Submarine cable burial depth detection method and device, server and storage medium
By using the temperature data and neural network model of the optical fibers inside the submarine cable, the problem of inaccurate burial depth measurement caused by weak signal in deep water environments is solved, and a more accurate detection of submarine cable burial depth is achieved.
Patent Information
- Application Number
- CN202411216463.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-30
AI Technical Summary
In the prior art, the signal of the marine magnetometer is not obvious when the water depth is greater than 50 meters, resulting in inaccurate measurement of the burial depth of the submarine cable.
By obtaining the center frequency data of the optical fiber inside the submarine cable, calculating the temperature data, and then marking it according to the temperature interval, it is input into the trained neural network model to predict the buried depth value of the submarine cable.
The accuracy of submarine cable burial depth detection is improved, especially when the water depth is greater than 50 meters, ensuring the reliability of burial depth measurement.
Smart Images

Figure CN119089216A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of submarine cable technology, and in particular to a method, device, server and storage medium for detecting the buried depth of a submarine cable. Background Art
[0002] Submarine cable communication has become the main technical means of communication between islands due to its advantages of long transmission distance, low loss and good confidentiality. In order to protect submarine cables from the influence of the natural environment, cables are usually buried under the seabed. However, when the cables buried under the seabed are affected by tides or ocean currents, they will be exposed to the seabed and damaged by friction, causing them to lose or even break. Therefore, it is very necessary to measure the buried depth of submarine cables.
[0003] In the prior art, the traditional method for detecting the buried depth of submarine cables mainly relies on operators to use marine magnetometers to detect the buried depth of submarine cables, and to clearly identify the coordinate position of the submarine cables to display the buried depth scene of the submarine cables.
[0004] However, in the prior art, the traditional submarine cable burial depth detection method has an obvious marine magnetometer signal when the water depth is less than 50 meters, and the coordinate position of the submarine cable can be clearly identified; but when the water depth is greater than 50 meters, the marine magnetometer signal is not obvious, which can easily lead to inaccurate measurement of the submarine cable burial depth. Summary of the invention
[0005] The present application provides a method, device, server and storage medium for detecting the buried depth of a submarine cable, so as to solve the problem that when the water depth is greater than 50 meters, the signal of the ocean magnetometer is not obvious, which easily leads to inaccurate measurement of the buried depth of the submarine cable.
[0006] In a first aspect, the present application provides a method for detecting the buried depth of a submarine cable, which is applied to a server, comprising:
[0007] Obtain the center frequency data of the optical fiber inside the submarine cable to be detected within a preset time;
[0008] Calculating temperature data of the optical fiber according to the center frequency data;
[0009] Marking corresponding temperature intervals according to the temperature data of the optical fiber to obtain marked temperature data;
[0010] The labeled temperature data is input into a trained neural network model for processing to obtain a corresponding predicted burial depth label;
[0011] Determine the corresponding submarine cable burial depth value according to the predicted burial depth label;
[0012] Output the buried depth value of the submarine cable.
[0013] In a possible design, the training process of the trained neural network model includes: obtaining the temperature data of the submarine cable optical fiber within a preset time from a preset sample library; controlling the sonar device to obtain the submarine cable burial depth data within the preset time; correspondingly marking the temperature data of the optical fiber in different temperature ranges to obtain each marked temperature data; matching the corresponding submarine cable burial depth data according to each marked temperature data to obtain a sample data set, and determining part of the data in the sample data set as a training set; creating a neural network model and setting an initial weight combination value; inputting the training set into the neural network model for iterative loop, and outputting the actual weight combination value each time through a preset feedback network. The network processes the actual weight combination value and the preset expected weight to correct the actual weight combination value until a final actual weight combination value is output; determines whether the difference between the final actual weight combination value and the expected weight is less than a preset error; if the difference between the final actual weight combination value and the expected weight is less than the preset error, outputs the trained predicted depth label to complete the training of the neural network model; if the difference between the final actual weight combination value and the expected weight is not less than the preset error, modifies the neural network model to obtain a modified neural network model, and inputs the training set into the modified neural network model for a re-iterative cycle until the training of the neural network model is completed.
[0014] In a possible design, it also includes: determining part of the data in the sample data set as a test set, and determining the true burial depth label corresponding to the test set; inputting the test set into the trained neural network model for prediction processing to obtain the corresponding predicted burial depth label; determining the evaluation value corresponding to the predicted burial depth label based on the true burial depth label; if the evaluation value meets the preset accuracy rate, it is determined that the test of the trained neural network model is completed.
[0015] In a possible design, the different temperature intervals include abnormal temperature intervals and normal temperature intervals; accordingly, the temperature data of the optical fiber in different temperature intervals are marked accordingly to obtain each marked temperature data, including: marking the temperature data of the optical fiber in the abnormal temperature interval accordingly to obtain first marked temperature data; marking the temperature data of the optical fiber in each normal temperature interval accordingly to obtain second marked temperature data; accordingly, matching the corresponding submarine cable burial depth data according to each marked temperature data to obtain a sample data set, including: matching the corresponding submarine cable burial depth data according to the first marked temperature data and the first marked temperature data respectively to obtain a sample data set.
[0016] In a possible design, the weight combination value is a weight and a threshold; accordingly, the actual weight combination value and the preset expected weight are processed by a preset feedback network to correct the actual weight combination value, and the calculation formula is:
[0017] W new =W old -μ*X
[0018] Where W new is the actual weight after correction; W old is the preset expected weight; μ is the learning rate set to 0.01; X is the gradient of the loss function in the preset feedback network with respect to the weight.
[0019] In a possible design, the evaluation value is an accuracy rate; accordingly, the calculation formula for determining the evaluation value corresponding to the predicted burial depth label according to the actual burial depth label is:
[0020]
[0021] Wherein, Accuracy is the accuracy of the predicted burial depth label; TP is the number of correctly predicted positive examples in the predicted burial depth label determined according to the true burial depth label; TN is the number of correctly predicted negative examples in the predicted burial depth label determined according to the true burial depth label; FP is the number of incorrectly predicted positive examples in the predicted burial depth label determined according to the true burial depth label; FN is the number of incorrectly predicted negative examples in the predicted burial depth label determined according to the true burial depth label.
[0022] In a possible design, the temperature data of the optical fiber is calculated according to the center frequency data, and the calculation formula is:
[0023] in
[0024] Wherein, ΔT is the change temperature corresponding to the temperature data of the optical fiber; Δλ B is the variable wavelength; B is the initial wavelength; ξ is the thermo-optic coefficient; c is the speed of light; f0 is the center frequency.
[0025] In a second aspect, the present application provides a submarine cable buried depth detection device, which is applied to a server, comprising:
[0026] The first acquisition module is used to obtain the center frequency data of the optical fiber inside the submarine cable at the buried depth to be detected within a preset time period;
[0027] A calculation module, used for calculating the temperature data of the optical fiber according to the center frequency data;
[0028] A first marking module, used for marking a corresponding temperature interval according to the temperature data of the optical fiber to obtain marked temperature data;
[0029] A first processing module is used to input the labeled temperature data into a trained neural network model for processing to obtain a corresponding predicted burial depth label;
[0030] A first determination module, used to determine a corresponding submarine cable burial depth value according to the predicted burial depth label;
[0031] The first output module is used to output the submarine cable burial depth value.
[0032] In a third aspect, the present application provides a server, comprising: at least one processor and a memory;
[0033] The memory stores computer-executable instructions;
[0034] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method for detecting the buried depth of the submarine cable as described in the first aspect and various possible designs of the first aspect.
[0035] In a fourth aspect, the present application provides a computer storage medium storing computer execution instructions. When a processor executes the computer execution instructions, the method for detecting the buried depth of a submarine cable as described in the first aspect and various possible designs of the first aspect is implemented.
[0036] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the method for detecting the buried depth of a submarine cable as described in the first aspect and various possible designs of the first aspect.
[0037] The present application provides a method, device, server and storage medium for detecting the buried depth of a submarine cable, which obtains the center frequency data of the internal optical fiber of the submarine cable whose buried depth is to be detected within a preset time; calculates the temperature data of the optical fiber according to the center frequency data; labels the corresponding temperature interval according to the temperature data of the optical fiber to obtain the labeled temperature data; inputs the labeled temperature data into a trained neural network model for processing to obtain the corresponding predicted buried depth label; determines the corresponding submarine cable buried depth value according to the predicted buried depth label; and outputs the submarine cable buried depth value, so that the detection of the buried depth of the submarine cable is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0039] Figure 1 A schematic diagram of an application scenario of a method for detecting the buried depth of a submarine cable provided in an embodiment of the present application;
[0040] Figure 2 Schematic diagram of the process of detecting the buried depth of submarine cables provided in the embodiment of the present application Figure 1 ;
[0041] Figure 3 Schematic diagram of the process of detecting the buried depth of submarine cables provided in the embodiment of the present application Figure 2 ;
[0042] Figure 4 A schematic diagram of the structure of a submarine cable buried depth detection device provided in an embodiment of the present application;
[0043] Figure 5 A schematic diagram of the hardware structure of the server provided in an embodiment of the present application. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0045] Submarine cable communication has become the main technical means for international intercontinental, continental and island communications, and island-to-island communications due to its advantages of long transmission distance, large capacity, low loss, high reliability, and good anti-interference and confidentiality. In order to protect the cables from the influence of natural environment and human factors, the cables are usually buried under the seabed. However, due to the complex underwater environment, as time goes by, some cable sections originally buried under the seabed will be exposed above the seabed. When affected by tides or ocean currents, the exposed cables may be repeatedly damaged by friction, or the cables may be suspended and periodically swung or twisted due to ocean currents. This long-term friction will damage the optical fiber inside the cable, causing it to lose or even break. Therefore, it is very necessary to measure the burial depth of the submarine cable. In the prior art, the traditional submarine cable burial depth detection method mainly uses operators to use marine magnetometers to detect the burial depth of the submarine cable, and clearly identify the coordinate position of the submarine cable to display the burial depth scene of the submarine cable. However, in the prior art, the traditional submarine cable burial depth detection method has an obvious marine magnetometer signal when the water depth is less than 50 meters, and the coordinate position of the submarine cable can be clearly identified; but when the water depth is greater than 50 meters, the marine magnetometer signal is not obvious, which can easily lead to inaccurate measurement of the submarine cable burial depth.
[0046] In order to solve the above technical problems, the embodiments of the present application propose the following technical concept: Taking into account the problem of inaccurate measurement of submarine cable burial depth by marine magnetometers in the prior art, the inventors perform temperature interval marking based on the temperature data of the optical fiber inside the submarine cable to obtain marked temperature data, and use a trained neural network model to process the marked temperature data to obtain a corresponding predicted burial depth label, so as to determine and output the submarine cable burial depth according to the predicted burial depth label, thereby making the detection of the submarine cable burial depth more accurate.
[0047] Figure 1 It is a schematic diagram of an application scenario of the method for detecting the buried depth of a submarine cable provided in an embodiment of the present application.
[0048] like Figure 1 As shown, the scenario includes: a display terminal 101 and a server 102 .
[0049] The display terminal 101 may be a display screen or a terminal such as a personal computer.
[0050] The server 102 may be an independent server or a cluster consisting of multiple servers.
[0051] The server 102 obtains the center frequency data of the optical fiber inside the submarine cable with the buried depth to be detected within the preset time from the database, calculates the temperature data of the optical fiber according to the center frequency data, and marks the temperature data of the optical fiber with a temperature interval, inputs the marked temperature data into the trained neural network model for processing to obtain the corresponding predicted buried depth label, and determines the corresponding submarine cable buried depth value according to the predicted buried depth label, so as to output the submarine cable buried depth value to the display terminal 101 through the wireless network for display. The following is a detailed description using a detailed embodiment.
[0052] Figure 2 Schematic diagram of the process of detecting the buried depth of submarine cables provided in the embodiment of the present application Figure 1 , the execution subject of this embodiment can be Figure 1 The server in the embodiment shown is not particularly limited in this embodiment. Figure 2 As shown, the method includes:
[0053] S201: Acquire the center frequency data of the optical fiber inside the submarine cable at the buried depth to be detected within a preset time.
[0054] In this embodiment, the preset time may be any time within a month, half a year or a year, or may be other time.
[0055] In this embodiment, the center frequency data will change accordingly as the buried depth of the submarine cable changes at different locations.
[0056] S202: Calculate temperature data of the optical fiber according to the center frequency data.
[0057] In this embodiment, the temperature data of the optical fiber is calculated according to the center frequency data, and the calculation formula is:
[0058] in
[0059] Where ΔT is the change temperature corresponding to the temperature data of the optical fiber; Δλ B is the variable wavelength; B is the initial wavelength; ξ is the thermo-optical coefficient; c is the speed of light; f0 is the center frequency.
[0060] S203: marking corresponding temperature intervals according to the temperature data of the optical fiber to obtain marked temperature data.
[0061] In this embodiment, the temperature interval may be one or more temperature span intervals of 2° C., 4° C., or 6° C., or may be other temperature span intervals.
[0062] Exemplarily, the corresponding temperature span intervals of 2° C. and 4° C. are marked according to the temperature data of the optical fiber, so that the marked temperature data are obtained as the first temperature data and the second temperature data.
[0063] S204: Input the labeled temperature data into the trained neural network model for processing to obtain a corresponding predicted burial depth label.
[0064] In this embodiment, the trained neural network model can be trained through an AI model or through a database.
[0065] In this embodiment, the predicted burial depth label is a mapping relationship between temperature and burial depth.
[0066] Exemplarily, the predicted burial depth label is the burial depth of the submarine cable corresponding to the first temperature data and the burial depth of the submarine cable corresponding to the second temperature data.
[0067] S205: Determine the corresponding submarine cable burial depth value according to the predicted burial depth label.
[0068] Exemplarily, the buried depth of the submarine cable at the location corresponding to the first temperature data is 1 m; and the buried depth of the submarine cable at the location corresponding to the second temperature data is 2 m.
[0069] S206: Output the buried depth value of the submarine cable.
[0070] Exemplarily, the buried depth of the submarine cable at the position corresponding to the first temperature data output on the display interface is 1 m, and the buried depth of the submarine cable at the position corresponding to the second temperature data is 2 m.
[0071] In summary, the method for detecting the buried depth of a submarine cable provided in the present embodiment obtains the center frequency data of the optical fiber inside the submarine cable of the buried depth to be detected within a preset time; calculates the temperature data of the optical fiber based on the center frequency data; performs corresponding temperature interval marking based on the temperature data of the optical fiber to obtain the marked temperature data; inputs the marked temperature data into a trained neural network model for processing to obtain a corresponding predicted buried depth label; determines the corresponding submarine cable buried depth value based on the predicted buried depth label; and outputs the submarine cable buried depth value, so that the detection of the submarine cable buried depth is more accurate.
[0072] In addition, this embodiment directly collects the optical fiber center frequency data inside the submarine cable for subsequent temperature and burial depth analysis, making it easier to obtain optical fiber temperature data.
[0073] Figure 3 Schematic diagram of the process of detecting the buried depth of submarine cables provided in the embodiment of the present application Figure 2 In the embodiment of the present application, Figure 2 Based on the embodiment provided, the specific training process of the trained neural network model in S204 is described in detail. Figure 3As shown, the method includes:
[0074] S301: Acquire temperature data of a submarine cable optical fiber within a preset time from a preset sample library.
[0075] In this embodiment, the preset sample database may be a MySQL database or other databases.
[0076] In this embodiment, the preset time may be any time within a month, half a year or a year, or may be other time.
[0077] S302: Control the sonar device to obtain submarine cable burial depth data within a preset time.
[0078] In this embodiment, the sonar device may be a side scan sonar device or other sonar devices.
[0079] S303: Correspondingly marking the temperature data of the optical fiber in different temperature ranges to obtain marked temperature data.
[0080] In this embodiment, the different temperature intervals include abnormal temperature intervals and normal temperature intervals; accordingly, step S303 specifically includes:
[0081] S3031: Correspondingly marking the temperature data of the optical fiber in the abnormal temperature range to obtain first marked temperature data.
[0082] In this embodiment, the abnormal temperature interval is an interval in which the temperature difference variation trend increases from small to large and then decreases from large to small within a preset time.
[0083] Exemplarily, the temperature data of the optical fiber in the abnormal temperature range is marked with 0, so that the temperature data after the first marking is the temperature data marked with 0.
[0084] S3032: Correspondingly marking the temperature data of the optical fiber in each normal temperature range to obtain second marked temperature data.
[0085] Exemplarily, each normal temperature interval may be [0, 2], [2, 4], and (4, +∞).
[0086] Exemplarily, the temperature data of [0, 2), [2, 4] and (4, +∞) are labeled accordingly, so that the temperature data after the second labeling are temperature data labeled with 1, temperature data labeled with 2 and temperature data labeled with 3 respectively.
[0087] S304: Match the corresponding submarine cable burial depth data according to each labeled temperature data to obtain a sample data set, and determine part of the data in the sample data set as a training set.
[0088] In this embodiment, the partial data in the sample data set may be any one of 70%, 80% or 90%, or other data.
[0089] Specifically, step S304 is specifically: according to the first annotated temperature data and the second annotated temperature data, respectively matching the corresponding submarine cable buried depth data to obtain a sample data set.
[0090] Exemplarily, the temperature data marked with 0 matches the corresponding submarine cable burial depth data that the submarine cable is above the seabed; the temperature data marked with 1 matches the corresponding submarine cable burial depth data that the submarine cable is below the seabed at an average depth of 1m; the temperature data marked with 2 matches the corresponding submarine cable burial depth data that the submarine cable is below the seabed at an average depth of 2m; the temperature data marked with 3 matches the corresponding submarine cable burial depth data that the submarine cable is below the seabed at an average depth of 3m.
[0091] S305: Create a neural network model and set initial weight combination values.
[0092] S306: Input the training set into the neural network model for an iterative cycle, and each time the actual weight combination value is output, the actual weight combination value and the preset expected weight are processed through the preset feedback network to correct the actual weight combination value until the final actual weight combination value is output.
[0093] In this embodiment, the weight combination value is a weight and a threshold; accordingly, the actual weight combination value and the preset expected weight are processed by a preset feedback network to correct the actual weight combination value, and the calculation formula is:
[0094] W new =W old -μ*X
[0095] Where W new is the actual weight after correction; W old is the preset expected weight; μ is the learning rate set to 0.01; X is the gradient of the loss function with respect to the weight in the preset feedback network.
[0096] S307: Determine whether the difference between the final actual weight combination value and the expected weight is less than a preset error.
[0097] In this embodiment, the preset error may be any error value among 5%, 10% or 15%, or may be other error values.
[0098] In addition, the preset error can also be a preset threshold. When the loss function of the model (such as the mean square error) is lower than a preset threshold, the training stops; or, when the last calculated loss function result is higher than the preset threshold and it is difficult for the model to converge, a maximum number of iterations is set. After the maximum number of iterations is reached, the model training ends and the label of the unknown data is predicted.
[0099] S308: If the difference between the final actual weight combination value and the expected weight is less than the preset error, the trained predicted burial depth label is output to complete the training of the neural network model.
[0100] S309: If the difference between the final actual weight combination value and the expected weight is not less than the preset error, the neural network model is modified to obtain a modified neural network model, and the training set is input into the modified neural network model for re-iteration cycle until the training of the neural network model is completed.
[0101] In addition, the testing process of the trained neural network model specifically includes steps a to d:
[0102] Step a: Determine part of the data in the sample data set as the test set, and determine the true burial depth label corresponding to the test set.
[0103] In this embodiment, the partial data in the sample data set may be any one of the remaining 30%, 20% or 10%, or may be other corresponding remaining data.
[0104] Step b: Input the test set into the trained neural network model for prediction processing to obtain the corresponding predicted burial depth label.
[0105] Step c: Determine the evaluation value corresponding to the predicted burial depth label according to the actual burial depth label.
[0106] In this embodiment, the evaluation value is the accuracy rate; accordingly, the evaluation value corresponding to the predicted burial depth label is determined according to the actual burial depth label, and the calculation formula is:
[0107]
[0108] Where Accuracy is the accuracy of the predicted depth label; TP is the number of correctly predicted positive examples in the predicted depth label determined according to the true depth label; TN is the number of correctly predicted negative examples in the predicted depth label determined according to the true depth label; FP is the number of incorrectly predicted positive examples in the predicted depth label determined according to the true depth label; FN is the number of incorrectly predicted negative examples in the predicted depth label determined according to the true depth label.
[0109] In addition, the evaluation value may also be a recall rate, an F1 value, or other calculated values.
[0110] Step d: If the evaluation value meets the preset accuracy, it is determined that the test of the trained neural network model is completed.
[0111] In this embodiment, the preset accuracy rate may be any one of 70%, 80% or 90%, or other accuracy rates.
[0112] In summary, the method for detecting the buried depth of a submarine cable provided in the present embodiment obtains the temperature data of the submarine cable optical fiber within a preset time from a preset sample library; controls the sonar device to obtain the buried depth data of the submarine cable within a preset time; marks the temperature data of the optical fiber in different temperature ranges accordingly, and matches the corresponding buried depth data of the submarine cable according to each marked temperature data, and determines part of the data in the sample data set as a training set; inputs the training set into the created neural network model for an iterative cycle, and processes the actual weight combination value and the preset expected weight through a preset feedback network to correct the actual weight combination value; determines whether the difference between the final actual weight combination value and the expected weight is less than a preset error; if so, outputs the trained predicted buried depth label; if not, modifies the neural network model to obtain a modified neural network model, and inputs the training set into the modified neural network model for a re-iterative cycle until the training of the neural network model is completed, which can make the subsequent detection of the buried depth of the submarine cable more accurate.
[0113] In addition, this embodiment realizes the online detection of the buried depth of the submarine cable and the real-time online monitoring of multiple channels and multiple links by training the corresponding neural network model, while also reducing the detection cost of the buried depth of the submarine cable.
[0114] Figure 4 This is a schematic diagram of the structure of a submarine cable buried depth detection device provided in an embodiment of the present application. Figure 4 As shown, the submarine cable buried depth detection device includes: a first acquisition module 401, a calculation module 402, a first marking module 403, a first processing module 404, a first determination module 405 and a first output module 406.
[0115] The first acquisition module 401 is used to obtain the center frequency data of the optical fiber inside the submarine cable to be detected within a preset time period;
[0116] A calculation module 402, configured to calculate the temperature data of the optical fiber according to the center frequency data;
[0117] A first marking module 403 is used to mark the corresponding temperature interval according to the temperature data of the optical fiber to obtain marked temperature data;
[0118] A first processing module 404 is used to input the labeled temperature data into a trained neural network model for processing to obtain a corresponding predicted burial depth label;
[0119] A first determination module 405 is used to determine the corresponding submarine cable burial depth value according to the predicted burial depth label;
[0120] The first output module 406 is used to output the submarine cable burial depth value.
[0121] In a possible implementation manner, the device further includes:
[0122] The second acquisition module 407 is used to acquire the temperature data of the submarine cable optical fiber within a preset time from a preset sample library;
[0123] The third acquisition module 408 is used to control the sonar device to acquire the submarine cable burial depth data within the preset time;
[0124] A second marking module 409 is used to mark the temperature data of the optical fiber in different temperature intervals accordingly to obtain the marked temperature data;
[0125] A matching module 410 is used to match the corresponding submarine cable burial depth data according to the labeled temperature data to obtain a sample data set, and determine part of the data in the sample data set as a training set;
[0126] A creation module 411 is used to create a neural network model and set an initial weight combination value;
[0127] A first loop module 412 is used to input the training set into the neural network model for iterative loop, and each time when the actual weight combination value is output, the actual weight combination value and the preset expected weight are processed through a preset feedback network to correct the actual weight combination value until the final actual weight combination value is output;
[0128] A judgment module 413 is used to judge whether the difference between the final actual weight combination value and the expected weight is less than a preset error;
[0129] A second output module 414 is configured to output a trained predicted depth label if the difference between the final actual weight combination value and the expected weight is less than a preset error, so as to complete the training of the neural network model;
[0130] The second loop module 415 is used to modify the neural network model to obtain a modified neural network model if the difference between the final actual weight combination value and the expected weight is not less than a preset error, and input the training set into the modified neural network model for re-iteration loop until the training of the neural network model is completed.
[0131] In a possible implementation manner, the device further includes:
[0132] A second determination module 416 is used to determine part of the data in the sample data set as a test set, and determine a true burial depth label corresponding to the test set;
[0133] The second processing module 417 is used to input the test set into the trained neural network model for prediction processing to obtain a corresponding predicted burial depth label;
[0134] A third determination module 418 is used to determine the evaluation value corresponding to the predicted burial depth label according to the actual burial depth label;
[0135] The fourth determination module 419 is used to determine that the test of the trained neural network model is completed if the evaluation value meets the preset accuracy.
[0136] In a possible implementation, the different temperature intervals include abnormal temperature intervals and normal temperature intervals; accordingly, the second marking module 409 specifically includes:
[0137] A first marking unit 4091 is used to mark the temperature data of the optical fiber in the abnormal temperature interval accordingly to obtain first marked temperature data;
[0138] A second marking unit 4092, configured to mark the temperature data of the optical fiber in each normal temperature interval accordingly to obtain second marked temperature data;
[0139] Correspondingly, the matching module 410 is specifically used to match the corresponding submarine cable burial depth data according to the first annotated temperature data and the first annotated temperature data, respectively, to obtain a sample data set.
[0140] In a possible implementation, the weight combination value is a weight and a threshold; accordingly, the actual weight combination value and the preset expected weight are processed by a preset feedback network to correct the actual weight combination value, and the calculation formula is:
[0141] W new =W old -μ*X
[0142] Where W new is the actual weight after correction; W old is the preset expected weight; μ is the learning rate set to 0.01; X is the gradient of the loss function in the preset feedback network with respect to the weight.
[0143] In a possible implementation, the evaluation value is an accuracy rate; accordingly, the calculation formula for determining the evaluation value corresponding to the predicted burial depth label according to the actual burial depth label is:
[0144]
[0145] Wherein, Accuracy is the accuracy of the predicted burial depth label; TP is the number of correctly predicted positive examples in the predicted burial depth label determined according to the true burial depth label; TN is the number of correctly predicted negative examples in the predicted burial depth label determined according to the true burial depth label; FP is the number of incorrectly predicted positive examples in the predicted burial depth label determined according to the true burial depth label; FN is the number of incorrectly predicted negative examples in the predicted burial depth label determined according to the true burial depth label.
[0146] In a possible implementation, the temperature data of the optical fiber is calculated according to the center frequency data, and the calculation formula is:
[0147] in
[0148] Wherein, ΔT is the change temperature corresponding to the temperature data of the optical fiber; Δλ B is the variable wavelength; B is the initial wavelength; ξ is the thermo-optic coefficient; c is the speed of light; f0 is the center frequency.
[0149] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.
[0150] Figure 5 The hardware structure diagram of the server provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the server of this embodiment includes: a processor 501 and a memory 502; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the above submarine cable burial depth detection method.
[0151] Optionally, the memory 502 may be independent or integrated with the processor 501 .
[0152] When the memory 502 is independently provided, the server further includes a bus 503 for connecting the memory 502 and the processor 501 .
[0153] An embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method for detecting the buried depth of a submarine cable as described above is implemented.
[0154] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for detecting the buried depth of a submarine cable as described above is implemented.
[0155] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.
[0156] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.
[0157] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
[0158] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.
[0159] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
[0160] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.
[0161] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0162] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0163] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.
[0164] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for detecting the buried depth of a submarine cable, characterized in that: Applicable to servers, including: Obtain the center frequency data of the optical fiber inside the submarine cable at the buried depth to be detected within a preset time; Calculating temperature data of the optical fiber according to the center frequency data; Marking corresponding temperature intervals according to the temperature data of the optical fiber to obtain marked temperature data; The labeled temperature data is input into a trained neural network model for processing to obtain a corresponding predicted burial depth label; Determine the corresponding submarine cable burial depth value according to the predicted burial depth label; Output the buried depth value of the submarine cable.
2. The method according to claim 1, characterized in that The training process of the trained neural network model includes: Acquire temperature data of the submarine cable optical fiber within a preset time from a preset sample library; Controlling the sonar equipment to obtain the submarine cable burial depth data within the preset time; Correspondingly marking the temperature data of the optical fiber in different temperature intervals to obtain marked temperature data; Matching the corresponding submarine cable burial depth data according to the labeled temperature data to obtain a sample data set, and determining part of the data in the sample data set as a training set; Create a neural network model and set the initial weight combination value; Inputting the training set into the neural network model for iterative loop, and processing the actual weight combination value and the preset expected weight through a preset feedback network each time the actual weight combination value is output, so as to correct the actual weight combination value, until the final actual weight combination value is output; Determine whether the difference between the final actual weight combination value and the expected weight is less than a preset error; If the difference between the final actual weight combination value and the expected weight is less than a preset error, the trained predicted depth label is output to complete the training of the neural network model; If the difference between the final actual weight combination value and the expected weight is not less than a preset error, the neural network model is modified to obtain a modified neural network model, and the training set is input into the modified neural network model for a re-iterative cycle until the training of the neural network model is completed.
3. The method according to claim 2, characterized in that Also includes: Determine part of the data in the sample data set as a test set, and determine the true burial depth label corresponding to the test set; The test set is input into the trained neural network model for prediction processing to obtain the corresponding predicted burial depth label; Determine the evaluation value corresponding to the predicted burial depth label according to the actual burial depth label; If the evaluation value meets the preset accuracy, it is determined that the test of the trained neural network model is completed.
4. The method according to claim 2, characterized in that: The different temperature intervals include abnormal temperature intervals and normal temperature intervals; Correspondingly, the temperature data of the optical fiber in different temperature intervals are marked accordingly to obtain the marked temperature data, including: Correspondingly marking the temperature data of the optical fiber in the abnormal temperature interval to obtain first marked temperature data; Correspondingly marking the temperature data of the optical fiber in each normal temperature interval to obtain second marked temperature data; Accordingly, matching the corresponding submarine cable burial depth data according to the labeled temperature data to obtain a sample data set includes: According to the first annotated temperature data and the first annotated temperature data, the corresponding submarine cable burial depth data are matched respectively to obtain a sample data set.
5. The method according to claim 2, characterized in that: The weight combination value is a weight and a threshold; Accordingly, the actual weight combination value and the preset expected weight are processed by the preset feedback network to correct the actual weight combination value, and the calculation formula is: W new =W old -μ*X Where W new is the actual weight after correction; W old is the preset expected weight; μ is the learning rate set to 0.01; X is the gradient of the loss function with respect to the weight in the preset feedback network.
6. The method according to claim 3, characterized in that The evaluation value is the accuracy rate; Accordingly, the calculation formula for determining the evaluation value corresponding to the predicted burial depth label according to the actual burial depth label is: Wherein, Accuracy is the accuracy of the predicted burial depth label; TP is the number of correctly predicted positive examples in the predicted burial depth label determined according to the true burial depth label; TN is the number of correctly predicted negative examples in the predicted burial depth label determined according to the true burial depth label; FP is the number of incorrectly predicted positive examples in the predicted burial depth label determined according to the true burial depth label; FN is the number of incorrectly predicted negative examples in the predicted burial depth label determined according to the true burial depth label.
7. The method according to any one of claims 1 to 6, characterized in that: The calculation formula for calculating the temperature data of the optical fiber according to the center frequency data is: in Wherein, ΔT is the change temperature corresponding to the temperature data of the optical fiber; Δλ B is the variable wavelength; B is the initial wavelength; ξ is the thermo-optical coefficient; c is the speed of light; f0 is the center frequency.
8. A device for detecting the buried depth of a submarine cable, characterized in that: Applicable to servers, including: The first acquisition module is used to obtain the center frequency data of the optical fiber inside the submarine cable at the buried depth to be detected within a preset time period; A calculation module, used for calculating the temperature data of the optical fiber according to the center frequency data; A first marking module, used for marking a corresponding temperature interval according to the temperature data of the optical fiber to obtain marked temperature data; A first processing module is used to input the labeled temperature data into a trained neural network model for processing to obtain a corresponding predicted burial depth label; A first determination module, used to determine a corresponding submarine cable burial depth value according to the predicted burial depth label; The first output module is used to output the submarine cable burial depth value.
9. A server, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method for detecting the buried depth of a submarine cable as described in any one of claims 1 to 7.
10. A computer storage medium, characterized in that: The computer storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, the method for detecting the buried depth of a submarine cable as claimed in any one of claims 1 to 7 is implemented.
11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for detecting the buried depth of a submarine cable as claimed in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Method for measuring the burial depth of a line and device
CN110785681A
Buried cable temperature wireless monitoring system
CN113865727A
Cable fault type identification method based on deep learning
CN114545292A
Cable trench state monitoring method and device, storage medium and terminal
CN114777959A
Submarine cable burial depth detection system, method and device, computer equipment and program product
CN115166751A
