Submarine optical fiber vibration event detection method based on confidence weighting

Abstract

The present invention relates to the technical field of optical signal processing and analysis, and specifically provides a submarine optical fiber vibration event detection method based on trust weighting, the method comprising: obtaining an optical pulse echo matrix based on a received signal, and decomposing the signal using a low-rank and sparse decomposition model. A trust coefficient is introduced to measure the reliability of the data, and an optimization model is created. The trust coefficient is set to a tidal trust coefficient or a natural disaster trust coefficient according to the marine environment. The optimization model is solved to obtain a sparse item estimation matrix corresponding to the sparse items; and natural disaster events and vibration events in the received signal are detected based on the sparse item estimation matrix. The method can dynamically adjust the reliability assessment of the signal according to different marine environments, effectively distinguish between noise and real vibration events, maintain strong robustness in a complex and multi-interference marine environment, is not easily affected by interference sources, and has good event detection precision and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of optical signal processing and analysis, and in particular to a submarine optical fiber vibration event detection method based on confidence weighting. Background Art

[0002] Optical Time Domain Reflectometer (OTDR) technology can assess optical fiber loss and fault locations by analyzing the echo information of optical pulse signals. Therefore, OTDR technology is widely used in the inspection and maintenance of optical fiber communication systems, and is specifically used to monitor the occurrence of vibration events in marine environments.

[0003] Existing technologies for detecting vibration events rely on conventional signal processing methods, which cannot accurately separate noise from target vibration events and are therefore unsuitable for complex marine environments. For example, during tidal periods, the OTDR echo signal contains significant periodic interference from the tide, resulting in a high false alarm rate. Existing technologies struggle to eliminate interference from environmental factors, resulting in insufficient accuracy in detecting vibration events in high-noise marine environments. Summary of the Invention

[0004] The present invention provides a submarine optical fiber vibration event detection method based on confidence weighting. By introducing a confidence coefficient to distinguish interference noise from actual vibration events, it at least solves the problem that the interference of the marine environment affects the detection accuracy.

[0005] In a first aspect, the present invention provides a method for detecting submarine optical fiber vibration events based on confidence weighting, the method comprising:

[0006] Obtaining an optical pulse echo matrix according to the received signal; wherein the optical pulse echo matrix includes a noise term, a low-rank term, and a sparse term;

[0007] creating an optimization model based on the optical pulse echo matrix, wherein the optimization model is used to optimize the optical pulse echo matrix based on a confidence coefficient, the confidence coefficient is used to weight the noise term, and the confidence coefficient is set to a tidal confidence coefficient or a natural disaster confidence coefficient based on the ocean environment;

[0008] Solving the optimization model to obtain a sparse item estimation matrix corresponding to the sparse item;

[0009] Natural disaster events and vibration events in the received signal are detected according to the sparse item estimation matrix.

[0010] The confidence-weighted submarine optical fiber vibration event detection method provided by an embodiment of the present invention further includes, before creating an optimization model based on the optical pulse echo matrix:

[0011] Predict expected echo data based on tidal patterns;

[0012] The tidal confidence coefficient is calculated based on a difference between actually detected optical pulse echo data and the expected echo data; wherein the actually detected optical pulse echo data is obtained based on the received signal.

[0013] The confidence-weighted submarine optical fiber vibration event detection method provided by an embodiment of the present invention further includes, before creating an optimization model based on the optical pulse echo matrix:

[0014] The natural disaster confidence coefficient is calculated based on the noise level of optical pulse echo data; wherein the optical pulse echo data is obtained based on the received signal.

[0015] The present invention provides a submarine optical fiber vibration event detection method based on confidence weighting, which creates an optimization model based on the optical pulse echo matrix, including:

[0016] According to the ocean environment, the confidence coefficient is set to the tidal confidence coefficient, or the natural disaster confidence coefficient;

[0017] Calculate the element-by-element product of the confidence coefficient and the noise term, and take the F-norm of the calculation result;

[0018] Performing singular value decomposition on the low-rank term and summing the singular values ​​to obtain a nuclear norm of the low-rank term;

[0019] Obtaining a zero norm of the sparse term according to the number of non-zero elements of the sparse term;

[0020] The square of the F norm, the weighted nuclear norm, and the weighted zero norm are summed to obtain the optimization model.

[0021] The submarine optical fiber vibration event detection method based on confidence weighting provided by an embodiment of the present invention further includes: before solving the optimization model to obtain the sparse item estimation matrix, the method further includes:

[0022] According to the receiving time and receiving position of the optical pulse echo data, adjacent data points are taken to determine the neighborhood range;

[0023] The confidence coefficient is corrected by using the average of multiple adjacent data points.

[0024] The trust-weighted submarine optical fiber vibration event detection method provided by the embodiment of the present invention solves the optimization model to obtain a sparse item estimation matrix, including:

[0025] Introducing the Lagrange multiplier matrix;

[0026] Initializing the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix;

[0027] Alternately updating the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix, and iterating repeatedly;

[0028] When the iteration termination condition is met, the process stops and the sparse item estimation matrix is ​​output.

[0029] The present invention provides a submarine optical fiber vibration event detection method based on confidence weighting, which detects natural disaster events and vibration events in the received signal according to the sparse item estimation matrix, including:

[0030] detecting natural disaster events based on the sparse term estimation matrix;

[0031] Setting the elements corresponding to the natural disaster events in the sparse item estimation matrix to zero;

[0032] According to the zeroed sparse item estimation matrix, vibration events are detected through event dictionary learning or modal decomposition method.

[0033] The present invention provides a trust-weighted submarine optical fiber vibration event detection method, which detects natural disaster events according to the sparse item estimation matrix, including:

[0034] The signal mutation degree is calculated based on the variation and noise level of the optical pulse echo data at adjacent moments at the same position;

[0035] Calculating the reconstruction confidence of the natural disaster according to the signal mutation degree;

[0036] A mutation threshold and a reconstruction confidence threshold are set; when the signal mutation degree is greater than the mutation threshold and the reconstruction confidence is less than the reconstruction confidence threshold, the event corresponding to the current optical pulse echo data is a natural disaster event.

[0037] In a second aspect, the present invention also provides an electronic device, comprising: a processor, and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the confidence-weighted submarine optical fiber vibration event detection method according to any of the above embodiments.

[0038] In a third aspect, the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the submarine optical fiber vibration event detection method based on confidence weighting described in any of the above embodiments.

[0039] This embodiment provides a trust-weighted submarine optical fiber vibration event detection method that uses a trust coefficient to measure data reliability and dynamically adjusts the signal reliability assessment based on varying ocean environments. It uses a low-rank and sparse decomposition model to decompose OTDR signals, distinguishing between noise and vibration events. This method maintains strong robustness in complex, high-interference ocean environments, is less susceptible to interference sources, and achieves high event detection precision and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without inventive effort.

[0041] Figure 1 The present invention is a flowchart of a submarine optical fiber vibration event detection method based on confidence weighting in an embodiment of the present invention.

[0042] Figure 2 It is a structural schematic diagram of the electronic device created by the present invention. DETAILED DESCRIPTION

[0043] The following describes embodiments of the present invention in more detail with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0044] Submarine optical fibers, as critical infrastructure for marine communications systems, carry massive amounts of data. Therefore, their maintenance is crucial to the proper functioning of marine facilities and activities. Submarine optical fibers vibrate under external forces. Slight vibrations can cause microbends in the fiber, increasing light signal scattering and loss, and impacting communication quality. Continuous vibrations can subject the fiber to prolonged stress, leading to fatigue damage and structural fractures, shortening its service life and, in severe cases, causing communication interruptions.

[0045] To monitor the status of submarine optical fibers promptly and accurately and prevent communication failures, optical time domain reflectometer (OTDR) technology has been introduced into submarine optical fiber communication systems for maintenance. OTDR technology transmits optical pulses into the fiber and uses the information in the echo signals to accurately locate faults and abnormalities within the fiber. It also assesses fiber loss changes in real time, ensuring the safe and stable operation of submarine optical fiber communication networks.

[0046] Related technologies rely on fixed signal processing methods to process OTDR echo signals. These methods are not suitable for complex marine environments with numerous interference sources, making it difficult to separate impurity noise from target vibration events. For example, during tidal periods, the OTDR signal contains a large amount of periodic interference, which can easily lead to false detections and false alarms. During natural disasters, sudden vibration events are mixed with noise, making traditional processing methods difficult to accurately detect vibration events in high-noise environments.

[0047] Accordingly, refer to Figure 1 As shown, this embodiment provides a submarine optical fiber vibration event detection method based on confidence weighting. This method processes OTDR echo signals, isolates the influence of factors such as tides and natural disasters, and accurately detects vibration events in high-noise environments. The inclusion of a confidence factor to measure data reliability results in high detection accuracy and robustness.

[0048] Specifically, the submarine optical fiber vibration event detection method provided in this embodiment includes the following steps:

[0049] Step S100: Obtain an optical pulse echo matrix based on the received signal .

[0050] In this embodiment, the received signal is received by the spectrum analyzer. In the OTDR-based distributed optical fiber sensing system, the OTDR echo optical pulse signal received by the spectrum analyzer is the received signal. The matrix formed by the sampling Rayleigh curves corresponding to the echo light pulse signals is the light pulse echo matrix . Optical pulse echo matrix Specifically expressed as:

[0051] ;

[0052] Where, Indicates the The sampling Rayleigh curve corresponding to the echo optical pulse signal, is an integer, and 1≤ ≤ In this embodiment, the initial monitoring time of the vibration event is set to , the pulse repetition interval of the light pulse emitted by the light source is , so the The monitoring time corresponding to the echo optical pulse signal is + The sampled Rayleigh curve contains position information x and time information t; the position information x corresponds to different positions on the optical fiber and is used to determine the fault and loss points on the optical fiber, and the time information t reflects the monitoring time.

[0053] In submarine optical fiber vibration detection, common events that cause false alarms and misjudgments include periodic disturbances such as tides and natural disasters such as earthquakes and tsunamis. This embodiment uses the optical pulse echo matrix to calculate the difference between the two types of events. Disassemble, optical pulse echo matrix Including noise terms, low-rank terms and sparse terms, refer to the following formula:

[0054] ;

[0055] Where, It is a low-rank term used to reflect periodic slow-changing events such as tides and some ocean current changes. is a sparse term used to reflect non-periodic emergencies. Emergencies include natural disasters such as earthquakes and tsunamis, as well as submarine optical fiber vibrations. The submarine optical fiber vibration events are the target vibration events to be detected. is a noise term used to reflect other noise. The method provided in this embodiment uses a low-rank and sparse decomposition model to separate slowly varying events from sudden events, eliminating the impact of periodic events such as tides on detection accuracy. It also calculates and separates natural disasters and target vibration events in the sparse term, ultimately performing vibration detection and feedback on the target vibration event.

[0056] Step S200: According to the optical pulse echo matrix Create an optimization model.

[0057] The optimization model is used to calculate the confidence coefficient Optical pulse echo matrix Optimize to achieve higher accuracy in subsequent solutions. Used to weight the noise term , which measures the reliability of the received signal at each location at each moment.

[0058] Based on this, before creating the optimization model, this embodiment also specifically sets the trust coefficient As an implementation option, set the trust factor Including setting the tidal confidence factor and natural disaster trust coefficient Specifically, set the tidal trust coefficient The steps are as follows:

[0059] Predict expected echo data based on tidal patterns . Among them, the echo light pulse signal of the OTDR monitoring area in the past astronomical tidal cycle is corresponded to the optical fiber sampling Rayleigh curve, and the above-mentioned tidal pattern is obtained by fitting. The tidal pattern is a mode of the optical fiber sampling Rayleigh curve. Since the data disturbance during the tide has a certain regularity and has a strong correlation with the water level change, the optical pulse echo data under the influence of the tide also has periodic changes. The tidal pattern is established by analyzing the echo signals in the past astronomical tidal cycle. Therefore, the tidal pattern is essentially a sampling Rayleigh curve with a fixed periodic fluctuation component. According to the tidal pattern prediction, the corresponding time can be obtained. and location Expected echo data .

[0060] According to the actual detected optical pulse echo data R i,j and expected echo data The difference between the two values ​​can be calculated by referring to the following formula to obtain the tidal confidence coefficient. :

[0061] ;

[0062] Where, It is an adjustment parameter used to adjust the absolute value in the formula. i,j The optical pulse echo data during actual monitoring, that is, the optical pulse echo matrix Corresponding time and location elements.

[0063] It should be noted that in this embodiment, the periodic interference of tidal events is eliminated by using the predicted values ​​of historical data and the actual data monitoring values. If periodic fluctuations occur and are consistent with the expected tidal pattern, then the tidal confidence coefficient Higher; if the fluctuation is caused by other interference sources or sensor failure, it will deviate from the tidal pattern, and the large data difference will lead to a large absolute value in the formula, and the corresponding tidal confidence coefficient Lower.

[0064] Continuing, natural disaster trust coefficient Refer to the following formula for calculation:

[0065] ;

[0066] Where, For the corresponding time and location Optical pulse echo matrix The optical pulse echo data R i,j noise level. is the trust attenuation control coefficient.

[0067] Because natural disasters such as earthquakes usually cause non-periodic, strong vibrations or drastic changes, which are significantly different from the regular periodic fluctuations during tides, sensors are very likely to malfunction or malfunction during natural disasters, resulting in increased data errors. Therefore, the trust factor during natural disasters is It is calculated based on the mutation type and noise level of the data. If there is a significant interference signal in the data, then the natural disaster trust coefficient Low; if the data is not significantly disturbed and / or is consistent with the expected fluctuations under natural disasters, then the natural disaster trust coefficient Higher.

[0068] As an implementable method, step S200 includes the following steps:

[0069] Step S210: According to the ocean environment, the trust coefficient Set as tidal confidence factor , or, set it to the natural disaster trust coefficient.

[0070] Specifically, the marine environment includes tidal events and natural disasters such as earthquakes and tsunamis. The following formula is the trust coefficient matrix:

[0071] ;

[0072] Where, The tidal deviation threshold is obtained by matching the echo light pulse signal of the OTDR monitoring area in the past astronomical tidal cycle to the fiber sampling Rayleigh curve and then training it. i,j and expected echo data The tidal confidence coefficient is calculated by the difference between , when the calculated result is greater than the tidal deviation threshold When the light pulse echo data R i,j The corresponding ocean environment is a tidal event, and the calculation result is taken as the corresponding moment and location Trust coefficient When the calculated result is less than or equal to the tidal deviation threshold When the light pulse echo data R i,j The corresponding ocean environment deviates from the tidal event, which is a natural disaster event. and the trust decay control coefficient Calculating the Trust Factor for Natural Disasters As the corresponding moment and location Trust coefficient .

[0073] Step S220: introduce the trust coefficient set in step S210 Get the optimized model. Refer to the following formula:

[0074] ;

[0075] In the formula, the trust coefficient Element-wise product with the noise term, Indicates that the matrix operation is the Hadamard product, also known as the element-wise product. The F-norm, also known as the Frobenius norm, is taken from the result of the element-wise product to measure the fitting error of the optimization model.

[0076] For low-rank terms Perform singular value decomposition and sum the singular values ​​to obtain low-rank terms The nuclear norm is used to control the low-rank terms rank.

[0077] According to the sparse items The number of non-zero elements of The zero norm of , used to control the sparse terms The sparsity of .

[0078] The optimization model is obtained by summing the square of the F norm, the weighted nuclear norm, and the weighted zero norm. and is a regularization parameter used to balance the low-rank terms and sparse terms The weight of .

[0079] Before solving the optimization model, this embodiment also corrects each element in the trust coefficient matrix to further enhance the robustness of the trust coefficient matrix. The correction process is referred to the following formula:

[0080] ;

[0081] Where, the tidal trust coefficient is is the corresponding time during the tidal event and location Trust coefficient ; Natural disaster trust coefficient The corresponding time during the natural disaster event and location Trust coefficient .

[0082] It's time and location The time-space neighborhood of , which contains the time t k and position x l ; Correspondingly, is the time t corresponding to the tidal period k and position x l Trust coefficient ; is the time t corresponding to the natural disaster event k and position x l Trust coefficient .

[0083] When making corrections, first use the optical pulse echo data R i,j Receiving time and receiving location Take adjacent data points, that is, the optical pulse echo matrix Element R i,j For example, the optical pulse echo data R i-1,j 、R i+1,j 、R i,j-1 、R i,j+1 In this embodiment, three adjacent elements can be taken as adjacent data points to determine the neighborhood scope.

[0084] Since the received signals at adjacent locations or adjacent times have certain similarities, the confidence of the current signal can be corrected and adjusted based on the adjacent received signals. The confidence coefficient w of the data points within the range k,l The weighted mean of and location The trust coefficient w i,j Make corrections, and so on to correct each element in the trust coefficient matrix. The trust coefficient is corrected by the correlation of adjacent data points in the time-space neighborhood. Smoothing is performed to eliminate the influence of local outliers on the trust coefficient matrix, thereby making the trust coefficient distribution smoother and more reliable.

[0085] Step S300, solve the optimization model in step S200 to obtain sparse terms The corresponding sparse term estimation matrix .

[0086] In this embodiment, the sparse terms in the optimization model are solved by the Alternating Direction Method of Multipliers (ADMM). , get the sparse item estimation matrix The specific steps are as follows:

[0087] Introducing the Lagrange multiplier matrix;

[0088] Initialize the noise term , low-rank term , sparse items and the Lagrange multiplier matrix;

[0089] For noise terms , low-rank term , sparse items Alternately update the Lagrange multiplier matrix and repeat the iteration;

[0090] Stop and output sparse items when the iteration termination condition is met The corresponding sparse term estimation matrix .

[0091] ADMM algorithm is an algorithm for solving optimization problems. It combines the ideas of augmented Lagrangian function and dual ascent algorithm. It is widely used in many fields such as machine learning, signal processing, image processing, statistical analysis, etc. The optimization model is optimized and solved using ADMM algorithm. The sparse item estimation matrix obtained is Includes natural disaster events and target vibration events.

[0092] Step S400, estimating the matrix based on the sparse terms Detect natural disaster events and vibration events in received signals.

[0093] As an implementable method, step S400 includes the following steps:

[0094] Step S410, estimate the matrix for sparse items Analyze the sparse non-zero elements of and estimate the matrix based on the sparse terms Detection of natural disaster events. Specifically including:

[0095] Step S411: quantitatively analyze the signal mutation according to the variation of the optical pulse echo data at adjacent moments at the same position, and then Calculate the signal mutation degree. The signal mutation degree is calculated according to the following formula:

[0096] Δx i,j =R i,j -R i,j-1 ;

[0097] ;

[0098] Where Ri,j For the corresponding time and location The optical pulse echo data, R i,j-1 is the corresponding time t j-1 and location The optical pulse echo data, namely R i,j Adjacent time data of Δx i,j =R i,j -R i,j-1 Indicates location The signal change at adjacent moments is used to quantify the signal mutation degree. For the corresponding time and location The optical pulse echo data R i,j The noise level. C i,j For the corresponding time and location signal mutation rate.

[0099] Step S412: according to the signal mutation degree C i,j Calculate the reconstruction confidence α of natural disasters i,j . Reconstruction confidence α i,j Refer to the following formula for calculation:

[0100] ;

[0101] Where, It is an adjustment parameter used to control the sensitivity of the reconstruction confidence to mutation.

[0102] When adjusting parameters When it is large, the mutation of the signal has an impact on the reconstruction confidence α i,j The influence of When it is small, the mutation confidence α i,j The impact is small.

[0103] Step S413: Setting the mutation threshold and reconstruction confidence threshold .

[0104] When a natural disaster occurs, the signal often shows a drastic mutation. i,j Greater than the mutation threshold , and the reconstruction confidence α calculated in step S412 i,j Less than the reconstruction confidence threshold Detect the current time and location The optical pulse echo data R i,j The corresponding event is a natural disaster event.

[0105] Dissatisfied Under this condition, the current moment and location The optical pulse echo data R i,j The corresponding event is not a natural disaster event.

[0106] Step S420, estimate the matrix for the sparse items The elements corresponding to natural disaster events are set to zero.

[0107] when hour, .

[0108] The elements that exclude natural disaster events in step S410 are not processed. The processing is to separate natural disaster events and target vibration events, and to separate and eliminate the impact of natural disaster events on the detection of target vibration events.

[0109] Step S430, estimating the matrix based on the sparse terms after setting to zero , vibration events are detected by event dictionary learning or modal decomposition method.

[0110] Among them, event dictionary learning requires initializing the dictionary matrix, and the column vector in the dictionary matrix is ​​set to a vibration mode. The sparse item estimation matrix after zeroing Each column vector of corresponds to the sparse coefficient, and the dictionary matrix is ​​updated according to the sparse coefficient, and the representation ability of the dictionary is continuously optimized. Finally, the sparse coefficients are analyzed. If a sparse coefficient has a large non-zero value at the position corresponding to a column vector of a dictionary matrix, it means that the vibration mode represented by the dictionary matrix column is in the corresponding sparse item estimation matrix. exists in the column vector of .

[0111] The modal decomposition method is to estimate the sparse terms after setting them to zero. Perform modal decomposition to obtain a series of modal components. Features are extracted from each modal component, which can reflect the characteristics of different vibration events. Based on the extracted features, a threshold is set or a machine learning classification algorithm is used to determine whether each modal component corresponds to a vibration event.

[0112] For the sparse item estimation matrix after zeroing , the method for detecting target vibration events can also use other methods according to the detection requirements, and is not limited to this.

[0113] This embodiment provides a confidence-weighted submarine optical fiber vibration event detection method that incorporates a confidence coefficient to measure data reliability and dynamically adjusts signal reliability assessment based on varying ocean environments. It employs a low-rank and sparse decomposition model to decompose OTDR signals, distinguishing between noise and vibration events. This method achieves high event detection precision and accuracy.

[0114] Combining the confidence factor with the temporal and spatial characteristics of OTDR signals effectively addresses environmental interference such as tides and accurately detects vibration events triggered by natural disasters. The system maintains strong robustness in complex, multi-interference marine environments and is less susceptible to interference sources. Through smooth adjustment of the confidence factor and mutation analysis, the likelihood of false detections and false alarms is effectively reduced, improving the system's practical application effectiveness.

[0115] The method provided in this embodiment not only detects sudden events caused by natural disasters but also effectively distinguishes other types of events, such as tidal and local vibrations, and has broad applicability. Real-time analysis of OTDR echo optical pulse data facilitates rapid response to sudden events in submarine optical fiber networks, enabling timely action and improving system automation.

[0116] This embodiment further provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements the above-mentioned submarine optical fiber vibration event detection method based on confidence weighting.

[0117] This embodiment further provides a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform the confidence-weighted submarine optical fiber vibration event detection method.

[0118] An embodiment of the present invention further provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, and when executed by the at least one processor, the computer program causes the electronic device to perform the confidence-weighted submarine optical fiber vibration event detection method.

[0119] The structural block diagram of the electronic device that can be used as the server or client of the embodiment of the present invention will now be described, which is an example of the hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0120] like Figure 2 As shown, the electronic device includes a computing unit 101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 102 or a computer program loaded from a storage unit 108 into a random access memory (RAM) 103. Various programs and data required for the operation of the electronic device can also be stored in the RAM 103. The computing unit 101, ROM 102, and RAM 103 are connected to each other via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0121] Multiple components in the electronic device are connected to the I / O interface 105, including: an input unit 106, an output unit 107, a storage unit 108, and a communication unit 109. The input unit 106 can be any type of device capable of inputting information into the electronic device. The input unit 106 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 107 can be any type of device capable of presenting information and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 108 can include, but is not limited to, a magnetic disk and an optical disk. The communication unit 109 allows the electronic device to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks, and can include, but is not limited to, a modem, a network card, an infrared communication device, and / or a wireless communication transceiver, such as a Bluetooth device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0122] The computing unit 101 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 101 include, but are not limited to, a CPU, a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing units, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 101 performs the various methods and processes described above. For example, in some embodiments, the method embodiments of the present invention may be implemented as a computer program tangibly embodied in a machine-readable medium, such as a storage unit 108. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device via the ROM 102 and / or the communication unit 109. In some embodiments, the computing unit 101 may be configured to perform the above-described methods by any other suitable means (e.g., via firmware).

[0123] The computer programs for implementing the methods of the embodiments of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable signal medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, or infrared system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] It should be noted that the term "including" and its variations used in the embodiments of the present invention are open inclusions, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "multiple" mentioned in the embodiments of the present invention are illustrative and not restrictive. Those skilled in the art should understand that unless the context clearly indicates otherwise, they should be understood as "one or more".

[0126] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entrances shall be provided for users to choose to authorize or refuse.

[0127] The various steps described in the method implementation methods provided by the embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method implementation methods may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.

[0128] The term "embodiment" in this specification refers to specific features, structures or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. The various embodiments in this specification are described in a related manner, and the same or similar parts between the various embodiments are referenced to each other. In particular, for the device, equipment, and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment.

[0129] The above-described embodiments merely represent several implementation methods of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of protection. It should be noted that a person of ordinary skill in the art would be able to make various modifications and improvements without departing from the scope of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A submarine optical fiber vibration event detection method based on confidence weighting, characterized in that: The method comprises: Obtaining an optical pulse echo matrix according to the received signal; wherein the optical pulse echo matrix includes a noise term, a low-rank term, and a sparse term; An optimization model is created based on the optical pulse echo matrix to calculate the tidal confidence coefficient. ； Where, is the tidal trust coefficient, To adjust the parameters, R i,j is the corresponding time in the optical pulse echo matrix and location Elements, To predict the corresponding time according to the tidal pattern and location Expected echo data ; When the calculated result of the tidal confidence coefficient is greater than the tidal deviation threshold, the calculated result of the tidal confidence coefficient is used as the corresponding moment and location Trust coefficient; when the calculated result of the tidal trust coefficient is less than or equal to the tidal deviation threshold, the natural disaster trust coefficient is calculated as the corresponding moment and location wherein the optimization model is used to optimize the optical pulse echo matrix according to the trust coefficient, the trust coefficient is used to weight the noise term, and the trust coefficient is set to a tidal trust coefficient or a natural disaster trust coefficient according to the marine environment; Solving the optimization model to obtain a sparse item estimation matrix corresponding to the sparse item; Natural disaster events and vibration events in the received signal are detected according to the sparse item estimation matrix.

2. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 1 is characterized in that: Before creating the optimization model according to the optical pulse echo matrix, the method further includes: Predict expected echo data based on tidal patterns; The tidal confidence coefficient is calculated based on a difference between actually detected optical pulse echo data and the expected echo data; wherein the actually detected optical pulse echo data is obtained based on the received signal.

3. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 1 is characterized in that: Before creating the optimization model according to the optical pulse echo matrix, the method further includes: The natural disaster confidence coefficient is calculated based on the noise level of optical pulse echo data; wherein the optical pulse echo data is obtained based on the received signal.

4. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 1 is characterized in that: Creating an optimization model according to the optical pulse echo matrix includes: According to the ocean environment, the confidence coefficient is set to the tidal confidence coefficient, or the natural disaster confidence coefficient; Calculate the element-by-element product of the confidence coefficient and the noise term, and take the F-norm of the calculation result; Performing singular value decomposition on the low-rank term and summing the singular values ​​to obtain a nuclear norm of the low-rank term; Obtaining a zero norm of the sparse term according to the number of non-zero elements of the sparse term; The square of the F norm, the weighted nuclear norm, and the weighted zero norm are summed to obtain the optimization model.

5. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 1, characterized in that: Before solving the optimization model to obtain a sparse term estimation matrix, the method further includes: According to the receiving time and receiving position of the optical pulse echo data, adjacent data points are taken to determine the neighborhood range; The confidence coefficient is corrected by using the average of multiple adjacent data points.

6. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 1, characterized in that: Solving the optimization model to obtain a sparse term estimation matrix includes: Introducing the Lagrange multiplier matrix; Initializing the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix; Alternately updating the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix, and iterating repeatedly; When the iteration termination condition is met, the process stops and the sparse item estimation matrix is ​​output.

7. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 1, characterized in that: Detecting natural disaster events and vibration events in the received signal according to the sparse item estimation matrix includes: detecting natural disaster events based on the sparse term estimation matrix; Setting the elements corresponding to the natural disaster events in the sparse item estimation matrix to zero; According to the zeroed sparse item estimation matrix, vibration events are detected through event dictionary learning or modal decomposition method.

8. The submarine optical fiber vibration event detection method based on confidence weighting according to claim 7, characterized in that: Detecting a natural disaster event according to the sparse item estimation matrix includes: The signal mutation degree is calculated based on the variation and noise level of the optical pulse echo data at adjacent moments at the same position; Calculating the reconstruction confidence of the natural disaster according to the signal mutation degree; Set the mutation threshold and reconstruction confidence threshold; When the signal mutation degree is greater than the mutation threshold and the reconstruction confidence is less than the reconstruction confidence threshold, the event corresponding to the current optical pulse echo data is a natural disaster event.

9. An electronic device comprising: A processor and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to perform the submarine optical fiber vibration event detection method based on confidence weighting according to any one of claims 1 to 8.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for detecting submarine optical fiber vibration events based on confidence weighting according to any one of claims 1 to 8 is implemented.

Images