Seabed optical fiber vibration event detection method based on credibility weighting

Abstract

The invention relates to the technical field of optical signal processing and analysis, and particularly provides a submarine optical fiber vibration event detection method based on credibility weighting, and the method comprises the steps: obtaining an optical pulse echo matrix according to a received signal, and carrying out the decomposition of the signal through a low-rank and sparse decomposition model. A credibility coefficient is introduced to measure the reliability of the data, an optimization model is established, and the credibility coefficient is set to be a tide credibility coefficient or a natural disaster credibility coefficient according to the marine environment. Solving the optimization model to obtain a sparse item estimation matrix corresponding to the sparse item; and detecting a natural disaster event and a vibration event in the received signal according to the sparse term estimation matrix. According to the method, reliability evaluation of the signals can be dynamically adjusted according to different marine environments, noise and real vibration events are effectively distinguished, high robustness is kept in the complex and multi-interference marine environment, the method is not prone to being affected by interference sources, and event detection precision and accuracy are good.

Description

Technical Field

[0001] The present invention relates to the technical field of optical signal processing and analysis, and particularly to a method for detecting submarine optical fiber vibration events based on confidence-weighting. Background Art

[0002] Optical Time Domain Reflectometer (OTDR) technology can evaluate the loss and fault location of an optical fiber by analyzing the echo information of an optical pulse signal. Therefore, OTDR technology is widely used in the detection and maintenance of optical fiber communication systems, and is specifically used to monitor the occurrence of vibration events in the marine environment.

[0003] In the prior art, the detection of vibration events relies on conventional signal processing means and cannot accurately separate noise and target vibration events. Therefore, it is not applicable to complex marine environments. For example, during the tide period, there are a large number of periodic interferences caused by the tide in the OTDR echo signal, resulting in a high false alarm rate. It is difficult to exclude the interference of environmental factors in the prior art, and the detection accuracy of vibration events in a high-noise marine environment is insufficient. Summary of the Invention

[0004] An embodiment of the present invention provides a method for detecting submarine optical fiber vibration events based on confidence-weighting, which can distinguish interference noise from actual vibration events by introducing a confidence coefficient, and at least solve 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: Obtaining an optical pulse echo matrix according to a received signal; wherein, the optical pulse echo matrix includes a noise term, a low-rank term, and a sparse term; Creating an optimization model according to the optical pulse echo matrix, wherein the optimization model is used to optimize the optical pulse echo matrix according to a confidence coefficient, the confidence coefficient is used to weight the noise term, and the confidence coefficient is set as a tide confidence coefficient or a natural disaster confidence coefficient according to the marine environment; Solving the optimization model to obtain a sparse term estimation matrix corresponding to the sparse term; Detecting natural disaster events and vibration events in the received signal according to the sparse term estimation matrix.

[0006] Before creating the optimization model according to the optical pulse echo matrix, the method provided by the embodiment of the present invention further comprises: Predicting expected echo data according to a tide pattern; Calculate the tidal confidence coefficient according to the difference between the actually detected optical pulse echo data and the expected echo data; wherein, the actually detected optical pulse echo data is obtained according to the received signal.

[0007] Before creating an optimization model based on the optical pulse echo matrix in the embodiment of the present invention, the method further includes: Calculate the natural disaster confidence coefficient according to the noise level of the optical pulse echo data; wherein, the optical pulse echo data is obtained according to the received signal.

[0008] The method for detecting submarine optical fiber vibration events based on confidence weighted provided by the embodiment of the present invention, creating an optimization model according to the optical pulse echo matrix, includes: According to the ocean environment, set the confidence coefficient to the tidal confidence coefficient, or set it to the natural disaster confidence coefficient; Perform an element-wise product calculation on the confidence coefficient and the noise term, and take the F-norm of the calculation result; Perform singular value decomposition on the low-rank term, and sum the singular values to obtain the nuclear norm of the low-rank term; Obtain the zero norm of the sparse term according to the number of non-zero elements of the sparse term; Sum the square of the F-norm, the weighted nuclear norm, and the weighted zero norm to obtain the optimization model.

[0009] Before solving the optimization model to obtain the sparse term estimation matrix in the embodiment of the present invention, the method further includes: Determine the neighborhood range by taking adjacent data points according to the reception time and reception position of the optical pulse echo data; Correct the confidence coefficient by the mean value of multiple adjacent data points.

[0010] The method for detecting submarine optical fiber vibration events based on confidence weighted provided by the embodiment of the present invention, solving the optimization model to obtain the sparse term estimation matrix, includes: Introduce a Lagrange multiplier matrix; Initialize the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix; Alternately update the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix, and repeat the iteration; Stop and output the sparse term estimation matrix when the iteration termination condition is met.

[0011] The method for detecting submarine optical fiber vibration events based on trust degree weighting provided by the embodiment of the present invention creates detects natural disaster events and vibration events in the received signal according to the sparse term estimation matrix, including: Detect natural disaster events according to the sparse term estimation matrix; Set the elements corresponding to natural disaster events in the sparse term estimation matrix to zero; According to the sparse term estimation matrix after setting to zero, detect vibration events by event dictionary learning or modal decomposition method.

[0012] The method for detecting submarine optical fiber vibration events based on trust degree weighting provided by the embodiment of the present invention creates detects natural disaster events according to the sparse term estimation matrix, including: Calculate the signal mutation degree according to the change amount and noise level of the optical pulse echo data at adjacent moments at the same position; Calculate the reconstruction confidence degree of natural disasters according to the signal mutation degree; Set a mutation threshold and a reconstruction confidence threshold; when the signal mutation degree is greater than the mutation threshold and the reconstruction confidence degree is less than the reconstruction confidence threshold, the event corresponding to the current optical pulse echo data is a natural disaster event.

[0013] In a second aspect, the present invention also provides an electronic device, including: a processor, and a memory for storing a program, the program includes instructions, and when the instructions are executed by the processor, the processor executes the method for detecting submarine optical fiber vibration events based on trust degree weighting according to any of the above embodiments.

[0014] In a third aspect, the present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method for detecting submarine optical fiber vibration events based on trust degree weighting according to any of the above embodiments.

[0015] The method for detecting submarine optical fiber vibration events based on trust degree weighting provided by this embodiment introduces a trust degree coefficient to measure the reliability of data, and dynamically adjusts the reliability evaluation of the signal according to different ocean environments. The OTDR signal is decomposed by using a low-rank and sparse decomposition model, so as to distinguish noise from vibration events, maintain strong robustness in a complex and multi-interference ocean environment, is not easily affected by interference sources, and has good event detection accuracy and accuracy. Description of the Drawings

[0016] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the method for detecting submarine optical fiber vibration events based on trust degree weighting in the embodiments of the present invention.

[0018] Figure 2 It is a schematic structural diagram of the electronic device of the present invention. Detailed implementation manners

[0019] The following will describe the embodiments of the present invention in more detail with reference to the accompanying drawings. Although some 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 set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0020] As a key infrastructure of the marine communication system, submarine optical fibers undertake a huge amount of data transmission tasks. Therefore, the maintenance of submarine optical fibers is of great significance for the normal operation of marine facilities and marine activities. When a submarine optical fiber is vibrated by an external force, a slight vibration causes microbending of the optical fiber, increasing the scattering and loss of the optical signal and affecting the communication quality. Continuous vibration will keep the optical fiber in a stressed state for a long time, resulting in fatigue damage of the optical fiber material and fracture of the optical fiber structure, affecting the service life of the optical fiber and even causing communication interruption in severe cases.

[0021] To monitor the state of submarine optical fibers in a timely and accurate manner and avoid communication failures, an Optical Time Domain Reflectometer (OTDR) technology is introduced into the submarine optical fiber communication system for maintenance. The OTDR technology emits optical pulse signals into the optical fiber and, through the information in the echo signals, accurately locates the fault points and abnormal positions in the optical fiber, and evaluates the loss changes of the optical fiber in real time, providing guarantee for the safe and stable operation of the submarine optical fiber communication network.

[0022] In the related art, a fixed signal processing method is relied on to process the OTDR echo signal. Such a processing method is not applicable to a complex marine environment with many interference sources, and it is difficult to separate impurity noise and target vibration events. For example, during the tide, there are a large number of periodic interferences in the OTDR signal, which are very likely to cause false detections and false alarms. During natural disasters, sudden vibration events are mixed with noise, and traditional processing methods are difficult to accurately detect vibration events in a high-noise environment.

[0023] Accordingly, referring to Figure 1 as shown, this embodiment provides a method for detecting submarine optical fiber vibration events based on confidence-weighting, which processes the OTDR echo signal, separates the influences of factors such as tides and natural disasters, and accurately detects vibration events in a high-noise environment. A confidence coefficient is introduced to measure the reliability of data, and the detection accuracy and robustness are relatively high.

[0024] Specifically, the method for detecting submarine optical fiber vibration events provided in this embodiment includes the following steps: Step S100, obtaining an optical pulse echo matrix according to the received signal .

[0025] In this embodiment, the received signal is obtained by a spectrum analyzer. In a distributed optical fiber sensing system based on OTDR, the OTDR echo optical pulse signal received by the spectrum analyzer is the received signal. The matrix formed by the sampled Rayleigh curves corresponding to the received echo optical pulse signals is the optical pulse echo matrix . The optical pulse echo matrix is specifically expressed as: ; wherein, represents the sampled Rayleigh curve corresponding to the th echo optical pulse signal, is an integer, and 1 ≤ ≤ . In this embodiment, the monitoring initial moment of the vibration event is set as , the pulse repetition interval of the light pulse emitted by the light source is , so the monitoring moment corresponding to the th 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 moment.

[0026] 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 divides the optical pulse echo matrix according to the differences between the two types of events Perform disassembly, and the optical pulse echo matrix includes a noise term, a low-rank term, and a sparse term, as shown in the following formula: ; In the formula, is the low-rank term, which is used to reflect slow-changing events that occur periodically, such as tides and partial ocean current changes. is the sparse term, which is used to reflect sudden events that occur aperiodically; among them, sudden events include natural disasters such as earthquakes and tsunamis, as well as the vibration of submarine optical fibers, and the vibration events of submarine optical fibers are the target vibration events to be detected. is the noise term, which is used to reflect other noises. The method provided in this embodiment adopts a low-rank and sparse decomposition model to separate slow-changing events from sudden events, eliminate the influence of periodic events such as tides on the detection accuracy, and at the same time calculate and separate natural disasters and target vibration events in the sparse term, and finally perform vibration detection and feedback on the target vibration events.

[0027] Step S200, create an optimization model according to the optical pulse echo matrix Create an optimization model.

[0028] The optimization model is used to optimize the optical pulse echo matrix according to the confidence coefficient so as to have higher accuracy in subsequent solutions. The confidence coefficient is used to weight the noise term and measure the reliability of the received signal at each position at each moment.

[0029] Accordingly, before creating the optimization model, this embodiment also specifically sets the confidence coefficient . As an implementable manner, setting the confidence coefficient includes setting the tidal confidence coefficient and the natural disaster confidence coefficient . Specifically, the steps of setting the tidal confidence coefficient are as follows: Predict the expected echo data according to the tidal pattern . Among them, the backscattered optical pulse signals in the OTDR monitoring area during the past astronomical tidal cycle are corresponded to the fiber sampling Rayleigh curve, and the above tidal pattern is obtained by fitting. The tidal pattern is a mode of the fiber sampling Rayleigh curve. Since the data perturbation during tides has a certain pattern and has a strong correlation with the water level change, the optical pulse echo data affected by tides also has periodic changes. The tidal pattern is established by analyzing the echo signals during the past astronomical tidal cycle. Therefore, the tidal pattern is essentially a sampling Rayleigh curve with a fixed-period fluctuation component. According to the tidal pattern prediction, the corresponding moment can be obtained and position of the expected echo data .

[0030] Based on the difference between the actually detected optical pulse echo data R i,j and the expected echo data , the tidal confidence coefficient is calculated with reference to the following formula : ; In the formula, is an adjustment parameter used to adjust the magnitude of the absolute value in the formula. R i,j is the optical pulse echo data during actual monitoring, that is, the optical pulse echo matrix at the corresponding time and position of the element

[0031] It should be noted that in this embodiment, the periodic interference of the tidal event is excluded by the predicted value of the historical data and the actual data monitoring value. If there is a periodic fluctuation and it is consistent with the expected tidal pattern, then the tidal confidence coefficient is higher; if the fluctuation is caused by other interference sources or sensor failures, it will deviate from the tidal pattern, and the data difference is large, resulting in a large absolute value in the formula, and the corresponding tidal confidence coefficient is lower

[0032] Next, the natural disaster confidence coefficient is calculated with reference to the following formula ; In the formula, is the optical pulse echo data R at the corresponding time and position in the optical pulse echo matrix i,j of the noise level is the confidence decay control coefficient

[0033] Since natural disasters such as earthquakes usually cause non-periodic and relatively strong vibrations or drastic changes, which are significantly different from the regular periodic fluctuations during tides. During natural disasters, sensors are extremely prone to failure or abnormality, resulting in an increase in data error. Therefore, the confidence coefficient during natural disasters is calculated based on the mutation type and noise level of the data. If there are significant interference signals in the data, then the natural disaster confidence coefficient is lower; if the data has no significant interference and / or conforms to the expected fluctuations under natural disasters, then the natural disaster confidence coefficient is higher

[0034] As an implementable manner, step S200 includes the following steps: Step S210, according to the marine environment, set the confidence coefficient as the tidal confidence coefficient , or set it as the natural disaster confidence coefficient.

[0035] Specifically, the marine environment includes tidal events and natural disaster events such as earthquakes and tsunamis. Refer to the following formula for the confidence coefficient matrix: ; In the formula, is the tidal deviation threshold, which is obtained by corresponding the backscattered optical pulse signals in the OTDR monitoring area within the past astronomical tidal cycle to the fiber sampling Rayleigh curve and then training. According to the actually detected optical pulse echo data R i,j and the expected echo data calculate the tidal confidence coefficient . When the calculation result is greater than the tidal deviation threshold , it is considered that the marine environment corresponding to the optical pulse echo data R i,j is a tidal event, and then take the calculation result as the confidence coefficient at the corresponding time and position . When the calculation result is less than or equal to the tidal deviation threshold , it is considered that the marine environment corresponding to the optical pulse echo data R i,j deviates from the tidal event and is a natural disaster event. Calculate the natural disaster confidence coefficient and the confidence decay control coefficient to obtain the natural disaster confidence coefficient as the confidence coefficient at the corresponding time and position .

[0036] Step S220, introduce the confidence coefficient set in step S210 to obtain an optimized model. As shown in the following formula: ; In the formula, perform an element-wise product calculation on the confidence coefficient and the noise term, indicating that the matrix operation is the Hadamard product, also known as the element-wise product. Take the F norm of the calculation result of the element-wise product, also known as the Frobenius norm, to measure the fitting error of the optimized model.

[0037] Perform singular value decomposition on the low-rank term and sum the singular values to obtain the low-rank term The nuclear norm is used to control the low-rank term of the rank.

[0038] According to the sparse term the number of non-zero elements of, the zero norm of the sparse term is obtained to control the sparsity of the sparse term .

[0039] The sum of the square of the F norm, the weighted nuclear norm, and the weighted zero norm is obtained to get the optimization model. Wherein and are regularization parameters used to balance the low-rank term and the sparse term weights.

[0040] Before solving the optimization model, each element in the confidence coefficient matrix is corrected in this embodiment to further enhance the robustness of the confidence coefficient matrix. The correction process refers to the following formula: ; In the formula, the tidal confidence coefficient is the confidence coefficient and position at the corresponding moment during the tidal event ; the natural disaster confidence coefficient is the confidence coefficient and position at the corresponding moment during the natural disaster event .

[0041] is the time-space neighborhood of the moment and position , and the neighborhood contains the moment t k and position x l ; correspondingly, is the confidence coefficient k and position x l at the corresponding moment t during the tide ; is the confidence coefficient k and position x l at the corresponding moment t during the natural disaster event .

[0042] During correction, adjacent data points are first taken according to the reception moment i,j and reception position of the optical pulse echo data R , that is, the adjacent elements of the element R in the optical pulse echo matrix i,j . For example, the optical pulse echo data R i-1,j 、Ri+1,j , R i,j-1 , R i,j+1 etc. In this embodiment, 3 adjacent elements can be taken as adjacent data points to determine the neighborhood range.

[0043] Since the received signals at adjacent positions or adjacent times have a certain similarity, the confidence coefficient of the current signal can be corrected and adjusted through the adjacent received signals. Calculate the weighted mean of the confidence coefficient w k,l of the data points within the time and position i,j to correct the confidence coefficient w . And so on, correct each element in the confidence coefficient matrix. Through the correlation of adjacent data points in the time - space neighborhood, the confidence coefficient

[0044] Step S300: Solve the optimization model in Step S200 to obtain the sparse term corresponding sparse term estimation matrix .

[0045] In this embodiment, the sparse term in the optimization model is solved by the Alternating Direction Method of Multipliers (ADMM) to obtain the sparse term estimation matrix . The specific steps are as follows: Introduce the Lagrange multiplier matrix; Initialize the noise term , the low - rank term , the sparse term and the Lagrange multiplier matrix; Alternately update the noise term , the low - rank term , the sparse term and the Lagrange multiplier matrix, and repeat the iteration; Stop when the iteration termination condition is met and output the sparse term corresponding sparse term estimation matrix .

[0046] The ADMM algorithm is an algorithm for solving optimization problems, which combines the ideas of the augmented Lagrangian function and the dual ascent algorithm and has been widely used in many fields such as machine learning, signal processing, image processing, and statistical analysis. Using the ADMM algorithm to optimize and solve the optimization model, the obtained sparse term estimation matrix It includes natural disaster events and target vibration events.

[0047] Step S400: Detect natural disaster events and vibration events in the received signal according to the sparse term estimation matrix As an implementable manner, step S400 includes the following steps:

[0048] Step S410: Analyze the sparse non-zero elements of the sparse term estimation matrix and detect natural disaster events according to the sparse term estimation matrix . Specifically, it includes: Step S411: Quantitatively analyze the signal mutation based on the change amount of the optical pulse echo data at adjacent moments at the same position, and calculate the signal mutation degree according to the quantitative analysis result and the noise level . The signal mutation degree is calculated with reference to the following formula: Δx i,j =R i,j -R i,j-1 ; ; In the formula, R i,j is the optical pulse echo data at the corresponding moment and position . R i,j-1 is the optical pulse echo data at the corresponding moment t j-1 and position , that is, the adjacent moment data of R i,j . Δx i,j =R i,j -R i,j-1 represents the signal change amount at the adjacent moments at the position and quantifies the signal mutation degree. is the noise level of the optical pulse echo data R i,j at the corresponding moment and position . C i,j is the signal mutation degree at the corresponding moment and position .

[0049] Step S412: Calculate the reconstruction confidence level α i,j of the natural disaster according to the signal mutation degree C i,j . The reconstruction confidence level α i,j is calculated with reference to the following formula: ; In the formula, is the adjustment parameter used to control the sensitivity of the reconstruction confidence level to the mutability.

[0050] When the adjustment parameter is large, the mutability of the signal has a great influence on the reconstruction confidence level α i,j ; when the adjustment parameter is small, the influence of the mutation on the reconstruction confidence level α i,j is small.

[0051] Step S413, set the mutation threshold and the reconstruction confidence level threshold .

[0052] When a natural disaster event occurs, the signal often shows a drastic mutation. When the signal mutation degree C i,j calculated in step S411 is greater than the mutation threshold , and the reconstruction confidence level α i,j calculated in step S412 is less than the reconstruction confidence level threshold , detect the optical pulse echo data R at the current moment and the position i,j corresponding to the event as a natural disaster event.

[0053] When this condition is not satisfied , the optical pulse echo data R at the current moment and the position i,j corresponding to the event is not a natural disaster event.

[0054] Step S420, set the elements corresponding to the natural disaster event in the sparse term estimation matrix to zero.

[0055] When , .

[0056] Do not process the elements excluding the natural disaster event in step S410. The processing of the sparse term estimation matrix is to separate the natural disaster event and the target vibration event, and separate and exclude the influence of the natural disaster event on the detection of the target vibration event.

[0057] Step S430, according to the sparse term estimation matrix after setting to zero, detect the vibration event by event dictionary learning or modal decomposition method.

[0058] Among them, event dictionary learning requires initializing the dictionary matrix, and the column vectors in the dictionary matrix are set to a vibration mode. For the sparse term estimation matrix For each column vector, the sparse coefficients are solved, and the dictionary matrix is updated according to the sparse coefficients to continuously optimize the representation ability of the dictionary. Finally, the obtained sparse coefficients are analyzed. If a certain sparse coefficient has a large non-zero value at the position corresponding to a column vector of a dictionary matrix, it indicates that the vibration mode represented by this column of the dictionary matrix exists in the column vector of the corresponding sparse term estimation matrix exists.

[0059] The modal decomposition method is to perform modal decomposition on the sparse term estimation matrix after setting to zero to obtain a series of modal components. Features are extracted for each modal component, and these features can reflect the characteristics of different vibration events. According to the extracted features, by setting thresholds or using machine learning classification algorithms, it is determined whether each modal component corresponds to a vibration event.

[0060] For the sparse term estimation matrix after setting to zero , when performing target vibration event detection, other methods can also be selected according to detection requirements, not limited to this.

[0061] The method for detecting submarine optical fiber vibration events based on trust - degree weighting provided in this embodiment introduces a trust - degree coefficient to measure the reliability of data, and dynamically adjusts the reliability evaluation of signals according to different ocean environments. The low - rank and sparse decomposition model is used to decompose the OTDR signal, so as to distinguish noise from vibration events, and the event detection accuracy and accuracy are better.

[0062] Combining the trust - degree coefficient with the spatio - temporal characteristics of the OTDR signal can effectively cope with environmental interferences such as tides, and accurately detect vibration events caused by natural disasters. It maintains strong robustness in complex and multi - interference ocean environments and is not easily affected by interference sources. Through the smooth adjustment and mutation analysis of trust - degree, the possibility of false detection and false alarm is effectively reduced, and the actual application effect of the system is improved.

[0063] Through the method provided in this embodiment, not only can sudden events caused by natural disasters be detected, but also other types of events such as tides and local vibrations can be effectively distinguished, with wide applicability. It realizes the real - time analysis of OTDR back - scattered optical pulse data, helps to quickly respond to emergencies in submarine optical fiber networks, take timely measures, and improve the automation level of the system.

[0064] This embodiment also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the above - mentioned method for detecting submarine optical fiber vibration events based on trust - degree weighting.

[0065] This embodiment also 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 execute the above-mentioned method for detecting submarine optical fiber vibration events based on confidence weighting.

[0066] An embodiment of the present invention also provides an electronic device, including: 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 the computer program, when executed by the at least one processor, is used to cause the electronic device to execute the above-mentioned method for detecting submarine optical fiber vibration events based on confidence weighting.

[0067] The structural block diagram of an electronic device that can be a server or a client as an embodiment of the present invention will now be described. It is an example of a 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 devices, 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 processors, 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 claimed herein.

[0068] As Figure 2 shown, the electronic device includes a computing unit 101, which can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 102 or the computer program loaded from the storage unit 108 into the random access memory (RAM) 103. In the RAM 103, various programs and data required for the operation of the electronic device can also be stored. The computing unit 101, the ROM 102, and the RAM 103 are connected to each other through a bus 104. The input / output (I / O) interface 105 is also connected to the bus 104.

[0069] 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 the user settings and / or function controls 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, magnetic disks and optical discs. 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.

[0070] The computing unit 101 can be various general-purpose and / or special-purpose processing components 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 dedicated artificial intelligence (AI) computing units, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 101 executes the various methods and processes described above. For example, in some embodiments, the method embodiments of the present invention can be implemented as a computer program tangibly embodied in a machine-readable medium, such as the storage unit 108. In some embodiments, part or all of the computer program can 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 can be configured to execute the above-described methods in any other suitable manner (e.g., by means of firmware).

[0071] The computer program for implementing the method of the embodiments of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the computer programs are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, executed as an independent software package partially on the machine and partially on a remote machine, or executed entirely on a remote machine or server.

[0072] In the context of embodiments of the present inventive concept, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection 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 the machine-readable storage medium would 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0073] It should be noted that the term "including" and its variations used in the embodiments of the present inventive concept are open-ended, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "an embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "a plurality" mentioned in the embodiments of the present inventive concept are illustrative rather than restrictive. Those skilled in the art should understand that, unless clearly specified otherwise in the context, it should be construed as "one or more".

[0074] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present inventive concept are all information and data that have been authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of the relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entrances are provided for the user to select to authorize or reject.

[0075] The various steps recited in the method embodiments provided by the embodiments of the present inventive concept may be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The protection scope of the present inventive concept is not limited in this regard.

[0076] As used in this specification, the term "embodiment" means that the specific features, structures or characteristics described in connection with an embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily mean the same embodiment, nor does it mean that it is independent or alternative to other embodiments and mutually exclusive. The embodiments in this specification are all described in a related manner, and the same or similar parts among the embodiments are cross-referenced. In particular, for the embodiments of the device, equipment, and system, 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 embodiments.

[0077] The above-described embodiments merely represent several implementation manners of the present invention, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation of the protection scope. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the appended claims.

Claims

1. A method for detecting submarine optical fiber vibration events based on trust - weighted, characterized in that, The method includes: Obtaining an optical pulse echo matrix based on the received signal; wherein, the optical pulse echo matrix includes a noise term, a low-rank term, and a sparse term; Creating an optimization model based on the optical pulse echo matrix, wherein the optimization model is used to optimize the optical pulse echo matrix according to a confidence coefficient, the confidence coefficient is used to weight the noise term, and the confidence coefficient is set as a tidal confidence coefficient or a natural disaster confidence coefficient according to the ocean environment; Solving the optimization model to obtain a sparse term estimation matrix corresponding to the sparse term; Detecting natural disaster events and vibration events in the received signal according to the sparse term estimation matrix.

2. The method for detecting submarine optical fiber vibration events based on trust degree weighting according to claim 1, wherein Before creating the optimization model based on the optical pulse echo matrix, the method further includes: Predicting expected echo data according to the tidal pattern; Calculating the tidal confidence coefficient according to the difference between the 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 method for detecting submarine optical fiber vibration events based on trustworthiness weighting according to claim 1, wherein Before creating the optimization model based on the optical pulse echo matrix, the method further includes: Calculating the natural disaster confidence coefficient according to the noise level of the optical pulse echo data; wherein, the optical pulse echo data is obtained based on the received signal.

4. The method for detecting submarine optical fiber vibration events based on trustworthiness weighting according to claim 1, wherein Creating the optimization model based on the optical pulse echo matrix includes: According to the ocean environment, setting the confidence coefficient as the tidal confidence coefficient, or setting it as the natural disaster confidence coefficient; Performing an element-wise product calculation on the confidence coefficient and the noise term, and taking the F-norm of the calculation result; Performing singular value decomposition on the low-rank term, and summing the singular values to obtain the nuclear norm of the low-rank term; Obtaining the zero norm of the sparse term according to the number of non-zero elements of the sparse term; Summing the square of the F-norm, the weighted nuclear norm, and the weighted zero norm to obtain the optimization model.

5. The method for detecting submarine optical fiber vibration events based on trust degree weighting according to claim 1, wherein Before solving the optimization model to obtain the sparse term estimation matrix, the method further includes: Determining a neighborhood range by taking adjacent data points according to the reception time and reception position of the optical pulse echo data; Correcting the confidence coefficient by the mean value of multiple adjacent data points.

6. The method for detecting submarine optical fiber vibration events based on trust degree weighting according to claim 1, wherein Solving the optimization model to obtain the sparse term estimation matrix includes: Introducing a Lagrange multiplier matrix; Initializing the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix; Performing alternating updates on the noise term, the low-rank term, the sparse term, and the Lagrange multiplier matrix, and repeating the iteration; Stopping and outputting the sparse term estimation matrix when the iteration termination condition is satisfied.

7. The method for detecting submarine optical fiber vibration events based on trust degree weighting according to claim 1, wherein Detecting natural disaster events and vibration events in the received signal according to the sparse term estimation matrix includes: Detecting natural disaster events according to the sparse term estimation matrix; Setting to zero the elements corresponding to the natural disaster events in the sparse term estimation matrix; Detecting vibration events according to the zeroed sparse term estimation matrix through event dictionary learning or modal decomposition method.

8. The method for detecting submarine optical fiber vibration events weighted based on trust as claimed in claim 7, wherein Detecting natural disaster events according to the sparse term estimation matrix includes: Calculating the signal mutation degree according to the change amount and noise level of the optical pulse echo data at adjacent times at the same position; Calculate the reconstruction confidence of natural disasters according to the signal mutation degree; Set the mutation threshold and the 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 includes instructions that, when executed by the processor, cause the processor to execute the method for detecting submarine optical fiber vibration events weighted by trust 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 weighted by trust according to any one of claims 1 to 8 is implemented.

Images