Anchor damage detection method and apparatus, processor, and electronic device

Abstract

Disclosed in the present application are an anchor damage detection method and apparatus, a processor, and an electronic device. The method comprises: acquiring n phase signals to be tested; and performing feature extraction on said n phase signals, so as to obtain p phase signal values corresponding to each phase signal; constructing an initially empty target matrix, the size of the matrix being m×n; sequentially filling the p phase signal values corresponding to each phase signal into the target matrix; performing convolution processing on the target matrix in a convolution detection state to obtain a first convolution result, and, on the basis of the first convolution result, determining a first anchor damage detection result of the n phase signals under first time information; and removing the phase signal values already filled in the first row in the target matrix, moving the phase signal values already filled in the second row to the mth row in the target matrix to the first row to the (m-1)th row, and recovering the target state of the target matrix from the convolution detection state to a signal filling state. The present application solves the problem of low detection accuracy of anchor damage in related technologies.

Description

Anchor damage detection method, device, processor and electronic equipment

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on December 25, 2023, with application number 202311809667.1 and application name “Anchor Damage Detection Method, Device, Processor and Electronic Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of optical cable detection technology, and in particular to an anchor damage detection method, device, processor, and electronic device. Background Art

[0003] Anchor intrusion occurs when submarine anchor chains or other anchoring equipment accidentally come into contact with optical cables, potentially causing damage, breakage, or other problems. This can lead not only to expensive repair and replacement costs but also to data interruptions, impacting the availability and reliability of communications networks.

[0004] Currently, there are some technologies for monitoring and preventing submarine cable anchor intrusion, such as using underwater sensors and cameras to monitor activity around the cables. However, this approach can be limited by underwater visibility and harsh ocean conditions, leading to issues with the accuracy of detection results.

[0005] That is, there is a technical problem in the related art that the accuracy of anchor damage detection is low.

[0006] Summary of the Invention

[0007] The main purpose of this application is to provide a method, device, processor and electronic device for detecting anchor damage, so as to solve the problem of low accuracy of anchor damage detection in related technologies and improve the accuracy of anchor damage detection.

[0008] In a first aspect, the present application discloses a method for detecting anchor damage, comprising:

[0009] Obtain n phase signals to be detected, where n is a positive integer;

[0010] Perform feature extraction on n phase signals to obtain p phase signal values ​​corresponding to each phase signal;

[0011] Constructing an initially empty target matrix with a matrix size of m times n, where m is used to indicate the first time information selected from all time information corresponding to p phase signal values, m and p are positive integers and m is less than p;

[0012] sequentially filling the target matrix with p phase signal values ​​corresponding to each phase signal, wherein, if there is no region in the target matrix that is not filled with the phase signal value, determining the target state of the target matrix as a convolution detection state;

[0013] Performing convolution processing on a target matrix of a convolution detection state to obtain a first convolution result, and determining a first anchor damage detection result of the n phase signals under first time information based on the first convolution result;

[0014] The phase signal values ​​filled in the first row of the target matrix are removed, the phase signal values ​​filled in the second to m-th rows of the target matrix are moved to the first to m-1-th rows, and the target state of the target matrix is ​​restored from the convolution detection state to the signal filling state.

[0015] Based on the above technical content, by constructing a target matrix, a first-in-first-out detection order is adopted to perform multiple convolution detection processes on the target number of phase signal values ​​in p phase signal values ​​in turn. Among them, after each convolution detection process is performed to obtain the anchor detection result of the phase signal of the current time information, the earliest row of signal value data filled in the target matrix is ​​eliminated, and the signal value data of the subsequent rows are moved forward to allow a new row of signal value data to be further filled in, and convolution detection processing of the new overall signal value data is performed to obtain the anchor detection result of the phase signal of the new time information. This not only achieves the purpose of autonomously controlling the recognition range and customizing the duration of the anchor event, but also can realize multiple and global detection of the anchor event under different time information based on certain signal data, thereby achieving the technical effect of improving the accuracy of anchor detection.

[0016] In one implementation, a convolution process is performed on a target matrix of a convolution detection state to obtain a first convolution result, and anchor detection results of n phase signals are determined based on the first convolution result, including: using a two-dimensional convolution kernel to perform a two-dimensional convolution calculation on the target matrix to obtain a first calculation matrix with a matrix size of i times j; elements in the first calculation matrix whose values ​​are greater than a first preset threshold are recorded as 1, and elements in the convolution matrix whose values ​​are not greater than the first preset threshold are recorded as 0 to obtain a second calculation matrix; elements included in the second calculation matrix are added column by column to obtain a third calculation matrix with a matrix size of 1 times j; based on the values ​​of the j elements included in the third calculation matrix and the second preset threshold, the values ​​of the j elements are respectively judged to obtain a first anchor detection result.

[0017] Furthermore, by using the two-dimensional convolution method to judge the seabed anchor damage events, it is possible to realize the functions of autonomously controlling the recognition range, customizing the duration and vibration intensity of the anchor damage events, and realizing multiple and global detection of anchor damage events under different time information based on certain signal data, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0018] In one implementation, based on the values ​​of the j elements included in the third calculation matrix and the second preset threshold, the values ​​of the j elements are determined separately, including: determining the current element from the j elements in turn; when the value of the current element is greater than the second preset threshold multiplied by i, determining that there is an anchor risk in the optical fiber area of ​​the phase signal corresponding to the current element.

[0019] Furthermore, the values ​​of the j elements included in the third calculation matrix and the second preset threshold are used to judge the values ​​of the j elements respectively to obtain the first anchor damage detection result, thereby realizing the functions of autonomously controlling the recognition range, customizing the duration and vibration intensity of anchor damage events, and being able to identify and locate anchor damage events even in the absence of actual anchor damage data, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0020] In one implementation, performing a two-dimensional convolution calculation on a target matrix using a two-dimensional convolution kernel includes: obtaining a two-dimensional convolution kernel having a matrix size of k times k, where k is an odd number and is not greater than m or n; performing row padding and column padding on the target matrix to obtain a padded target matrix having a matrix size of k times k; and performing a product process on the padded target matrix using the two-dimensional convolution kernel.

[0021] Furthermore, by performing row filling and column filling processing on the target matrix, it is ensured that the input and output have the same height and width, thereby improving the accuracy of subsequent data processing, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0022] In one implementation, after restoring the target state of the target matrix from the convolution detection state to the signal filling state, the method also includes: sequentially determining n phase signal values ​​from multiple phase signal values ​​that are not filled into the target matrix among the p phase signal values; sequentially filling the n phase signal values ​​into the m-th row area of ​​the target matrix; after all the n phase signal values ​​are filled into the target matrix, adjusting the target state from the signal filling state to the convolution detection state; performing a second convolution processing on the target matrix in the convolution detection state to obtain a second convolution result, and determining a second anchor detection result of the n phase signals under the second time information based on the second convolution result.

[0023] Furthermore, by constructing a target matrix, a first-in-first-out detection order is adopted to perform multiple convolution detection processes on the target number of phase signal values ​​in the p phase signal values ​​in turn. After each convolution detection process is performed to obtain the anchor detection result of the phase signal of the current time information, the earliest row of signal value data filled in the target matrix is ​​eliminated, and the signal value data of the subsequent rows are shifted forward to allow a new row of signal value data to be further filled in, and convolution detection process of the new overall signal value data is performed to obtain the anchor detection result of the phase signal of the new time information, thereby achieving the technical effect of improving the accuracy of anchor detection.

[0024] In one implementation, feature extraction is performed on n phase signals to obtain p phase signal values ​​corresponding to each phase signal, including: performing feature variance extraction processing on the n phase signals according to a first period to obtain phase feature values ​​corresponding to multiple first periods; and accumulating the phase feature values ​​corresponding to multiple first periods according to a second period to obtain p phase signal values ​​corresponding to each phase signal, wherein a second period includes at least two first periods, and different second periods do not overlap with each other.

[0025] Furthermore, through preprocessing such as variance processing, the object to be detected is obtained, which can cover the global signal information within a period of time, thereby achieving the purpose of improving the accuracy of subsequent data processing from the source of data processing, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0026] In one implementation, obtaining n phase signals to be detected includes: using a laser light source to emit laser light into a coupler, wherein the coupler inputs a first proportion of the laser light intensity detection light into an acousto-optic modulator to obtain a pulse signal, and the acousto-optic modulator is used to convert the laser light into a pulse signal; using an erbium-doped fiber amplifier to amplify the pulse signal and then input it into an optical fiber to obtain Rayleigh scattering of the optical fiber, and determining two coherent lights based on the Rayleigh scattering and the second proportion of intrinsic light separated by the coupler; inputting the two coherent lights into a balanced detector to obtain a target electrical signal, wherein a smoothing detector is used to convert the optical signal into an electrical signal; and inputting the target electrical signal into an acquisition card to obtain n phase signals output by the acquisition card.

[0027] Furthermore, the entire process realizes the conversion and extraction from optical signals to electrical signals and then to digital phase signals through the cooperation of components such as laser light source, coupler, acousto-optic modulator, erbium-doped fiber amplifier, optical fiber, balanced detector and acquisition card, providing basic data for subsequent anchor damage detection, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0028] In a second aspect, the present application discloses an anchor damage detection device, comprising:

[0029] An acquisition unit is used to acquire n phase signals to be detected, wherein n is a positive integer; an extraction unit is used to perform feature extraction on the n phase signals to obtain p phase signal values ​​corresponding to each phase signal; a construction unit is used to construct an initially empty target matrix with a matrix size of m times n, wherein m is used to indicate the first time information selected from all time information corresponding to the p phase signal values, m and p are positive integers and m is less than p; a filling unit is used to fill the p phase signal values ​​corresponding to each phase signal into the target matrix in sequence, wherein there is no unoccupied phase signal in the target matrix. When the area of ​​the phase signal value is filled, the target state of the target matrix is ​​determined to be a convolution detection state; a convolution unit is used to perform convolution processing on the target matrix in the convolution detection state to obtain a first convolution result, and determine the first anchor detection result of the n phase signals under the first time information based on the first convolution result; a elimination unit is used to eliminate the phase signal values ​​filled in the first row of the target matrix, move the phase signal values ​​filled in the second to m-th rows of the target matrix to the first to m-1-th rows, and restore the target state of the target matrix from the convolution detection state to the signal filling state.

[0030] In a third aspect, the present application discloses an anchoring damage detection processor, which is used to run a program, wherein the anchoring damage detection method is executed when the program is running.

[0031] In a fourth aspect, the present application discloses an electronic device for detecting anchor damage, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned anchor damage detection method is implemented.

[0032] In a fifth aspect, the present application discloses a computer-readable storage medium, in which a program is stored. When the program is executed by a processor, the above-mentioned anchor damage detection method is implemented.

[0033] In a sixth aspect, the present application discloses a computer program product, including a computer program, which implements the above-mentioned anchor damage detection method when executed by a processor.

[0034] In combination with the above-mentioned technical solution, the anchor detection method, device, processor and electronic device provided by the present application, through the constructed target matrix, adopt a first-in-first-out detection order, and perform multiple convolution detection processing on the target number of phase signal values ​​in p phase signal values ​​in turn. Among them, after each convolution detection processing is performed to obtain the anchor detection result of the phase signal of the current time information, the earliest row of signal value data filled in the target matrix is ​​eliminated, and the signal value data of the subsequent rows are moved forward to allow a new row of signal value data to be further filled in, and convolution detection processing of the new overall signal value data is performed to obtain the anchor detection result of the phase signal of the new time information. It not only achieves the purpose of autonomous control of the recognition range and customized anchor event duration, but also can realize multiple and global detection of anchor events under different time information based on certain signal data, thereby achieving the technical effect of improving the accuracy of anchor detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] FIG1 is a flow chart of an anchor damage detection method according to an embodiment of the present application;

[0036] FIG2 is a schematic diagram of an anchor damage detection method provided according to an embodiment of the present application;

[0037] FIG3 is a schematic diagram of the original phase characteristics of the entire optical cable provided according to an embodiment of the present application;

[0038] FIG4 is a schematic diagram of an O1 matrix of vibration positions when the convolution kernel is (3,3) according to an embodiment of the present application;

[0039] FIG5 is a schematic diagram of an O1 matrix of vibration positions when the convolution kernel is (5,5) according to an embodiment of the present application;

[0040] FIG6 is a schematic diagram of data obtained by performing two-dimensional convolution on the original phase features according to an embodiment of the present application;

[0041] 7 is a schematic diagram of the original phase characteristics of an optical cable subjected to a single-point anchor damage test according to an embodiment of the present application;

[0042] FIG8 is a schematic diagram of an anchor damage detection device provided according to an embodiment of the present application;

[0043] FIG9 is a schematic diagram of an electronic device for detecting anchor damage according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0045] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0046] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display and analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0048] The present application is described below in conjunction with preferred implementation steps. FIG1 is a flow chart of an anchor damage detection method provided according to an embodiment of the present application. As shown in FIG1 , the method includes the following steps:

[0049] Step S101, obtaining n phase signals to be detected, where n is a positive integer;

[0050] Step S102, performing feature extraction on the n phase signals to obtain p phase signal values ​​corresponding to each phase signal;

[0051] Step S103, constructing an initially empty target matrix with a matrix size of m times n, where m is used to indicate the first time information selected from all the time information corresponding to the p phase signal values, m and p are positive integers and m is less than p;

[0052] Step S104: sequentially filling the target matrix with the p phase signal values ​​corresponding to the respective phase signals, wherein, if there is no region in the target matrix that is not filled with the phase signal value, the target state of the target matrix is ​​determined to be a convolution detection state;

[0053] Step S105, performing convolution processing on the target matrix of the convolution detection state to obtain a first convolution result, and determining a first anchor damage detection result of the n phase signals under the first time information based on the first convolution result;

[0054] Step S106: remove the phase signal values ​​filled in the first row of the target matrix, move the phase signal values ​​filled in the second to m-th rows of the target matrix to the first to m-1-th rows, and restore the target state of the target matrix from the convolution detection state to the signal filling state.

[0055] Optionally, in this embodiment, the above-described anchor damage detection method can be applied, but is not limited to, to online submarine anchor damage assessment scenarios. With the rapid development of the internet, submarine optical cable networks have become a key infrastructure for global information transmission. These cable networks play a vital role in connecting international data centers, communication systems, and cloud computing services. However, the installation and maintenance of submarine optical cables in marine environments face a number of challenges, one of which is the threat of submarine anchor damage.

[0056] Traditionally, anchor intrusion occurs when submarine anchor chains or other anchoring equipment accidentally come into contact with optical cables, potentially causing damage, breakage, or other problems. This can not only lead to expensive repair and replacement costs, but can also disrupt data transmission, impacting the availability and reliability of communication networks.

[0057] Currently, several technologies exist for monitoring and preventing anchor intrusion in submarine optical cables, including but not limited to: 1) Anchor detection systems: Some methods use underwater sensors and cameras to monitor activity around the cable. However, these systems can be limited by underwater visibility and harsh ocean conditions. 2) Physical protection: Other methods employ physical protection measures, such as armor and protective layers, to improve the cable's resistance to anchor intrusion. However, this increases cost and complexity.

[0058] At the same time, due to the lack of anchor damage data, according to statistics, an anchor damage incident occurs only once every 30,000 hours on average. Therefore, it is difficult to determine anchor damage in the absence of data.

[0059] For the above problem, the above-mentioned anchor detection method is used. By constructing a target matrix, a first-in-first-out detection order is adopted to perform multiple convolution detection processes on the target number of phase signal values ​​in the p phase signal values ​​in turn. After each convolution detection process is performed to obtain the anchor detection result of the phase signal of the current time information, the earliest row of signal value data filled in the target matrix is ​​eliminated, and the signal value data of the subsequent rows are moved forward to allow a new row of signal value data to be further filled in, and convolution detection process of the new overall signal value data is performed to obtain the anchor detection result of the phase signal of the new time information. This not only achieves the purpose of autonomously controlling the recognition range and customizing the duration of the anchor event, but also can realize multiple and global detection of the anchor event under different time information based on certain signal data, thereby achieving the beneficial effect of improving the accuracy of anchor detection.

[0060] Optionally, in this embodiment, obtaining n phase signals to be detected can be achieved by, but is not limited to, including a distributed optical fiber disturbance monitoring system. The DAS uses a laser light source to emit laser light into a coupler. The coupler inputs 90% of the laser light intensity detection light into an acousto-optic modulator. The acousto-optic modulator converts the laser light into a pulse signal, which is amplified by an erbium-doped fiber amplifier and then input into the optical fiber. The Rayleigh scattering of the optical fiber and the other 10% of the intrinsic light separated by the coupler enter the coupler and output two coherent lights that enter a balanced detector, so that the optical signal is converted into an electrical signal, which is finally input into the acquisition card to obtain a phase signal.

[0061] Optionally, in this embodiment, feature extraction may be, but is not limited to, taking into account the characteristics of the acquisition card, outputting a phase signal every 0.1 seconds, and thus performing variance processing on the phase signal every 0.1 seconds, using the following formula:

[0062] Where N is the number of phase signals in 0.1 seconds, x i is the value of each phase signal, and μ is the phase mean value of 0.1 seconds. The 0.1 second phase signal is accumulated to 1 second and summed to obtain the 1 second phase characteristic signal value. The 1 second phase characteristic signal value is determined as a phase signal value corresponding to the above phase signal.

[0063] Optionally, in this embodiment, different phase signal values ​​among the p phase signal values ​​correspond to different time information, wherein the phase signal value obtained by feature extraction / variance calculation first corresponds to the earlier time information, and the order of filling in the target matrix is ​​also earlier.

[0064] Optionally, in this embodiment, when the target matrix has been filled with m times n phase signal values, the target state of the target matrix is ​​determined to be the convolution detection state. It will be understood that when there are areas in the target matrix that have not been filled with phase signal values, the target state of the target matrix is ​​determined to be the signal filling state.

[0065] Optionally, in this embodiment, when the target state of the target matrix is ​​a convolution detection state, convolution processing is performed on the target matrix to obtain a first convolution result indicating a first anchor detection result of n phase signals under the first time information.

[0066] It should be noted that when the phase signal values ​​included in the target matrix are different, the time information indicated by the anchor detection result obtained by the subsequent convolution processing is also different, wherein the time information indicated by the anchor detection result corresponds to the phase signal value included in the target matrix.

[0067] Optionally, in this embodiment, after obtaining the first anchor detection result under the above-mentioned first time information, the phase signal values ​​filled in the first row of the target matrix are eliminated, the phase signal values ​​filled in the second to m-th rows of the target matrix are moved to the first to m-1-th rows, and the target state of the target matrix is ​​restored from the convolution detection state to the signal filling state.

[0068] It should be noted that after the target state of the target matrix is ​​restored from the convolution detection state to the signal filling state, n phase signal values ​​are determined in sequence from the multiple phase signal values ​​that are not filled into the target matrix among the p phase signal values; the n phase signal values ​​are filled into the m-th row area of ​​the target matrix in sequence; after all the n phase signal values ​​are filled into the target matrix, the target state is adjusted from the signal filling state to the convolution detection state; a second convolution processing is performed on the target matrix in the convolution detection state to obtain a second convolution result, and a second anchor detection result of the n phase signals under the second time information is determined based on the second convolution result.

[0069] To further illustrate, the phase signal values ​​are input into the empty matrix A(m,n) in sequence. When the number of phase characteristic signals exceeds m and becomes m+1, the original first signal is deleted from the matrix A(m,n), and the original second to mth data are padded forward to become the first to m-1th data, and the subsequent m+1 data becomes the mth data. The same applies to subsequent new signals entering.

[0070] Through the embodiment provided by the present application, a target matrix is ​​constructed and a first-in-first-out detection order is adopted to perform multiple convolution detection processes on the target number of phase signal values ​​in p phase signal values ​​in turn. After each convolution detection process is performed to obtain the anchor detection result of the phase signal of the current time information, the earliest row of signal value data filled in the target matrix is ​​eliminated, and the signal value data of the subsequent rows are moved forward to allow a new row of signal value data to be further filled in, and convolution detection process of the new overall signal value data is performed to obtain the anchor detection result of the phase signal of the new time information. This not only achieves the purpose of autonomously controlling the recognition range and customizing the duration of the anchor event, but also can realize multiple and global detection of the anchor event under different time information based on certain signal data, thereby achieving the technical effect of improving the accuracy of anchor detection.

[0071] As an optional solution, performing convolution processing on the target matrix of the convolution detection state to obtain a first convolution result, and determining the anchor damage detection results of the n phase signals based on the first convolution result, including:

[0072] S1, use the two-dimensional convolution kernel to perform a two-dimensional convolution calculation on the target matrix to obtain the first calculation matrix with a matrix size of i times j;

[0073] S2, record the elements in the first calculation matrix whose values ​​are greater than the first preset threshold as 1, and record the elements in the convolution matrix whose values ​​are not greater than the first preset threshold as 0, to obtain a second calculation matrix;

[0074] S3, adding the elements included in the second calculation matrix by column to obtain a third calculation matrix with a matrix size of 1 times j;

[0075] S4 , based on the values ​​of the j elements included in the third calculation matrix and the second preset threshold, respectively determine the values ​​of the j elements to obtain a first anchor damage detection result.

[0076] Optionally, in this embodiment, the target matrix may be, but is not limited to, A(m,n), and the two-dimensional convolution kernel may be, but is not limited to, K(p,q). Whenever a new phase signal value enters a row in the matrix A(m,n), a two-dimensional convolution operation is performed on the matrix A(m,n) to obtain the first calculation matrix O(i,j). The operation process is as follows:

[0077] Where O(i,j) is the first calculation matrix of the output, A(i+p,j+q)K(p,q) represents the multiplication of an element A(i+p,j+q) of the input matrix and an element K(p,q) of the kernel matrix. and Accumulate in the horizontal and vertical directions of the matrix respectively. When performing convolution, the matrix A(m,n) needs to be padded with P h Row and P w Columns to ensure that the input and output have the same height and width. Generally set P h =p-1,P w =q-1, the convolution kernel uses odd height and width to ensure that the number of padding at both ends is equal.

[0078] Optionally, in this embodiment, for the first calculation matrix O(i, j) obtained after convolution, a threshold a is set and compared with the threshold. Elements in the first calculation matrix greater than the threshold a are recorded as 1, and elements less than the threshold a are recorded as 0, and the new second calculation matrix O2(i, j) is obtained by storing the matrix.

[0079] For the second calculation matrix O2(i,j) containing 01, it is added column by column to become the third calculation matrix O2'(1,j), where each value of j in the third calculation matrix O2'(1,j) is the sum of each column in the 01 matrix O2(i,j).

[0080] It should be noted that when each row of phase signal values ​​is input into the matrix A(m,n), the one-dimensional convolution kernel K(1,q) can be used to convolve the single phase signal value to obtain O'(1,j), and then each convolved phase feature signal O'(1,j) is input into the matrix to obtain the matrix O(i,j). The effect is the same as using the two-dimensional convolution kernel K(p,q) to directly perform a two-dimensional convolution on the entire matrix. The one-dimensional convolution formula is as follows:

[0081] Through the embodiments provided in this application, a two-dimensional convolution method is used to determine seabed anchor damage events, which can realize the functions of autonomously controlling the recognition range, customizing the duration and vibration intensity of anchor damage events, and realizing multiple and global detection of anchor damage events under different time information based on certain signal data, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0082] As an optional solution, based on the values ​​of the j elements included in the third calculation matrix and the second preset threshold, the values ​​of the j elements are determined separately, including:

[0083] S1, determine the current element from j elements in turn;

[0084] S2: When the value of the current element is greater than the second preset threshold multiplied by i, it is determined that the optical fiber region of the phase signal corresponding to the current element has an anchor risk.

[0085] Optionally, in this embodiment, for the third calculation matrix O2'(1,j), the number of j is the number of monitoring points, and its value is the sum of each column in the second calculation matrix O2(i,j). A second preset threshold b∈(0,1) is set, and each j value is judged. When j>b*i, it means that the signal at this point exceeds the threshold by b*100%, and it is judged as an anchor alarm signal. The index signal of the point is then restored to its true length to achieve the effect of the anchor alarm.

[0086] Through the embodiment provided by the present application, the values ​​of the j elements included in the third calculation matrix and the second preset threshold are used to judge the values ​​of the j elements respectively, and the first anchor damage detection result is obtained, thereby realizing the functions of autonomously controlling the recognition range, customizing the duration and vibration intensity of the anchor damage event, and realizing the identification and positioning of the anchor damage event even in the absence of actual anchor damage data, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0087] As an optional solution, a two-dimensional convolution kernel is used to perform a two-dimensional convolution calculation on the target matrix, including:

[0088] S1, obtain a two-dimensional convolution kernel with a matrix size of k times k, where k is an odd number and k is not greater than m and not greater than n;

[0089] S2, performing row filling and column filling processing on the target matrix to obtain a filled target matrix with a matrix size of k times k;

[0090] S3, uses the two-dimensional convolution kernel to perform product processing on the padded target matrix.

[0091] Optionally, in this embodiment, the two-dimensional convolution kernel may be, but is not limited to, a matrix size of k times k, where k is an odd number and k is not greater than m and not greater than n.

[0092] Optionally, in this embodiment, when performing convolution, it is necessary to perform row filling processing on the matrix A(m,n) to achieve filling P h The purpose of the row, and the column filling process to achieve the filling P w The purpose of the columns is to ensure that the input and output have the same height and width.

[0093] Through the embodiments provided in this application, by performing row filling and column filling processing on the target matrix, it is ensured that the input and output have the same height and width, thereby improving the accuracy of subsequent data processing, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0094] As an optional solution, after restoring the target state of the target matrix from the convolution detection state to the signal filling state, the method further includes:

[0095] S1, sequentially determining n phase signal values ​​from a plurality of phase signal values ​​that are not filled into the target matrix among the p phase signal values;

[0096] S2, fill the n phase signal values ​​into the mth row area of ​​the target matrix in sequence;

[0097] S3, after all n phase signal values ​​are filled into the target matrix, the target state is adjusted from the signal filling state to the convolution detection state;

[0098] S4, performing a second convolution process on the target matrix of the convolution detection state to obtain a second convolution result, and determining a second anchor detection result of the n phase signals under the second time information based on the second convolution result.

[0099] Optionally, in this embodiment, when the phase signal values ​​included in the target matrix are different, the time information indicated by the anchor detection result obtained by the subsequent convolution processing is also different, wherein the time information indicated by the anchor detection result corresponds to the phase signal value included in the target matrix.

[0100] Optionally, in this embodiment, after obtaining the anchor detection result corresponding to the previous time information, the phase signal values ​​of the first row included in the target matrix are removed, and the phase signal values ​​of the other rows are shifted forward by one row to obtain an area of ​​the last row to be filled. The unfilled phase signal values ​​are sequentially filled in the area of ​​the last row to be filled. After the filling is completed, the target matrix is ​​determined to enter a convolution detection state. The same processing method as the above convolution processing is performed to obtain the anchor detection result of the new time information corresponding to the new target matrix.

[0101] Through the embodiment provided by the present application, a target matrix is ​​constructed and a first-in-first-out detection order is adopted to perform multiple convolution detection processes on a target number of phase signal values ​​in p phase signal values ​​in turn. After each convolution detection process is performed to obtain the anchor detection result of the phase signal of the current time information, the earliest row of signal value data filled in the target matrix is ​​eliminated, and the signal value data of subsequent rows are shifted forward so that a new row of signal value data can be further filled in, and convolution detection process of the new overall signal value data is performed to obtain the anchor detection result of the phase signal of the new time information, thereby achieving the technical effect of improving the accuracy of anchor detection.

[0102] As an optional solution, feature extraction is performed on the n phase signals to obtain p phase signal values ​​corresponding to each phase signal, including:

[0103] S1, according to the first period, performing feature variance extraction processing on n phase signals respectively to obtain multiple phase feature values ​​corresponding to the first period;

[0104] S2, according to the second period, accumulate the phase characteristic values ​​corresponding to multiple first periods to obtain p phase signal values ​​corresponding to each phase signal, wherein one second period includes at least two first periods, and different second periods do not overlap with each other.

[0105] Optionally, in this embodiment, the first period may be, but is not limited to, every 0.1 seconds, and the second period may be, but is not limited to, every 1 second. It is understood that the first period and the second period may also be, but are not limited to, other time values, and this embodiment does not impose any specific restrictions on the specific time values.

[0106] Optionally, in this embodiment, considering the characteristics of the acquisition card, a phase signal is output every 0.1 second, so the first period is set to 0.1 second, and the phase signal every 0.1 second is processed for variance, and the formula is as follows:

[0107] Where N is the number of phase signals in 0.1 seconds, x i is the value of each phase signal, and μ is the phase mean value of 0.1 seconds.

[0108] Furthermore, the second cycle is set to 1 second, the phase signal of 0.1 seconds is accumulated to 1 second, and the sum is performed to obtain the phase characteristic signal value of 1 second, and the phase characteristic signal value of 1 second is determined as a phase signal value corresponding to the above phase signal.

[0109] Through the embodiments provided in this application, through preprocessing such as variance processing, the object to be detected is obtained, which can cover global signal information within a period of time, thereby achieving the purpose of improving the accuracy of subsequent data processing from the source of data processing, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0110] As an optional solution, obtaining n phase signals to be detected includes:

[0111] S1, using a laser light source to emit laser light into a coupler, wherein the coupler inputs a light intensity detection light of a first proportion of the laser light into an acousto-optic modulator to obtain a pulse signal, and the acousto-optic modulator is used to convert the laser light into a pulse signal;

[0112] S2, using an erbium-doped fiber amplifier to amplify the pulse signal and then input it into the optical fiber to obtain Rayleigh scattering of the optical fiber, and determining two coherent lights based on the Rayleigh scattering and the second proportion of the intrinsic light separated by the coupler;

[0113] S3, inputting the two coherent lights into a balanced detector to obtain a target electrical signal, wherein a smoothing detector is used to convert the optical signal into an electrical signal;

[0114] S4, inputting the target electrical signal into the acquisition card to obtain n phase signals output by the acquisition card.

[0115] Optionally, in this embodiment, obtaining n phase signals to be detected can be achieved by, but is not limited to, including a distributed optical fiber disturbance monitoring system. The DAS uses a laser light source to emit laser light into a coupler. The coupler inputs 90% of the laser light intensity detection light into an acousto-optic modulator. The acousto-optic modulator converts the laser light into a pulse signal, which is amplified by an erbium-doped fiber amplifier and then input into the optical fiber. The Rayleigh scattering of the optical fiber and the other 10% of the intrinsic light separated by the coupler enter the coupler and output two coherent lights that enter a balanced detector, so that the optical signal is converted into an electrical signal, which is finally input into the acquisition card to obtain a phase signal.

[0116] Through the embodiments provided in this application, the entire process realizes the conversion and extraction from optical signals to electrical signals and then to digital phase signals through the cooperation of components such as laser light sources, couplers, acousto-optic modulators, erbium-doped fiber amplifiers, optical fibers, balanced detectors and acquisition cards, providing basic data for subsequent anchor damage detection, thereby achieving the technical effect of improving the accuracy of anchor damage detection.

[0117] As an optional solution, the above-mentioned anchor damage detection method is applied to an online judgment scenario of seabed anchor damage based on a distributed fiber optic disturbance monitoring system. Based on the long-distance and long-term characteristics of anchor damage events, the anchor damage events and their locations are identified, and accurate and effective alarms are provided.

[0118] Specifically, a distributed fiber optic disturbance monitoring system uses a laser light source to emit laser light into a coupler. The coupler inputs 90% of the laser light intensity detection light into an acousto-optic modulator. The acousto-optic modulator converts the laser light into a pulse signal, which is amplified by an erbium-doped fiber amplifier and input into the optical fiber. The Rayleigh scattering of the optical fiber and the other 10% of the intrinsic light separated by the coupler enter the coupler and output two coherent lights into a balanced detector, converting the optical signal into an electrical signal, which is finally input into the acquisition card to obtain the phase and envelope signals.

[0119] Furthermore, the specific steps of extracting features from the phase signal obtained by the acquisition card and processing it to realize the identification of anchor intrusion events are shown in Figure 2. The complete steps are as follows:

[0120] Step 1: Due to the characteristics of the acquisition card, the phase signal is output every 0.1 seconds. Therefore, the variance of the phase signal every 0.1 seconds is calculated. The formula is as follows:

[0121] Where N is the number of phase signals in 0.1 seconds, x i is the value of each phase signal, and μ is the phase mean value of 0.1 seconds.

[0122] Step 2: Accumulate the 0.1 second phase signal to 1 second and sum it to obtain the 1 second phase characteristic signal.

[0123] Step 3: Create an empty matrix A(m,n), where m is the number of rows and is a custom parameter, representing the selection of m seconds of data, and n is the number of fiber sampling points in the DAS.

[0124] Step 4: Input the 1-second phase characteristic signals in step 2 into the empty matrix A(m,n) in sequence. When the number of phase characteristic signals exceeds m and becomes m+1, the original first signal is deleted from the matrix A(m,n), and the original second to mth data are filled forward to become the first to m-1th data, and the subsequent m+1th data becomes the mth data. The same applies to subsequent new signals entering.

[0125] Step 5: Determine the two-dimensional convolution kernel K(p,q). Whenever the matrix A(m,n) enters a new phase feature, calculate a two-dimensional convolution operation on the matrix A(m,n). The operation process is as follows:

[0126] Where O(,i)j is the output matrix, A(i+p,j+q)K(p,q) represents the multiplication of an element A(i+p,j+q) of the input matrix and an element K(p,q) of the kernel matrix. and Accumulate in the horizontal and vertical directions of the matrix respectively. When performing convolution, the matrix A(m,n) needs to be padded with P h Row and P w Columns to ensure that the input and output have the same height and width. Generally set P h =p-1,P w =q-1, the convolution kernel uses odd height and width to ensure that the number of padding at both ends is equal.

[0127] Step 6: For the convolved matrix O(i,j), set a threshold a and compare it with the threshold. If the value is greater than the threshold a, the value of the matrix O(i,j) is recorded as 1, and if it is less than the threshold a, it is recorded as 0 and stored in the new matrix O2(i,j).

[0128] Step 7: For the 01 matrix O2(i,j), add it column by column to become O2'(1,j). Since the matrix A(m,n) and the matrix O2(i,j) have the same dimension, O2'(1,j) can also be written as O2'(1,n), where each value of n in O2'(1,n) is the sum of each column in the 01 matrix O2(i,j).

[0129] Step 8: For the matrix O2'(1,n), the number of n is the number of monitoring points, and its value is the sum of each column in the 01 matrix O2(i,j). Set the ratio b∈(0,1) and make a judgment on each n value. When n>b*i, it means that the signal at this point has b*100% exceeded the threshold, and it is judged as an anchor alarm signal. Then the index signal of this point is restored to its true length to achieve the effect of anchor alarm.

[0130] To further illustrate, after the acquisition card obtains the phase signal, the characteristic variance of the phase signal is extracted every 0.1 second, and the sum is calculated after accumulating to 1 second. In this embodiment, as shown in Figure 3, there are 1689 sampling points, so 1689 phase characteristic signals will be obtained every second.

[0131] Construct an empty matrix A(m,n), where m is a custom parameter and is defined as 10 in this embodiment, representing the selection of 10 seconds of data. n is the number of optical fiber sampling points in the distributed optical fiber disturbance monitoring system and is 1689 in this embodiment. Therefore, the constructed matrix A(m,n) is specifically A(10,1689).

[0132] The above-mentioned phase characteristic signals for each second are input into the empty matrix A(10,1689) in sequence. When the cumulative number reaches 11 seconds, the number of phase characteristic signals exceeds 10 and becomes 11. The original 1st signal is deleted from the matrix A(10,1689), and the original 2nd to 10th data are filled in and become 1st to 9th. The subsequent 11th data becomes 10th, and the same applies to subsequent new signals entering.

[0133] Determine the two-dimensional convolution kernel K(p,q). In this embodiment, to ensure that the number of paddings at both ends of the matrix is ​​equal during the convolution operation, odd numbers are selected as the height and width of the convolution kernel. The two-dimensional convolution kernels are determined to be (3,3) and (5,5), respectively. Whenever the matrix A(10,1689) enters a new phase feature, a two-dimensional convolution operation is calculated for the matrix A(10,1689). The operation process is as follows:

[0134] For the convolved matrix O(i,j), which is O(10,1689) in this example, a threshold a is set and compared with the threshold. Values ​​greater than the threshold a are recorded as 1 in the matrix O(10,1689), and values ​​less than the threshold a are recorded as 0. The matrix is ​​then stored in a new matrix O2(10,1689). In this example, the matrix threshold a is set to 500. The 01 matrices of the vibration points in the matrix O2(10,1689) with the convolution kernels (3,3) and (5,5) are shown in Figures 4 and 5, respectively.

[0135] For the 01 matrix O2(10,1689), adding them by columns changes it to O2'(1,1689), where each value in O2'(1,1689) is the sum of each column in the 01 matrix O2(10,1689).

[0136] For the matrix O2'(1,1689), the number of monitoring points in this example is 1689, and its value is the sum of each column in the 01 matrix O2(10,1689). Set the ratio b∈(0,1) and judge each value of the 1689 monitoring points. When n>b*i, it means that the signal at this point has b*100% exceeded the threshold, and it is judged as an anchor alarm signal. Then, the index signal of this point is restored to its true length, and the effect of anchor alarm can be achieved. In this example, b is taken as 0.8 means that when the signal exceeds the convolution threshold a=500 for 8 seconds within 10 seconds, an alarm is generated. In Figure 4, the sum of the 01 matrices of the 1631st, 1632nd, and 1633rd points is 8, which exceeds the threshold. In Figure 5, the sum of the 01 matrices of the 1630th, 1631st, 1632nd, 1633rd, and 1634th points is 8, which exceeds the threshold. It can be seen that different convolution kernels have different effects on the sensitivity of anchor damage events, realizing the sensitivity of anchor damage identification controlled by the convolution kernel.

[0137] It should be noted that the anchor damage detection effect obtained by using the above-mentioned two-dimensional convolution calculation is shown in Figure 6, and the anchor damage detection effect obtained without using the above-mentioned two-dimensional convolution calculation is shown in Figure 7. Among them, the anchor damage detection effect obtained by using the above-mentioned two-dimensional convolution calculation is more complete, comprehensive and accurate.

[0138] It should be noted that when performing a two-dimensional convolution operation on the matrix A(m,n), there is an alternative solution: when each phase characteristic signal is input into the matrix A(m,n), you can first use the one-dimensional convolution kernel K(1,q) to convolve the single phase characteristic signal to obtain O'(1,j), and then input each convolved phase characteristic signal O'(1,j) into the matrix to obtain the matrix O(i,j). The effect is the same as using the two-dimensional convolution kernel K(p,q) to directly perform a two-dimensional convolution on the entire matrix. The one-dimensional convolution formula is as follows:

[0139] Through the embodiments provided in this application, based on the fiber optic disturbance monitoring system, the two-dimensional convolution method is used to determine the seabed anchor damage events, which can realize the functions of autonomously controlling the recognition range, customizing the duration and vibration intensity of anchor damage events, and can also realize the identification and positioning of anchor damage events in the absence of actual anchor damage data, and achieve a relatively accurate level.

[0140] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0141] The present application also provides an anchor damage detection device. It should be noted that the anchor damage detection device of the present application can be used to execute the anchor damage detection method provided in the present application. The following describes the anchor damage detection device provided in the present application.

[0142] FIG8 is a schematic diagram of an anchor damage detection device according to an embodiment of the present application. As shown in FIG8 , the device includes:

[0143] An acquisition unit 802 is configured to acquire n phase signals to be detected, where n is a positive integer;

[0144] An extraction unit 804 is configured to perform feature extraction on the n phase signals to obtain p phase signal values ​​corresponding to each phase signal;

[0145] A construction unit 806 is configured to construct an initially empty target matrix with a matrix size of m times n, where m is used to indicate a first time information selected from all time information corresponding to p phase signal values, and m and p are positive integers and m is less than p;

[0146] a filling unit 808 configured to sequentially fill a target matrix with the p phase signal values ​​corresponding to each phase signal, wherein if no region in the target matrix is ​​not filled with a phase signal value, determining a target state of the target matrix as a convolution detection state;

[0147] A convolution unit 810 is configured to perform convolution processing on a target matrix of a convolution detection state to obtain a first convolution result, and determine a first anchor damage detection result of n phase signals under first time information based on the first convolution result;

[0148] The elimination unit 812 is used to eliminate the phase signal values ​​filled in the first row of the target matrix, move the phase signal values ​​filled in the second to m-th rows of the target matrix to the first to m-1-th rows, and restore the target state of the target matrix from the convolution detection state to the signal filling state.

[0149] As an optional solution, the convolution unit 810 includes:

[0150] A first calculation module is used to perform a two-dimensional convolution calculation on the target matrix using a two-dimensional convolution kernel to obtain a first calculation matrix with a matrix size of i times j;

[0151] A second calculation module is used to record the elements in the first calculation matrix whose values ​​are greater than the first preset threshold as 1, and to record the elements in the convolution matrix whose values ​​are not greater than the first preset threshold as 0, to obtain a second calculation matrix;

[0152] a third calculation module, configured to add the elements included in the second calculation matrix by columns to obtain a third calculation matrix having a matrix size of 1 times j;

[0153] The judgment module is used to judge the values ​​of the j elements included in the third calculation matrix based on the values ​​of the j elements and the second preset threshold value, so as to obtain a first anchor damage detection result.

[0154] As an optional solution, the judgment module includes:

[0155] The first determination submodule is used to determine the current element from j elements in sequence;

[0156] The second determining submodule is configured to determine that an optical fiber region of a phase signal corresponding to the current element has an anchor risk when the value of the current element is greater than a second preset threshold multiplied by i.

[0157] As an optional solution, the first computing module includes:

[0158] The acquisition submodule is used to obtain a two-dimensional convolution kernel with a matrix size of k times k, where k is an odd number and k is not greater than m and not greater than n;

[0159] The filling submodule is used to perform row filling and column filling processing on the target matrix to obtain a filled target matrix with a matrix size of k times k;

[0160] The product submodule is used to perform product processing on the padded target matrix using a two-dimensional convolution kernel.

[0161] As an optional solution, the device further includes:

[0162] a determination module, configured to, after restoring the target state of the target matrix from the convolution detection state to the signal filling state, sequentially determine n phase signal values ​​from a plurality of phase signal values ​​that are not filled into the target matrix among the p phase signal values;

[0163] A filling module, configured to fill the m-th row region of the target matrix with n phase signal values ​​in sequence after restoring the target state of the target matrix from the convolution detection state to the signal filling state;

[0164] an adjustment module for, after restoring the target state of the target matrix from the convolution detection state to the signal filling state, and after all the n phase signal values ​​are filled into the target matrix, adjusting the target state from the signal filling state to the convolution detection state;

[0165] The convolution module is used to perform a second convolution processing on the target matrix in the convolution detection state after restoring the target state of the target matrix from the convolution detection state to the signal filling state to obtain a second convolution result, and determine the second anchor detection result of the n phase signals under the second time information based on the second convolution result.

[0166] As an optional solution, the extraction unit 804 includes:

[0167] An extraction module is used to perform characteristic variance extraction processing on n phase signals according to the first period to obtain multiple phase characteristic values ​​corresponding to the first period;

[0168] The accumulation module is used to accumulate the phase characteristic values ​​corresponding to multiple first periods according to the second period to obtain p phase signal values ​​corresponding to each phase signal, wherein one second period includes at least two first periods, and different second periods do not overlap with each other.

[0169] As an optional solution, the obtaining unit 802 includes:

[0170] a transmitting module, configured to use a laser light source to transmit laser light into a coupler, wherein the coupler inputs a light intensity detection light of a first proportion of the laser light into an acousto-optic modulator to obtain a pulse signal, and the acousto-optic modulator is configured to convert the laser light into a pulse signal;

[0171] an amplification module, configured to amplify the pulse signal using an erbium-doped fiber amplifier and then input the amplified signal into an optical fiber to obtain Rayleigh scattering of the optical fiber, and determine two coherent lights based on the Rayleigh scattering and the second proportion of the intrinsic light separated by the coupler;

[0172] The first input module is used to input two coherent lights into a balanced detector to obtain a target electrical signal, wherein the smoothing detector is used to convert the optical signal into an electrical signal;

[0173] The second input module is used to input the target electrical signal into the acquisition card to obtain n phase signals output by the acquisition card.

[0174] An embodiment of the present application provides a computer-readable storage medium having a program stored thereon, which implements the above-mentioned anchor damage detection method when executed by a processor.

[0175] An embodiment of the present application provides a processor, which is used to run a program, wherein the above-mentioned anchor damage detection method is executed when the program is run.

[0176] As shown in FIG9 , an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned anchor damage detection method is implemented.

[0177] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the target model can be trained or optimized by adjusting the kernel parameters, thereby improving the efficiency of data loading.

[0178] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0179] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0180] The present application is described with reference to the flow chart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0181] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0182] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0183] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0184] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0185] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0186] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0187] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. An anchor damage detection method, characterized in that, Including: Obtain n phase signals to be detected, where n is a positive integer; Extract features from the n phase signals to obtain p phase signal values corresponding to each phase signal; Construct a target matrix that is initially empty and has a matrix size of m by n, where m is used to indicate the first time information selected from all the time information corresponding to the p phase signal values, and m and p are positive integers and m is less than p; Successively fill the p phase signal values corresponding to each phase signal into the target matrix. In the case where there is no area in the target matrix where the phase signal value has not been filled, determine the target state of the target matrix as the convolution detection state; Perform convolution processing on the target matrix in the convolution detection state to obtain a first convolution result, and determine a first anchor damage detection result of the n phase signals under the first time information based on the first convolution result; Delete the phase signal values filled in the first row of the target matrix, move the phase signal values filled in the second row to the mth row of the target matrix to the first row to the (m - 1)th row, and restore the target state of the target matrix from the convolution detection state to the signal filling state.

2. The method according to claim 1, characterized in that, The performing convolution processing on the target matrix in the convolution detection state to obtain a first convolution result, and determining an anchor damage detection result of the n phase signals based on the first convolution result includes: Perform two-dimensional convolution calculation on the target matrix using a two-dimensional convolution kernel to obtain a first calculation matrix with a matrix size of i by j; Mark the elements in the first calculation matrix with values greater than a first preset threshold as 1, and mark the elements in the convolution matrix with values not greater than the first preset threshold as 0 to obtain a second calculation matrix; Sum the elements included in the second calculation matrix column by column to obtain a third calculation matrix with a matrix size of 1 by j; Based on the values of the j elements included in the third calculation matrix and a second preset threshold, respectively determine the values of the j elements to obtain the first anchor damage detection result.

3. The method according to claim 2, wherein The respectively determining the values of the j elements based on the values of the j elements included in the third calculation matrix and the second preset threshold includes: Successively determine the current element from the j elements; When the value of the current element is greater than the second preset threshold multiplied by i, determine that there is an anchor damage risk in the optical fiber area of the phase signal corresponding to the current element.

4. The method according to claim 2 or 3, characterized in that, The performing two-dimensional convolution calculation on the target matrix using a two-dimensional convolution kernel includes: Obtain the two-dimensional convolution kernel with a matrix size of k by k, where k is an odd number and k is not greater than m and not greater than n; Perform row filling processing and column filling processing on the target matrix to obtain the filled target matrix with a matrix size of k by k; Use the two-dimensional convolution kernel to perform a product process on the filled target matrix.

5. The method according to any one of claims 1 to 4, characterized in that After restoring the target state of the target matrix from the convolution detection state to the signal filling state, the method further includes: Determine n phase signal values in sequence from the multiple phase signal values among the p phase signal values that have not been filled into the target matrix; Fill the n phase signal values into the m-th row region of the target matrix in sequence; After all the n phase signal values are filled into the target matrix, adjust the target state from the signal filling state to the convolution detection state; Perform a second convolution process on the target matrix in the convolution detection state to obtain a second convolution result, and determine a second anchor damage detection result of the n phase signals under second time information based on the second convolution result.

6. The method according to any one of claims 1 to 4, characterized in that The feature extraction of the n phase signals to obtain p phase signal values corresponding to each phase signal includes: Perform feature variance extraction processing on the n phase signals respectively according to a first period to obtain phase feature values corresponding to multiple first periods; Accumulate the phase feature values corresponding to multiple first periods according to a second period to obtain p phase signal values corresponding to each phase signal, where one second period includes at least two first periods and different second periods do not cross each other.

7. The method according to any one of claims 1 to 4, characterized in that, The obtaining of the n phase signals to be detected includes: Use a laser light source to emit laser light into a coupler, where the coupler inputs laser light with a first ratio of light intensity detection light into an acousto-optic modulator to obtain a pulse signal, and the acousto-optic modulator is used to convert the laser light into the pulse signal; Use an erbium-doped fiber amplifier to amplify the pulse signal and then input it into an optical fiber to obtain Rayleigh scattering of the optical fiber, and determine two coherent lights based on the Rayleigh scattering and the second ratio of the intrinsic light separated by the coupler; Input the two coherent lights into a balanced detector to obtain a target electrical signal, where the smoothing detector is used to convert an optical signal into an electrical signal; Input the target electrical signal into a data acquisition card to obtain the n phase signals output by the data acquisition card.

8. An anchor damage detection device, characterized in that, Includes: An acquisition unit for acquiring n phase signals to be detected, where n is a positive integer; An extraction unit for performing feature extraction on the n phase signals to obtain p phase signal values corresponding to each phase signal; A construction unit for constructing an initially empty target matrix with a matrix size of m multiplied by n, where m is used to indicate the first time information selected from all the time information corresponding to the p phase signal values, and m and p are positive integers and m is less than p; A filling unit for filling the p phase signal values corresponding to each phase signal into the target matrix in sequence, where in the case that there is no region in the target matrix where the phase signal value has not been filled, the target state of the target matrix is determined as the convolution detection state; A convolution unit for performing a convolution process on the target matrix in the convolution detection state to obtain a first convolution result, and determining a first anchor damage detection result of the n phase signals under the first time information based on the first convolution result; The elimination unit is used to eliminate the phase signal values filled in the first row of the target matrix, move the phase signal values filled in the second row to the m-th row of the target matrix to the first row to the (m-1)-th row, and restore the target state of the target matrix from the convolution detection state to the signal filling state.

9. A processor, characterized in that, The processor is used to run a program, wherein when the program runs, it executes the method described in any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory. The memory is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, it implements the method described in any one of claims 1 to 7.

12. A computer program product, characterized in that, It includes a computer program, and when the computer program is executed by a processor, it implements the method described in any one of claims 1 to 7.

Images