start time and the end time includes: Obtain a difference value according to the start time and the end time; A duration is obtained according to the difference and the target frequency.

[0014] In a possible implementation, the calculation formula corresponding to each interval is: The first interval is:

[0015] The calculation formula for the first interval is:

[0016] The second interval is:

[0017] The calculation formula for the second interval is:

[0018] The third interval is:

[0019] The calculation formula for the third interval is:

[0020] The fourth interval is:

[0021] The calculation formula for the fourth interval is:

[0022] The fifth interval is:

[0023] The calculation formula for the fifth interval is:

[0024] In the formula, Indicates the minimum vibration value; Indicates the maximum vibration value; Indicates the currently calculated vibration value.

[0025] On the other hand, the present invention also provides a distributed optical fiber vibration event detection device, comprising: A data acquisition module, used for acquiring an optical fiber vibration data set, and performing parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram; A color image determination module, used for segmenting and adjusting the optical fiber vibration waterfall image to obtain a color image; A target detection module, used to perform target detection on the color image according to an image target detection model to obtain a target frame; A position determination module, used to obtain a center position and a duration according to the target frame; The time judgment module is used to locate the position according to the center position when the duration is greater than the alarm limit time.

[0026] The beneficial effects of the present invention are as follows: a fiber optic vibration data set can be acquired, and then the fiber optic vibration data in the fiber optic vibration data set can be processed in parallel according to a preset running filter model, data that does not meet the requirements can be filtered out, and a fiber optic vibration waterfall diagram can be obtained, thereby improving the detection efficiency of the fiber optic vibration data; the fiber optic vibration waterfall diagram can also be segmented and adjusted to obtain a color diagram, and then the color diagram is subjected to target detection according to an image target detection model to obtain a target frame, thereby improving the detection accuracy through the image detection process; the center position and duration can also be obtained through the target frame, and when the duration is greater than the alarm limit time, positioning can be performed based on the center position, thereby improving the positioning accuracy of the fiber optic vibration data detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a flow chart of an embodiment of a distributed optical fiber vibration event detection method provided by the present invention; Figure 2 A schematic diagram of the structure of an embodiment of the optical fiber vibration data set provided by the present invention; Figure 3 For the present invention Figure 1 A schematic flow chart of an embodiment of step S101; Figure 4 A schematic diagram of the structure of an embodiment of the optical fiber vibration waterfall diagram provided by the present invention; Figure 5 A schematic diagram of the structure of an embodiment of a color image of 17920m after segmentation and enhancement provided by the present invention; Figure 6 A schematic diagram of the structure of an embodiment of a color image of 24320m after segmentation and enhancement provided by the present invention; Figure 7 A schematic diagram of a flow chart of an embodiment of contrast adaptive enhancement adjustment provided by the present invention; Figure 8 A schematic diagram of the structure of an embodiment of the recognition result of a color image provided by the present invention; Fig. 9 A schematic structural diagram of an embodiment of a distributed optical fiber vibration event detection device provided by the present invention; Fig.10 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0029] like Figure 1 As shown, a specific embodiment of the present invention discloses a distributed optical fiber vibration event detection method, comprising: S101, obtaining an optical fiber vibration data set, and performing parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram; S102, segmenting and adjusting the optical fiber vibration waterfall diagram to obtain a color diagram; S103, performing target detection on the color image according to the image target detection model to obtain a target frame; S104, obtaining the center position and duration according to the target frame; S105: When the duration is greater than the alarm limit time, positioning is performed according to the center position.

[0030] It should be understood that the optical fiber vibration data set obtained in step S101 may be an optical fiber vibration data set obtained from a distributed optical fiber device, or may be an optical fiber vibration data set historically stored in a storage medium, for example. Figure 2As shown, the horizontal axis is the length of the optical fiber, and the vertical axis is the vibration frequency of the optical fiber. The acquisition process of the optical fiber vibration data in the optical fiber vibration data set can be to collect the optical fiber vibration scattering signal at a sampling rate of 1GSPS through a high-speed 16-bit ADC, and the spatial interval of each sampling point is 0.1m. The amount of data collected in each optical pulse cycle is 31k·10·2B = 0.61MB. The optical pulse frequency is set to 1KHz, and the amount of data collected per second is 0.61MB·1K = 610MB.

[0031] In a specific embodiment of the present invention, during use, a parallel processing unit NPU and a preset running filter model can be set. After the optical fiber vibration data set is collected, the optical fiber vibration data of the optical fiber vibration data set can be processed in parallel in the parallel processing unit NPU through the preset running filter model to filter out unnecessary data, thereby obtaining an optical fiber vibration waterfall diagram. The optical fiber vibration waterfall diagram can then be segmented and adjusted to obtain a color image, and then the color image can be subjected to target detection to obtain a target box on the color image. The center position and duration can also be obtained based on the target box, and then the duration can be judged. When the duration is greater than the alarm limit time, an alarm message can be output, and the alarm message can include the center position, so that the alarm position can be accurately located.

[0032] Furthermore, a target detection data set can be obtained, and an image target detection model can be set; the target detection data set can be a data set made using actual operation data of the pipeline project, and the image target detection model can be a Fast R-CNN model, so that the Fast R-CNN model can be trained and debugged through the target detection data set, and the average precision mAP_50 is 99.4%, which is more accurate than the traditional manually designed incentive feature analysis method. The trained image target detection model Fast R-CNN is run in the parallel processing unit NPU, and the artificial and mechanical mining target boxes of the color image can be detected.

[0033] Compared with the prior art, the present embodiment provides a method for acquiring a fiber optic vibration data set, and then performing parallel processing on the fiber optic vibration data in the fiber optic vibration data set according to a preset running filter model, thereby filtering out data that does not meet the requirements and obtaining a fiber optic vibration waterfall diagram, thereby improving the detection efficiency of the fiber optic vibration data; the fiber optic vibration waterfall diagram can also be segmented and adjusted to obtain a color image, and then the color image can be subjected to target detection according to an image target detection model to obtain a target frame, thereby improving the detection accuracy through the image detection process; the center position and duration can also be obtained through the target frame, and when the duration is greater than the alarm limit time, positioning can be performed based on the center position, thereby improving the positioning accuracy of the fiber optic vibration data detection.

[0034] In some embodiments of the present invention, Figure 3 As shown, step S101 includes: S301, performing parallel bandpass filtering on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain filtered optical fiber vibration data; S302, combining and processing the filtered optical fiber vibration data of each pulse period to obtain combined optical fiber vibration data; S303, performing frequency reduction processing on the combined optical fiber vibration data to obtain an optical fiber vibration waterfall diagram.

[0035] In a specific embodiment of the present invention, a preset running filter model can be set. Specifically, python can be used to develop and generate the preset running filter model. The preset running filter model can be a tensorfow filter model. The preset running filter model in the parallel processing unit NPU performs bandpass filtering on the optical fiber vibration data in the collected optical fiber vibration data set, filters out the optical fiber scattering noise signal caused by the low-frequency drift of the laser below 2 Hz and the change of ambient temperature, and filters out the system noise above 80 Hz to obtain filtered optical fiber vibration data. Then, the filtered filtered optical fiber vibration data are merged in the parallel processing unit NPU at the same time. Specifically, the filtered data of each pulse period are averaged and merged every 20 sampling points to obtain merged optical fiber vibration data, wherein the filtering frequency and the number of sampling points can be set according to actual conditions, and the embodiment of the present invention is not limited here.

[0036] In some embodiments of the present invention, step S303 includes: The maximum value of the optical fiber vibration data of each preset number of cycles in the combined optical fiber vibration data is used as the corresponding vibration value after frequency reduction; Based on all vibration values, the fiber vibration waterfall diagram of the target frequency is obtained.

[0037] In a specific embodiment of the present invention, the maximum value of the combined optical fiber vibration data of each preset number of cycles can be used as the vibration value after the corresponding point is frequency-reduced, that is, multiple vibration values ​​can be obtained, and then a fiber optic vibration waterfall diagram of the target frequency can be generated, the spatial resolution of the fiber optic vibration waterfall diagram is 2m, and the target frequency is 20Hz; each preset number of cycles can be every 50 cycles, wherein each preset number of cycles, the spatial resolution and the target frequency can be set according to actual conditions, and the embodiment of the present invention is not limited here; then, fitting can be performed according to all vibration values ​​to obtain a fiber optic vibration waterfall diagram corresponding to the target frequency, and the fiber optic vibration waterfall diagram is as follows: Figure 4As shown, the horizontal axis is the length of the optical fiber, and the vertical axis is the absolute time. Taking the AI ​​processor Ascend310 as an example, it takes 1 second to execute the filtering process sequentially in its ARM core CPU, and it takes 100 ms to run the filtering model in its NPU for parallel processing. Compared with the sequential execution method of the CPU, the parallel processing efficiency of the NPU is improved by 10 times.

[0038] In some embodiments of the present invention, step S102 includes: Segment the optical fiber vibration waterfall diagram to obtain a segmentation matrix; The segmentation matrix is ​​contrast-adaptively enhanced according to all vibration values ​​to obtain a color map.

[0039] In a specific embodiment of the present invention, the optical fiber vibration waterfall diagram can be segmented to obtain a segmentation matrix. For example, the entire optical fiber vibration waterfall diagram can be segmented according to an optical fiber length interval of 1280m and a time interval of 32S, and a segmentation matrix after segmentation can be obtained. The specific segmentation optical fiber length interval and time interval can be set according to actual conditions, and the embodiment of the present invention is not limited thereto. During segmentation, the segmentation matrix can also be subjected to contrast adaptive enhancement adjustment to generate a color image. The size of the color image can be set according to actual conditions, and the embodiment of the present invention is not limited thereto. For example, the color image can be 640*640, such as Figure 5 and Figure 6 As shown, Figure 5 The starting position is the color image of 17920m after segmentation and enhancement. Figure 6 The starting position is the color image of 24320m after segmentation and enhancement, wherein the contrast adaptive enhancement adjustment of the image can be set according to actual conditions, and the embodiment of the present invention is not limited thereto.

[0040] In some embodiments of the present invention, Figure 7 As shown, the segmentation matrix is ​​contrast-adaptively enhanced according to all vibration values ​​to obtain a color map, including: S701, determining a maximum vibration value and a minimum vibration value according to all vibration values; S702, obtaining a preset number interval according to the maximum vibration value and the minimum vibration value; S703, determining a target interval corresponding to each vibration value according to a preset number of intervals; S704, obtaining the RGB value of each vibration value according to the calculation formula corresponding to the target interval; S705, performing contrast adaptive enhancement adjustment on the segmentation matrix according to the RGB values ​​to obtain a target segmentation matrix; S706: Obtain a color image according to the target segmentation matrix.

[0041] In a specific embodiment of the present invention, after obtaining the segmentation matrix, the maximum vibration value and the minimum vibration value can be determined according to the vibration value in the image, so that a preset number of intervals can be set according to the maximum vibration value and the minimum vibration value, and a calculation formula for the RGB value corresponding to each interval can be set, and a target interval corresponding to each vibration value can be determined according to the preset number of intervals, and then the RGB value of each vibration value can be calculated according to the calculation formula of the target interval of each vibration value, and then the segmentation matrix can be adaptively enhanced according to the RGB value, so that a target segmentation matrix can be obtained, and then a color image can be obtained according to the target segmentation matrix, wherein the calculation formula corresponding to each interval is: The first interval is shown in formula (1): (1) The calculation formula for the first interval is: (2) The second interval is: (3) The calculation formula for the second interval is: (4) The third interval is: (5) The calculation formula for the third interval is: (6) The fourth interval is: (7) The calculation formula for the fourth interval is: (8) The fifth interval is: (9) The calculation formula for the fifth interval is: (10) In the formula, Indicates the minimum vibration value; Indicates the maximum vibration value; Indicates the currently calculated vibration value.

[0042] Furthermore, in step S103, after the color image is identified, the color image can be detected by the image target detection model to detect the artificial and mechanical mining target frames of the color image. Figure 5 The recognition result can be obtained by reasoning with the vibration color map in the image. Figure 8As shown in the figure, taking the AI ​​processor Ascend310 as an example, the image target detection model is run in its NPU for inference acceleration. Compared with the CPU and GPU, more images can be inferred at the same power consumption.

[0043] In some embodiments of the present invention, the signal in the target frame is a mining signal; step S104 includes: Perform centroid processing on the target frame to obtain the center position of the mining signal; According to the upper and lower boundaries of the target box, the start and end times of the mining signal are obtained; According to the start time and end time, the duration of the mining signal is obtained.

[0044] In a specific embodiment of the present invention, the signal in the target frame can be a mining signal. The centroid processing is performed on the precise target frame that is accelerated and recognized by the trained image target detection model, and the center position of the mining signal in the target frame is calculated, which has higher accuracy than the traditional manually designed excitation feature analysis positioning method.

[0045] In some embodiments of the present invention, performing centroid processing on the target frame to obtain the center position of the mining signal includes: According to the color image, determine the upper left corner coordinates, lower right corner coordinates, the starting position of the grayscale image, and the grayscale value corresponding to the RGB value of each pixel of the target box; The gray value of each pixel is accumulated along the vertical axis to obtain the accumulated gray value of all vertical axes; the number of the horizontal coordinates of the upper left corner coordinates that is greater than the number of the accumulated gray values ​​of all vertical axes that is greater than the horizontal coordinate of the lower right corner coordinate; The center position of the mining signal is obtained based on the starting position and the accumulated grayscale values ​​of all vertical axes.

[0046] In a specific embodiment of the present invention, Figure 8 The following is the recognition result of the color image. Figure 8 The coordinates of the upper left corner of the mechanical excavation target box in the recognition result are (312, 15), the coordinates of the lower right corner are (447, 585), the starting position of the grayscale image where the target box is located is 17920m, and the grayscale values ​​corresponding to the RGB values ​​of each pixel in the target box are: G 312,15 、G 313,15 、……G 446,15 、G 447,15 G 312,16 、G 313,16 、……G 446,16 、G447,16 …… G 312,584 、G 313, 584 、……G 446, 584 、G 447, 584 G 312,585 、G 313, 585 、……G 446, 585 、G 447, 585 The grayscale values ​​of each pixel can be accumulated along the vertical axis to obtain G 312 、G 313 、……G 446 、G 447 The specific calculation can be G x =G x,15 + G x,16 + …… + G x,584 + G x,585 , the number of the upper left corner coordinates whose horizontal coordinate is greater than the number of the grayscale values ​​accumulated by all the vertical axes is greater than the horizontal coordinate of the lower right corner coordinate, for example, x is an integer greater than or equal to 312 and less than or equal to 447. Then, the center position of the mining signal can be obtained based on the starting position and the grayscale values ​​accumulated by all the vertical axes. The starting position is 17920m, and the calculation of the center position is shown in formula (11): (11) Furthermore, the start time and end time of the mining signal can be obtained according to the upper and lower boundaries of the target box; for example, the upper boundary can be 15 and the lower boundary can be 585, then the start time can be 15 and the end time can be 585.

[0047] In some embodiments of the present invention, obtaining the duration of the mining signal according to the start time and the end time includes: According to the start time and end time, get the difference; The duration is obtained based on the difference and the target frequency.

[0048] In a specific embodiment of the present invention, a difference may be calculated based on the start time and the end time, and then the duration may be obtained based on the difference and the target frequency. For example, if the target frequency is 20, the duration is (585-15) / 20=28S.

[0049] Furthermore, an alarm limit time may be set, for example, the alarm limit time may be 20 seconds, which may be set specifically according to actual conditions, and the embodiment of the present invention is not limited thereto. The duration and the alarm limit time may be judged, for example, if the duration is 28 seconds and the alarm limit time is 20 seconds, an alarm message may be output, the alarm point is the center position P, and the alarm type is mechanical excavation.

[0050] The embodiments of the present invention overcome the bottleneck of further improving the event detection accuracy, efficiency and positioning accuracy caused by the sequential execution of waterfall chart calculation processing and manually designed excitation feature analysis in the traditional optical fiber vibration event detection method, and perform efficient image processing, recognition and event positioning on the distributed optical fiber vibration data, so as to improve the detection accuracy, efficiency and positioning accuracy of distributed optical fiber vibration events.

[0051] In order to better implement the distributed optical fiber vibration event detection method in the embodiment of the present invention, based on the distributed optical fiber vibration event detection method, the embodiment of the present invention also provides a distributed optical fiber vibration event detection device, such as Fig. 9 As shown, the distributed optical fiber vibration event detection device 900 includes: The data acquisition module 901 is used to acquire a fiber vibration data set, and perform parallel processing on the fiber vibration data in the fiber vibration data set according to a preset running filter model to obtain a fiber vibration waterfall diagram; A color map determination module 902 is used to segment and adjust the optical fiber vibration waterfall map to obtain a color map; The target detection module 903 is used to perform target detection on the color image according to the image target detection model to obtain a target frame; A position determination module 904 is used to obtain a center position and a duration according to a target frame; The time judgment module 905 is used to locate the position according to the center position when the duration is greater than the alarm limit time.

[0052] The distributed optical fiber vibration event detection device 900 provided in the above embodiment can implement the technical solution described in the above distributed optical fiber vibration event detection method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above distributed optical fiber vibration event detection method embodiment, which will not be repeated here.

[0053] like Fig.10As shown, the present invention also provides an electronic device 1000. The electronic device 1000 includes a processor 1001, a memory 1002 and a display 1003. Fig.10 Only some components of the electronic device 1000 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0054] In some embodiments, the memory 1002 may be an internal storage unit of the electronic device 1000, such as a hard disk or memory of the electronic device 1000. In other embodiments, the memory 1002 may also be an external storage device of the electronic device 1000, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 1000.

[0055] Furthermore, the memory 1002 may include both an internal storage unit of the electronic device 1000 and an external storage device. The memory 1002 is used to store application software installed in the electronic device 1000 and various data.

[0056] In some embodiments, the processor 1001 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 1002, such as the distributed optical fiber vibration event detection method of the present invention.

[0057] In some embodiments, the display 1003 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 1003 is used to display information of the electronic device 1000 and to display a visual user interface. The components 1001-1003 of the electronic device 1000 communicate with each other via a system bus.

[0058] In some embodiments of the present invention, when the processor 1001 executes the distributed optical fiber vibration event detection program in the memory 1002, the following steps may be implemented: Obtaining an optical fiber vibration data set, and performing parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram; Segment and adjust the optical fiber vibration waterfall diagram to obtain a color diagram; Perform target detection on the color image according to the image target detection model to obtain the target frame; According to the target frame, get the center position and duration; When the duration is greater than the alarm limit time, positioning is performed based on the center position.

[0059] It should be understood that: when the processor 1001 executes the distributed optical fiber vibration event detection program in the memory 1002, in addition to the above functions, other functions may also be implemented, and details may refer to the description of the corresponding method embodiments above.

[0060] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 1000 mentioned, and the electronic device 1000 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1000 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0061] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the distributed optical fiber vibration event detection method provided in the above-mentioned method embodiments can be implemented.

[0062] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0063] The distributed optical fiber vibration event detection method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A distributed optical fiber vibration event detection method, characterized in that: include: Acquire an optical fiber vibration data set, and perform parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram; Segmenting and adjusting the optical fiber vibration waterfall diagram to obtain a color diagram; Performing target detection on the color image according to an image target detection model to obtain a target frame; According to the target frame, a center position and a duration are obtained; When the duration is greater than the alarm limit time, positioning is performed based on the central position.

2. The distributed optical fiber vibration event detection method according to claim 1, characterized in that: The method of performing parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to the preset running filter model to obtain an optical fiber vibration waterfall diagram includes: Performing parallel bandpass filtering on the optical fiber vibration data in the optical fiber vibration data set according to the preset running filter model to obtain filtered optical fiber vibration data; Merging the filtered optical fiber vibration data of each pulse period to obtain merged optical fiber vibration data; The combined optical fiber vibration data is subjected to frequency reduction processing to obtain an optical fiber vibration waterfall diagram.

3. The distributed optical fiber vibration event detection method according to claim 2, characterized in that: The step of performing frequency reduction processing on the combined optical fiber vibration data to obtain an optical fiber vibration waterfall diagram comprises: The maximum value of the optical fiber vibration data of each preset number of cycles in the combined optical fiber vibration data is used as the corresponding vibration value after frequency reduction; Based on all vibration values, the fiber vibration waterfall diagram of the target frequency is obtained.

4. The distributed optical fiber vibration event detection method according to claim 3, characterized in that: The optical fiber vibration waterfall diagram is segmented and adjusted to obtain a color diagram, including: Segmenting the optical fiber vibration waterfall diagram to obtain a segmentation matrix; The segmentation matrix is ​​subjected to contrast adaptive enhancement adjustment according to all the vibration values ​​to obtain a color image.

5. The distributed optical fiber vibration event detection method according to claim 4, characterized in that: The step of performing contrast adaptive enhancement adjustment on the segmentation matrix according to all the vibration values ​​to obtain a color image comprises: Determine the maximum vibration value and the minimum vibration value according to all the vibration values; Obtaining a preset number interval according to the maximum vibration value and the minimum vibration value; According to the preset number intervals, determine the target interval corresponding to each vibration value; According to the calculation formula corresponding to the target interval, the RGB value of each vibration value is obtained; Performing contrast adaptive enhancement adjustment on the segmentation matrix according to the RGB values ​​to obtain a target segmentation matrix; According to the target segmentation matrix, a color map is obtained.

6. The distributed optical fiber vibration event detection method according to claim 5, characterized in that: The signal in the target frame is a mining signal; and obtaining the center position and duration according to the target frame includes: Performing centroid processing on the target frame to obtain the center position of the mining signal; According to the upper and lower boundaries of the target box, the start time and the end time of the mining signal are obtained; The duration of the mining signal is obtained according to the start time and the end time.

7. The distributed optical fiber vibration event detection method according to claim 6, characterized in that: The performing centroid processing on the target frame to obtain the center position of the mining signal includes: According to the color image, determine the upper left corner coordinates, lower right corner coordinates, the starting position of the grayscale image, and the grayscale value corresponding to the RGB value of each pixel of the target frame; The grayscale value of each pixel is accumulated along the vertical axis to obtain the accumulated grayscale values ​​of all vertical axes; the abscissa of the coordinate of the upper left corner is greater than the number of the accumulated grayscale values ​​of all vertical axes that is greater than the abscissa of the coordinate of the lower right corner; The center position of the mining signal is obtained according to the starting position and the accumulated gray values ​​of all the vertical axes.

8. The distributed optical fiber vibration event detection method according to claim 6, characterized in that: The obtaining the duration of the mining signal according to the start time and the end time includes: Obtain a difference value according to the start time and the end time; A duration is obtained according to the difference and the target frequency.

9. The distributed optical fiber vibration event detection method according to claim 5, characterized in that: The calculation formula for each interval is: The first interval is: The calculation formula for the first interval is: The second interval is: The calculation formula for the second interval is: The third interval is: The calculation formula for the third interval is: The fourth interval is: The calculation formula for the fourth interval is: The fifth interval is: The calculation formula for the fifth interval is: In the formula, Indicates the minimum vibration value; Indicates the maximum vibration value; Indicates the currently calculated vibration value.

10. A distributed optical fiber vibration event detection device, characterized in that: include: A data acquisition module, used for acquiring an optical fiber vibration data set, and performing parallel processing on the optical fiber vibration data in the optical fiber vibration data set according to a preset running filter model to obtain an optical fiber vibration waterfall diagram; A color image determination module, used for segmenting and adjusting the optical fiber vibration waterfall image to obtain a color image; A target detection module, used to perform target detection on the color image according to an image target detection model to obtain a target frame; A position determination module, used to obtain a center position and a duration according to the target frame; The time judgment module is used to locate the position according to the center position when the duration is greater than the alarm limit time.

Images