Submarine cable burial depth monitoring method, computer program product and electronic equipment

Abstract

The invention provides a submarine cable burial depth monitoring method, a computer program product and electronic equipment. The method comprises the following steps: acquiring basic temperature data of a to-be-measured space point in a first submarine cable in each unit time of a preset time period; the basic temperature data comprises soil temperature data; obtaining a feature set of the spatial point to be measured according to the basic temperature data; and inputting the feature set into a burial depth monitoring model to obtain burial depth data of the to-be-measured spatial point. And reasoning the feature set by using the burial depth monitoring model to obtain the burial depth data of the to-be-measured spatial point without calculating the heat dissipation condition, thereby reducing the error introduced by parameter estimation in the calculation, avoiding a large amount of grid calculation, saving the calculation resource, reducing the complexity of submarine cable burial depth measurement and calculation time consumption, and improving the calculation efficiency. And the burial depth measuring and calculating efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of submarine cable monitoring, and more specifically, to submarine cable burial depth monitoring methods, computer program products, and electronic equipment. Background Technology

[0002] With the vigorous development of offshore energy development and marine engineering projects, a large number of submarine cables have been laid for data and / or energy transmission. Ensuring the safety of these cables has become a key focus of subsequent maintenance. Monitoring the condition of submarine cables by measuring their burial depth and enabling early warning of problems can effectively protect the cables and reduce the risk of failures.

[0003] In traditional methods of calculating submarine cable burial depth, each measurement requires either ship-based surveying or manual underwater exploration. However, manual operations are time-consuming, labor-intensive, and inefficient; furthermore, underwater operations are difficult, costly, and dangerous for personnel.

[0004] In addition, some related technologies simulate the heat dissipation of submarine cables and soil under current load, and then extract the differences in heat dissipation at different burial depths to establish a mapping relationship to solve for the burial depth. However, this method is highly dependent on data and has high computational complexity, resulting in low efficiency in burial depth calculation. Summary of the Invention

[0005] The purpose of this application is to provide a method for monitoring the burial depth of submarine cables, a computer program product, and an electronic device, in order to improve at least one of the above-mentioned problems.

[0006] In a first aspect, embodiments of this application provide a method for monitoring the burial depth of a submarine cable, comprising: acquiring basic temperature data of a spatial point to be measured in a first submarine cable for each unit time within a preset time period; the basic temperature data including soil temperature data; obtaining a feature set of the spatial point to be measured based on the basic temperature data; inputting the feature set into a burial depth monitoring model to obtain the burial depth data of the spatial point to be measured; the burial depth monitoring model is obtained by regression modeling of the historical feature set corresponding to the spatial sampling point and the measured burial depth value.

[0007] In the above implementation process, the burial depth monitoring model is used to infer the feature set to obtain the burial depth data of the spatial points to be measured. There is no need to calculate the heat dissipation of the soil, which reduces the error introduced by parameter estimation in this part of the calculation, avoids a lot of grid calculation, saves computing resources, reduces the complexity of submarine cable burial depth measurement, and improves the efficiency of burial depth measurement.

[0008] Optionally, in this embodiment of the application, the basic temperature data further includes ambient temperature data; obtaining the feature set of the spatial point to be measured based on the basic temperature data includes: extracting features from the soil temperature data to obtain feature parameters of the spatial point to be measured; the feature parameters are used to reflect the periodic changes in the soil temperature of the spatial point to be measured; and concatenating the feature parameters and the ambient temperature data to obtain the feature set of the spatial point to be measured.

[0009] In the above implementation process, when constructing the feature set, not only the periodic changes in mud temperature at the measured spatial points were considered, but also the ambient temperature data. When the feature set contains information from multiple dimensions, the model can more comprehensively understand the data, improving the distortion problem and greatly enhancing the accuracy and interpretability of the burial depth monitoring model. For example, if ambient temperature data is not considered, and the feature set only contains the periodic change characteristic parameters of mud temperature at the measured spatial points, the relative burial depth of different spatial points can be determined by comparing these parameters within any given time window. The above method of constructing the feature set is faster and more convenient. However, considering that the periodic change characteristic parameters of mud temperature will fluctuate due to changes in ambient temperature when the time window changes, causing distortion in the model constructed based on the feature set, incorporating ambient temperature data into the parameters of the feature set is equivalent to standardizing the periodic change parameters of mud temperature, preventing them from fluctuating due to changes in ambient temperature, thereby enabling the estimation of the absolute burial depth.

[0010] Optionally, in this embodiment of the application, the preset time period includes at least one preset period, which is the period of mud temperature change; the step of extracting features from the mud temperature data to obtain the feature parameters of the spatial point to be measured includes: determining the parameters corresponding to the objective function characterizing the mud temperature change according to the preset period based on the mud temperature data, and using the parameters corresponding to the objective function as the feature parameters of the spatial point to be measured within the at least one preset period.

[0011] The parameters corresponding to the objective function directly reflect the characteristics of the objective function. Differences in the characteristics of different objective functions are all caused by the parameters corresponding to the objective function, and these parameters are directly related to the burial depth of the spatial point being measured. In the above implementation process, the parameters corresponding to the objective function characterizing the change of mud temperature according to a preset period are determined using soil temperature data. These parameters are then used as characteristic parameters, enabling them to more accurately describe the periodic changes in mud temperature, thereby improving the accuracy of the burial depth monitoring model based on these parameters. Furthermore, the characteristic parameters have clear meaning, enhancing the interpretability of the burial depth monitoring model.

[0012] Optionally, in this embodiment of the application, determining the parameters corresponding to the objective function characterizing the change of mud temperature according to the preset period based on the mud temperature data, and using them as feature parameters of the spatial point to be measured within the at least one preset period, includes: constructing the objective function in Fourier expansion form based on the mud temperature data, and using the parameters in the objective function as feature parameters of the spatial point to be measured within the preset period; or, fitting the objective function characterizing the change of mud temperature according to the preset period based on the mud temperature data, and using the parameters of the objective function as feature parameters of the spatial point to be measured within the preset period.

[0013] In the above implementation process, multiple feature extraction methods are provided. In some embodiments, feature parameters obtained based on Fourier series expansion can be selected; in other embodiments, feature parameters reflecting the periodic changes in mud temperature at the measured spatial point can be obtained by fitting an objective function. Among these, the advantage of feature parameters obtained based on Fourier series expansion is that they have better computational accuracy and can achieve more accurate fitting; the objective function is simple to calculate, but it may be necessary to try different objective function forms to obtain better fitting results.

[0014] Optionally, in this embodiment of the application, the ambient temperature data includes the average air temperature data and / or average water temperature data of the spatial point to be measured.

[0015] In the above implementation process, when constructing the feature set, the ambient temperature, which is not affected by load and burial depth, is also taken into account, including average air temperature data and / or average water temperature data. This improves the richness of the feature set, mitigates the problem of model distortion, and greatly enhances the accuracy and interpretability of the burial depth monitoring model.

[0016] Optionally, acquiring soil temperature data of the target spatial point in the first submarine cable within each unit time of a preset time period includes: acquiring temperature measurement data of the target spatial point within each unit time of the preset time period; and calculating initial temperature measurement data of the target spatial point within each unit time of the preset time period based on the temperature measurement data of the target spatial point within each unit time of the preset time period, wherein the initial temperature measurement data is the mean, median, or minimum value calculated based on the temperature measurement data within each unit time period.

[0017] After obtaining the initial temperature measurement data, the initial temperature measurement data for each unit time period is used as the soil temperature data of the space point to be measured for each unit time period in the preset time period; or, after obtaining the initial temperature measurement data, the data representing high-frequency fluctuations in the initial temperature measurement data corresponding to each unit time period are filtered to obtain the soil temperature data of the space point to be measured for each unit time period in the preset time period. The filtering method includes low-pass filtering, or using a sliding window to extract the minimum value of each initial temperature measurement data within the time window length in the preset time period, then filtering other initial temperature measurement data, and then replacing the filtered initial temperature measurement data with interpolation according to the smooth transition trend formed by each minimum value.

[0018] In the above implementation process, for submarine cables with loads, the load itself affects temperature changes. Therefore, in this scenario, filtering can be performed. By filtering the initial temperature measurement data representing high-frequency fluctuations within a unit of time, soil temperature data that better reflects the annual fluctuations in mud temperature is obtained. This helps reduce the error impact of high-frequency fluctuations on subsequent processing and improves the accuracy and reliability of the soil temperature data. For submarine cables without loads, there is no load affecting temperature changes. Therefore, in this scenario, filtering is not required, simplifying calculations and improving efficiency.

[0019] Optionally, in this embodiment of the application, before inputting the feature set into the burial depth monitoring model to obtain the burial depth data of the spatial point to be measured, the method further includes: acquiring historical base temperature data of the spatial sampling point of the second submarine cable in each unit time period of the historical period and the measured burial depth value of the spatial sampling point; the historical base temperature data includes historical soil temperature data; obtaining the historical feature set of the spatial sampling point based on the historical base temperature data; and performing regression modeling using the historical feature set of the spatial sampling point and the measured burial depth value to obtain the burial depth monitoring model.

[0020] In the above implementation process, regression modeling is performed using the historical feature set of spatial sampling points and the measured burial depth value to capture the relationship between the historical feature set and the measured burial depth value, and to establish an accurate burial depth monitoring model. Then, the burial depth value of the spatial point to be measured can be monitored using the burial depth monitoring model, thereby improving the accuracy of the burial depth monitoring value.

[0021] Optionally, in this embodiment, the historical baseline temperature data further includes historical ambient temperature data; obtaining the historical feature set of the spatial sampling point based on the historical baseline temperature data includes: obtaining at least one subset of historical baseline temperature data for a preset period from the historical baseline temperature data of the spatial sampling point in each unit time of a historical period; the preset period is the period of mud temperature change; determining the parameter corresponding to the objective function characterizing the mud temperature change according to the preset period based on the subset of historical baseline temperature data, as the historical feature parameter of the spatial sampling point in the at least one preset period; concatenating the historical feature parameter in the at least one preset period with the historical ambient temperature data in the corresponding preset period to obtain the historical feature set of the spatial sampling point in the at least one preset period.

[0022] In the above implementation process, a subset of historical baseline temperature data for a preset period is divided from the historical baseline temperature data to form a historical feature set. This allows the model to fully consider the temporal characteristics within the preset period, establishing an accurate burial depth monitoring model and improving its robustness. When constructing the historical feature set, historical environmental temperature data is also considered. When the historical feature set contains information from multiple dimensions, the model can more comprehensively understand the data.

[0023] Optionally, in this embodiment of the application, if the at least one preset period is multiple preset periods, then the time between the multiple preset periods overlaps.

[0024] In the above implementation process, by overlapping the time intervals between preset periods, more subsets of historical baseline temperature data can be generated as samples. These samples maintain the continuity of the time series while introducing diversity. Enriching the diversity of samples helps the model learn more features from different time periods, thereby improving the model's generalization ability.

[0025] Optionally, in this embodiment, the step of obtaining the measured burial depth value of the spatial sampling point includes: obtaining the latitude and longitude data and measured burial depth value of the detection point for the second submarine cable using the measured burial depth method; determining the length coordinates of the detection point using the latitude and longitude data of the detection point; obtaining the length coordinates of the spatial sampling point; calculating the distance between the detection starting point and the spatial sampling starting point based on the latitude and longitude data of the detection starting point and the spatial sampling starting point, thereby aligning the length coordinates of the detection point and the length coordinates of the spatial sampling point; and performing interpolation calculation using the measured burial depth value of the detection point based on the aligned length coordinates of the detection point and the length coordinates of the spatial sampling point to obtain the measured burial depth value of the spatial sampling point.

[0026] In the above implementation process, after aligning the length coordinates of the detection point and the length coordinates of the spatial sampling point, the measured burial depth value of the spatial sampling point is obtained by interpolation. This eliminates the need to spend a lot of time and resources to measure the burial depth value for each spatial sampling point separately, thus improving the efficiency of obtaining the measured burial depth value. As a result, a large number of samples with measured burial depth value labels can be obtained quickly for regression modeling.

[0027] Secondly, this application also provides a submarine cable burial depth monitoring device, including: a data acquisition module, used to acquire the base temperature data of the spatial point to be measured in the first submarine cable in each unit time of a preset time period; the base temperature data includes soil temperature data;

[0028] The feature module is used to obtain the feature set of the spatial points to be measured based on the basic temperature data;

[0029] The monitoring module is used to input the feature set into the burial depth monitoring model to obtain the burial depth data of the spatial point to be measured; the burial depth monitoring model is obtained by regression modeling of the historical feature set and the measured burial depth value corresponding to the spatial sampling point.

[0030] Thirdly, embodiments of this application also provide a computer program product, including computer program instructions, which are executed by a processor to perform the method provided in the first aspect or any implementation thereof.

[0031] Fourthly, embodiments of this application also provide an electronic device, including: a processor and a memory, the memory storing computer program instructions, which are executed by the processor to perform the method provided in the first aspect or any implementation thereof.

[0032] Fifthly, embodiments of this application also provide a storage medium storing computer program instructions, which are executed by a processor to perform the method provided in the first aspect or any implementation thereof.

[0033] By using the submarine cable burial depth monitoring method, program product, equipment and medium provided in this application, the burial depth data of the spatial point to be measured can be obtained by using the burial depth monitoring model. There is no need to calculate heat dissipation, thereby reducing the error introduced by parameter estimation in this part of the calculation, avoiding a large amount of grid calculation, saving computing resources, reducing the complexity of submarine cable burial depth measurement, reducing calculation time, and improving the efficiency of burial depth measurement. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating a method for monitoring the burial depth of a submarine cable provided in this application embodiment;

[0036] Figure 2 A comparison chart of filtered initial temperature measurement data provided in the embodiments of this application;

[0037] Figure 3 This is a schematic diagram of the burial depth monitoring system provided in the embodiments of this application;

[0038] Figure 4 This is a schematic diagram of the structure of the submarine cable burial depth monitoring device provided in the embodiments of this application;

[0039] Figure 5 This is a schematic diagram of the device provided in an embodiment of this application. Detailed Implementation

[0040] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this application.

[0042] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0043] Please see Figure 1The illustration shows a flowchart of a submarine cable burial depth monitoring method provided in this application embodiment. The submarine cable burial depth monitoring method provided in this application embodiment can be applied to electronic devices, which may include physical devices such as servers, PCs, tablets, or smartphones, or virtual devices such as virtual machines or containers. The device can be a single device, a combination of multiple devices, or a cluster of a large number of devices. Of course, the electronic device can be a system device including fiber optic temperature sensing functionality. The submarine cable burial depth monitoring method may include:

[0044] Step S110: Obtain the basic temperature data of the spatial point to be measured in the first submarine cable for each unit time period within a preset time period; the basic temperature data includes soil temperature data.

[0045] Step S120: Based on the basic temperature data, obtain the feature set of the spatial points to be measured.

[0046] Step S130: Input the feature set into the burial depth monitoring model to obtain the burial depth data of the spatial points to be measured; the burial depth monitoring model is obtained by regression modeling of the historical feature set and measured burial depth value corresponding to the spatial sampling points.

[0047] In step S110, a submarinecable cable is a cable wrapped with insulating material and laid on the seabed, primarily used for telecommunications and / or power transmission. The first submarinecable cable can be a cable requiring depth monitoring. Depth refers to the depth at which the cable is laid on the seabed. The spatial point to be monitored in the first submarinecable cable is the location or area within the first submarinecable cable where depth monitoring is required.

[0048] The preset time period includes multiple units of time. For example, the preset time period can be 300 days, 365 days, 400 days or 500 days; the unit of time can be one hour, several hours, one day or several days, etc.

[0049] Specifically, based on actual measurement data from the sea, seabed temperature changes exhibit a periodic trend on an annual basis. Therefore, the preset time period can be either 366 or 365 days of a year, and the unit of time can be one day.

[0050] Taking a submarine cable application scenario with a load as an example, the method for obtaining soil temperature data of the test point in the first submarine cable within each unit time of a preset time period is as follows: One or more temperature measurement data points of the test point within each unit time of the preset time period are obtained through fiber optic sensing equipment. If only one temperature measurement data point is obtained within a unit time period, this temperature measurement data is used as the initial temperature measurement data for that unit time period. If multiple temperature measurement data points are obtained within a unit time period, the mean, median, or minimum value is calculated using these multiple temperature measurement data points to obtain the initial temperature measurement data for that unit time period. Then, based on the initial temperature measurement data for each unit time period within the preset time period, filtering is performed to obtain the soil temperature data for each unit time period within the preset time period.

[0051] Furthermore, taking the average of multiple temperature measurement data points within a preset time period of 365 days, a unit time of one day (24 hours), and the average temperature measurement data within that unit time as the initial temperature measurement data for that unit time as an example, the above process is described as follows: the spatial point i to be measured in the first submarine cable (i = 1, 2, ..., n) is obtained through the fiber optic sensing device. w n w This involves calculating the daily mud temperature values ​​for each of the 365 days (the number of spatial points to be measured in the first submarine cable). If only one mud temperature value (i.e., temperature measurement data) is obtained in a day, this value is used as the mud temperature data for that unit of time, which can also be called daily mud temperature data. If multiple mud temperature values ​​are obtained in a day, the average temperature data for that day is calculated based on these values. Then, the temperature sequence composed of all the average temperature data within a preset time period is filtered to obtain the mud temperature data for each unit of time within that preset time period, i.e., the daily mud temperature data. In this way, the daily mud temperature data for all the spatial points to be measured can be calculated for each day of the 365 days.

[0052] In some scenarios, if it's necessary to calculate the current (today's) burial depth of a spatial point under test, the soil temperature data for each unit of time within the preset time period refers to the current daily soil temperature data, as well as the daily soil temperature data for the previous 364 days. Of course, the burial depth data for the spatial point under test can be calculated for each day within the preset time period, meaning the burial depth data for the previous 364 days can also be calculated. This requires using daily soil temperature data from even earlier times; for example, the burial depth data for day 365 can be calculated from days 1-365, and the burial depth data for day 366 can be calculated from days 2-366.

[0053] Of course, the above scenario applies to submarine cables under load. For submarine cables without load, there is no load affecting temperature changes, so filtration is unnecessary in this scenario. Therefore, the average, median, or minimum temperature data calculated based on multiple mud temperature values ​​each day can be used as the mud temperature data for each unit of time within the preset time period. Other steps can refer to the relevant steps in the submarine cable under load application scenario, and will not be elaborated further.

[0054] In step S120, the feature set of the spatial points to be measured can be obtained based on the soil temperature data in the basic temperature data; if the basic temperature data also includes other data, the feature set of the spatial points to be measured can also be obtained based on the soil temperature data and other data.

[0055] For the first method mentioned above: feature extraction can be performed on the soil temperature data, and the extracted features can be used as the feature set of the spatial points to be measured. For the second method mentioned above: feature extraction can be performed on the soil temperature data, and the extracted features can be combined with other data included in the basic temperature data to form the feature set of the spatial points to be measured. The process of feature extraction of soil temperature data mentioned in the above two methods can be achieved using an objective function that characterizes the change of soil temperature according to a preset period, which will be explained in detail later.

[0056] In step S130, after obtaining the feature set of the spatial point to be measured, the burial depth monitoring model is used to infer the feature set to obtain the burial depth data of the spatial point to be measured. Following the above embodiment, the preset time period is 365 days, and the unit time is one day (24 hours). The current daily soil temperature data and the daily soil temperature data of the previous 364 days are obtained, totaling 365 days of daily soil temperature data, which can be used to calculate the burial depth data for the current day (the 365th day).

[0057] The generation of the burial depth monitoring model may include the following steps: obtaining a historical feature set based on the historical baseline temperature data of spatial sampling points within a unit time period; performing regression modeling based on the historical feature set and the measured burial depth values ​​of the spatial sampling points to obtain the burial depth monitoring model; this process will be explained in detail later.

[0058] In the above implementation process, the burial depth monitoring model is used to infer the feature set to obtain the burial depth data of the spatial point to be measured. There is no need to calculate the heat dissipation, which reduces the error introduced by parameter estimation in this part of the calculation, avoids a lot of grid calculation, saves computing resources, reduces the complexity of submarine cable burial depth measurement, reduces calculation time, and improves the efficiency of burial depth measurement.

[0059] Optionally, considering that the mud temperature at any point in the test area is related to the burial depth and seabed surface temperature, in this embodiment, ambient temperature data is used to characterize the influence of seabed surface temperature on mud temperature. Therefore, the basic temperature data also includes ambient temperature data. Ambient temperature data can be understood as the ambient temperature of the sea field, which is not affected by the load and burial depth of the submarine cable itself. For example, ambient temperature data includes at least one of the following: average air temperature data, average water temperature data, characteristic quantities of air temperature (such as the maximum annual variation of air temperature), and characteristic quantities of water temperature (such as the maximum annual variation of water temperature). Among them, the average air temperature data and / or average water temperature data can be obtained from meteorological stations or temperature measuring equipment, and can be the average air temperature data and / or average water temperature data for each unit time within a preset time period. If the ambient temperature data includes average air temperature data and average water temperature data, the total value can be obtained by averaging or weighted summation as the ambient temperature data; of course, the ambient temperature data can also directly include the two or more of these data, that is, there is no need to average them.

[0060] In the above implementation process, when constructing the feature set, the ambient temperature, which is not affected by the cable load and burial depth, was also taken into consideration. The ambient temperature data includes average air temperature data and / or average water temperature data. By introducing the ambient temperature parameter, the periodic variation characteristic parameter of mud temperature was standardized, eliminating the fluctuation of the periodic variation characteristic parameter of mud temperature caused by the change of ambient temperature at different times. This improved the richness of the feature set, improved the model distortion problem, and greatly improved the accuracy and interpretability of the burial depth monitoring model.

[0061] Optionally, in this embodiment of the application, obtaining the feature set of the spatial point to be measured based on the basic temperature data includes: extracting features from the soil temperature data to obtain feature parameters of the spatial point to be measured; the feature parameters are used to reflect the periodic changes in the soil temperature of the spatial point to be measured; and concatenating the feature parameters and the ambient temperature data to obtain the feature set of the spatial point to be measured.

[0062] According to the theory of heat conduction, mud temperature (equivalent to the temperature of the submarine cable excluding the influence of load) can be expressed as an objective function that changes according to a preset period. When extracting features from mud temperature data, this objective function that characterizes the mud temperature changing according to a preset period can be used to obtain the feature parameters of the spatial points to be measured. The feature parameters can be one or more, which will be described in detail later.

[0063] In the implementation of the above embodiments: when constructing the feature set, not only the periodic changes of mud temperature reflecting the spatial point to be measured are considered, but also the ambient temperature data are considered. When the feature set contains information of multiple dimensions, the model can understand the data more comprehensively, improve the distortion problem, and greatly improve the accuracy and interpretability of the burial depth monitoring model.

[0064] Optionally, in this embodiment, the preset time period in step S110 includes at least one preset cycle, which is the cycle of mud temperature change. For example, if the cycle of mud temperature change is one year (365 days), then the preset time period should be greater than or equal to one year (365 days). The cycle of mud temperature change can also be longer or shorter, such as 180 days or two years, etc., and this application does not limit it in this way.

[0065] Feature extraction is performed on soil temperature data to obtain characteristic parameters of the spatial points to be measured. This includes: determining the parameters corresponding to the objective function characterizing the change of soil temperature according to a preset period based on the soil temperature data, and using the parameters corresponding to the objective function as the characteristic parameters of the spatial points to be measured within at least one preset period. The objective function is used to characterize the change of soil temperature according to the preset period; that is, the objective function should be a periodic function, such as a sine or cosine function, or a combination of an exponential function or a polynomial function with a sine / cosine function. Soil temperature data can be substituted into the objective function characterizing the change of soil temperature according to the preset period to determine the corresponding parameters, and these parameters are used as the characteristic parameters of the spatial points to be measured within at least one preset period. The parameters corresponding to the objective function can be parameters of the objective function itself or parameters related to the objective function.

[0066] In the implementation process of the above embodiments: by using soil temperature data, the parameters corresponding to the objective function that characterizes the change of soil temperature according to a preset period are determined. The parameters corresponding to the objective function are used as feature parameters, so that the feature parameters can more accurately describe the periodic change of soil temperature, thereby improving the accuracy of the burial depth monitoring model based on these parameters. Moreover, the feature parameters have clear meanings, enhancing the interpretability of the burial depth monitoring model.

[0067] Optionally, in the embodiments of this application, the step of determining the parameter corresponding to the objective function characterizing the change of mud temperature according to a preset period based on the mud temperature data can be implemented in any of the following ways, and used as the characteristic parameter of the spatial point to be measured within at least one preset period.

[0068] (1) Based on the soil temperature data, construct the objective function in the form of Fourier expansion, and use the parameters in the objective function as the characteristic parameters of the spatial point to be measured within a preset period.

[0069] Following the above embodiment, taking a year as an example of mud temperature change cycle, the objective function is to express mud temperature as a periodic function with a yearly period. Therefore, for any mud temperature data at the spatial point i to be measured, the objective function can be represented by the Fourier series expansion form:

[0070]

[0071] Among them, T i(t) represents the soil temperature data of the spatial point i at unit (t); T i0 Represents the preset average temperature; A in ω represents the first characteristic parameter, characterizing the amplitude; n represents the order of the Fourier series, which in practice can be chosen based on the fitting situation or effect (e.g., 1-2, 1-3, not necessarily from 1 to ∞ as in the formula); ω represents the period parameter; t represents the unit time; φ in This represents the second characteristic parameter, characterizing the phase. The preset average temperature refers to the average temperature within this period.

[0072] If the cycle of mud temperature change is one year (365 days), then the cycle parameter ω = 2π / 365.

[0073] Based on soil temperature data, the first characteristic parameter A can be obtained from the Fourier series expansion of the objective function representing the change of soil temperature according to a preset period. in and / or the second characteristic parameter φ in As a feature parameter of the spatial point to be tested within a preset period.

[0074] It should be noted that the first characteristic parameter A in In this context, 'i' represents the i-th spatial point to be measured, and 'n' represents the Fourier series, i.e., the number of string functions in the combination. Each spatial point to be measured has 365 soil temperature data points per year, used to construct a periodic function, and then the parameters of this function are extracted. The feature parameters within a preset period refer to the feature parameters corresponding to all soil temperature data within a period. Each spatial point to be measured corresponds to a set of feature parameters.

[0075] (2) Based on the soil temperature data, fit an objective function characterizing the change of soil temperature according to a preset period, and use the parameters of the objective function as the characteristic parameters of the measured spatial points within the preset period. An example of an objective function characterizing the change of soil temperature according to a preset period is:

[0076] T i (t)=a*cos(ωt+b)+c

[0077] Among them, T i (t) represents the soil temperature data of the spatial point i under test at unit (t); a represents the characteristic parameter, which characterizes the amplitude parameter; ω represents the period parameter; b represents the phase offset parameter; c represents the vertical offset parameter.

[0078] If the cycle of mud temperature change is one year (365 days), then the cycle parameter ω = 2π / 365.

[0079] The objective function can be fitted to the soil temperature data using methods such as least squares or nonlinear regression to determine the parameters a and / or b in the objective function, which can then be used as characteristic parameters of the spatial points to be measured within a preset period.

[0080] In the implementation of the above embodiments, multiple feature extraction methods are provided. In some embodiments, feature parameters obtained based on Fourier series expansion can be selected; in other embodiments, feature parameters reflecting the periodic changes in mud temperature at the measured spatial point can be obtained by fitting an objective function. Among these, the advantage of feature parameters obtained based on Fourier series expansion is that they have better computational accuracy and can achieve more accurate fitting; the objective function is simple to calculate, but it may be necessary to try different objective function forms to obtain better fitting results.

[0081] Optionally, in this embodiment of the application, obtaining soil temperature data of the spatial point to be measured in the first submarine cable at each unit time within a preset time period includes:

[0082] Temperature data of the target spatial point is acquired at each unit time interval within a preset time period. This temperature data can be obtained through analysis using devices such as fiber optic sensing equipment, temperature sensors, or infrared thermometers. The fiber optic sensing equipment can be a temperature sensor based on Rayleigh scattering or a temperature strain sensor based on Brillouin scattering, such as DTS or BOTDA. Preferably, DTS temperature measurement can be used.

[0083] Based on the temperature measurement data of the spatial point under test in each unit time period of the preset time period, calculate the initial temperature measurement data of the spatial point under test in each unit time period of the preset time period. The initial temperature measurement data can be the mean, median, or minimum value of the temperature measurement data.

[0084] For submarine cables without load, after obtaining the initial temperature measurement data, the initial temperature measurement data for each unit time period is used as the soil temperature data for the target spatial point in each unit time period within the preset time period; or,

[0085] For submarine cables under load, after obtaining the initial temperature measurement data, the data representing high-frequency fluctuations in the initial temperature measurement data corresponding to each unit time are filtered to obtain the filtered soil temperature data of the spatial point to be measured within a preset time period. Specifically, taking the average of the temperature measurement data per unit time (average initial soil temperature data) as an example, the data representing high-frequency fluctuations in the average initial soil temperature data may represent temperature increases due to measurement errors, conductor current changes, etc. These data cannot reflect the annual fluctuations in soil temperature. Therefore, it is necessary to filter the data representing high-frequency fluctuations in the average initial soil temperature data. (High-frequency fluctuations and low-frequency fluctuations are divided according to the length of the fluctuation period, where low-frequency fluctuations correspond to long time spans, while high-frequency fluctuations correspond to short time spans). It should be noted that filtering the initial temperature measurement data does not change the amount of initial temperature measurement data; that is, the amount of soil temperature data is equal to the amount of initial temperature measurement data.

[0086] The process of filtering data representing high-frequency fluctuations involves, for example, determining the cutoff frequency. Based on the characteristics of the mud temperature data and the analytical requirements, a suitable cutoff frequency is determined, and an appropriate low-pass filtering method is selected, such as a Butterworth filter or a Chebyshev filter. Then, based on the cutoff frequency, the selected low-pass filter is applied to the initial average mud temperature data to filter out high-frequency fluctuations. This step can be implemented using software algorithms (such as MATLAB or Python) or dedicated signal processing hardware. The filtered mud temperature data can then be analyzed to verify whether the filtering effect meets the requirements. If the filtering effect does not meet the requirements, it may be necessary to adjust the cutoff frequency or select other filtering methods. The filtered mud temperature data that meets the requirements is then used as the soil temperature data for each unit time of the measured spatial point within a preset time period.

[0087] Please see Figure 2 The diagram shows a comparison of the initial temperature measurement data filtering provided in the embodiments of this application.

[0088] Optionally, taking the average of temperature measurement data per unit time (average initial mud temperature data) as an example, the filtering method also includes extracting the minimum value of each initial temperature measurement data within a preset time window using a sliding window, then filtering other initial temperature measurement data, and then replacing the filtered initial temperature measurement data according to the smooth transition trend formed by each minimum value using interpolation. Figure 2 As shown, the solid line represents the trend line connecting the initial average mud temperature data, and the dashed line represents the trend line of the soil temperature data, which is the filtered average mud temperature data.

[0089] In the implementation of the above embodiments: by filtering the data representing high-frequency fluctuations in the initial average mud temperature data per unit time, soil temperature data that better reflects the fluctuations of mud temperature over an annual cycle is obtained, reducing the error impact of high-frequency fluctuation data on subsequent processing, and improving the accuracy and reliability of soil temperature data.

[0090] Optionally, in this embodiment of the application, before inputting the feature set into the burial depth monitoring model to obtain the burial depth data of the spatial point to be measured, the method further includes obtaining the burial depth monitoring model. The process of obtaining the burial depth monitoring model is described below.

[0091] The historical baseline temperature data and measured burial depth values ​​of the spatial sampling points of the second submarine cable are obtained for each unit time period in the historical time period. The measured burial depth values ​​of the spatial sampling points refer to the burial depth values ​​obtained by measurement through professional equipment and technology. This step will be explained in detail later.

[0092] Historical baseline temperature data includes historical soil temperature data. The second submarine cable can be the same cable as the first, or it can be a different cable.

[0093] If the second submarine cable is the same as the first submarine cable, the burial depth value of the same spatial point may change over time. Therefore, the spatial sampling point used in the process of generating the burial depth monitoring model can also be used as the subsequent spatial point to be measured. That is, the spatial sampling point and the spatial point to be measured can be the same location or area, or they can be different locations or areas in the same submarine cable.

[0094] The process of obtaining historical baseline temperature data of the spatial sampling points of the second submarine cable in each unit time period is similar to the process of obtaining baseline temperature data of the spatial points to be measured in the first submarine cable in each unit time period in step S110.

[0095] For example, taking a day as the unit of time, spatial sampling points i (i = 1, 2, ..., n) are obtained through devices such as fiber optic sensing equipment, temperature sensors, or infrared thermometers. w n w (The number of spatial sampling points in the second submarine cable) Temperature measurement data for each unit time period in the historical time period. Based on the temperature measurement data for each unit time period in the historical time period, the historical initial average temperature measurement data for each unit time period is obtained, denoted as D. i (t). Explanatory, this example uses historical initial average temperature data, but it could also be historical initial median temperature data or historical initial minimum temperature data. This part corresponds to the previous content and will not be elaborated further.

[0096] Next, the data representing high-frequency fluctuations in the historical initial average temperature measurement data are filtered to obtain the historical soil temperature data for each unit time of the spatial sampling point within a preset time period. The processing procedure for filtering high-frequency fluctuation data is described above. Of course, in addition to low-pass filtering, other similar data denoising and smoothing methods can also be used to process the historical initial average temperature measurement data to obtain historical soil temperature data.

[0097] Based on historical baseline temperature data, a historical feature set for the spatial sampling points is obtained. Similar to the feature set of the spatial points to be measured, features can be extracted from historical soil temperature data in the historical baseline temperature data, and the extracted features can be used as the historical feature set of the spatial sampling points; alternatively, the features extracted from historical soil temperature data and other data contained in the historical baseline temperature data can be used together as the historical feature set of the spatial sampling points, which will be explained in detail later.

[0098] After obtaining the historical feature set of the spatial sampling points, regression modeling is performed using the historical feature set and the measured burial depth values ​​to obtain the burial depth monitoring model. Each spatial sampling point provides its corresponding historical feature set and measured burial depth value, which can be considered as a label in machine learning. For example, a suitable regression model is selected based on monitoring requirements; regression methods include decision tree regression, random forest regression, or Bagging regression. Using the determined regression method, a regression model is constructed based on the historical feature set and measured burial depth values. During this process, optimization algorithms such as least squares or gradient descent can be used to determine the model parameters, completing the establishment of the burial depth monitoring model. Furthermore, the performance of the burial depth monitoring model can be validated and evaluated after its generation to ensure that the model meets performance requirements.

[0099] In the implementation of the above embodiments: by using the historical feature set of spatial sampling points and the measured burial depth value for regression modeling, the relationship between the historical feature set and the measured burial depth value is captured, and an accurate burial depth monitoring model is established. Then, the burial depth value of the spatial point to be measured can be monitored using the burial depth monitoring model, thereby improving the accuracy of burial depth monitoring.

[0100] Optionally, in this embodiment of the application, the historical baseline temperature data further includes historical ambient temperature data; based on the historical baseline temperature data, a historical feature set of the spatial sampling points is obtained, including:

[0101] From the historical baseline temperature data of spatial sampling points within each unit time period of the historical time period, obtain at least one subset of historical baseline temperature data for a preset period; the preset period is the period of mud temperature change. The preset period can be regarded as a time window.

[0102] In an optional embodiment, if at least one preset period is multiple preset periods, then the time between the multiple preset periods overlaps. This allows for the acquisition of a larger subset of historical baseline temperature data as a sample from a limited pool of data. Optionally, the time difference between two temporally adjacent preset periods is one unit of time, thus obtaining the maximum subset of historical baseline temperature data.

[0103] For example, with a unit of time of 1 day and a preset period of 365 days, the historical baseline temperature data of spatial sampling point i can be represented as {T i (1), T i (2), T i (3), ..., T i (L)}, where L is the historical time period, L>= preset period (365 days), T i (1) represents the historical baseline temperature data of spatial sampling point i in the first unit of the historical period. Then, the historical baseline temperature data from day 1 to day 365 can be a subset of historical baseline temperature data for a preset period; the historical baseline temperature data from day 2 to day 366 can also be a subset of historical baseline temperature data for a preset period. That is, in the p-th (p = 1, 2, ..., L-365+1) preset period, the subset of historical baseline temperature data for point i can be represented as {T i (t)|t=p, p+1, p+2,..., p+364}.

[0104] By overlapping the time intervals between preset periods, more subsets of historical baseline temperature data can be generated as samples. These samples maintain the continuity of the time series while introducing diversity. Enriching the diversity of samples helps the model learn more features from different time periods, thereby improving the model's generalization ability.

[0105] Based on a subset of historical soil temperature data, the parameters corresponding to the objective function characterizing the change of soil temperature according to a preset period are determined, serving as historical characteristic parameters of the spatial sampling points within at least one preset period. This step is similar to the process of "determining the parameters corresponding to the objective function characterizing the change of soil temperature according to a preset period based on soil temperature data, serving as characteristic parameters of the spatial points to be measured within at least one preset period," and can also be implemented using any of the following methods.

[0106] (1) Based on a subset of historical soil temperature data, the second objective function representing the change of soil temperature according to a preset period is expanded into a Fourier series, and the parameters in the expanded result are used as historical characteristic parameters of the spatial sampling points within at least one preset period. The second objective function must be consistent with the aforementioned objective function form. For any subset of historical baseline temperature data at spatial sampling point k, it can be represented by the Fourier series expansion of the second objective function:

[0107]

[0108] Among them, T k (t) represents the historical soil temperature data of spatial sampling point k at time (t); T i0 Represents the preset average temperature; A in ′ represents the first historical characteristic parameter, characterizing the amplitude; n represents the order of the Fourier series; ω represents the period parameter; t represents unit time; φ in ' represents the second historical characteristic parameter, characterizing the phase. If the period of mud temperature change is one year (365 days), then the period parameter ω = 2π / 365. The first historical characteristic parameter A in the Fourier series expansion result can be... in ′ and / or the second historical feature parameter φ in ′ serves as a historical feature parameter for spatial sampling points.

[0109] (2) Based on a subset of historical soil temperature data, fit a second objective function characterizing the change of soil temperature according to a preset period, and use the parameters of the second objective function as historical characteristic parameters of spatial sampling points within the preset period. The second objective function is as follows:

[0110] T k (t)=a′*cos(ωt+b)+c

[0111] Among them, T k (t) represents the historical soil temperature data of spatial sampling point k in unit (t); a′ represents the first historical characteristic parameter; ω represents the periodic parameter; b′ represents the second historical characteristic parameter; c represents the vertical offset parameter. If the period of soil temperature change is one year (365 days), then the periodic parameter ω = 2π / 365.

[0112] Methods such as least squares or nonlinear regression can be used to fit a subset of historical baseline temperature data onto a second objective function to determine the parameter a′ in the second objective function.

[0113] And / or b′, using parameters a′ and / or b′ as feature parameters of spatial sampling points within a preset period.

[0114] By concatenating historical feature parameters within at least one preset period with historical ambient temperature data within the corresponding preset period, a historical feature set of spatial sampling points within at least one preset period is obtained.

[0115] Understandably, if at least one preset period consists of multiple preset periods, then the corresponding subset of historical baseline temperature data for each spatial sampling point within each preset period can yield a set of corresponding historical feature parameters. These historical feature parameters are then concatenated with the historical ambient temperature data for the corresponding preset period to obtain the historical feature set for the spatial sampling point within that preset period. For example, if the first preset period is from day 1 to day 365, the historical feature parameters obtained from the subset of historical baseline temperature data from day 1 to day 365 should be concatenated with the historical ambient temperature data from day 1 to day 365 to obtain the historical feature set for the spatial sampling point within the first preset period. For each spatial sampling point, the number of its corresponding historical feature sets is consistent with the number of preset periods or time windows.

[0116] In the implementation of the above embodiments: a subset of historical base temperature data for a preset period is divided from the historical base temperature data to form a historical feature set, so that the model fully considers the time-series features within the preset period, establishes an accurate burial depth monitoring model, and improves the robustness of the model.

[0117] Optionally, in this embodiment of the application, the step of obtaining the measured burial depth value of the spatial sampling point includes:

[0118] The latitude and longitude data and measured depth values ​​of the detection points for the second submarine cable are obtained using the measured burial depth method. The detection points are the locations or areas within the second submarine cable where the latitude and longitude data and measured burial depth values ​​are obtained using this method. The measured burial depth method includes scanning burial depth or initial point-marking burial depth, where scanning burial depth can be detected through shallow seismic profiling, side-scan sonar, or multibeam sonar.

[0119] Using the latitude and longitude data of the detection points, the length coordinates of the detection points are determined. For example, the distance between two detection points can be calculated from the latitude and longitude data. The latitude and longitude of the measured burial depth measurement points are converted into length coordinates, which can be regarded as one-dimensional coordinates. For example, the length coordinates of the detection points can be "0 meters, 52.5 meters, 78.8 meters, 128.2 meters...", where each value represents the location of a detection point. Furthermore, during the initial laying or manual detection using shallow seismic profiling, side-scan sonar, or multibeam sonar, the length coordinates and latitude and longitude coordinates corresponding to each location of the second submarine cable can be recorded simultaneously, thus directly establishing the correlation between the length coordinates and latitude and longitude coordinates in the early stages.

[0120] Interpretatively, when the distance between two detection points is sufficiently short, high accuracy is generally achievable, making the distance between the two detection points equivalent to the length of the second submarine cable between them. However, since the second submarine cable extends not only along latitude and longitude but also along altitude, further consideration of the absolute height of the detection points allows for the calculation of the specific extension direction of the second submarine cable in three-dimensional space. Based on the absolute height and latitude / longitude coordinates, a high-precision three-dimensional route map of the submarine cable is fitted and verified, thereby determining the high-precision length coordinates of each detection point. This enables a high-precision match between the measured burial depth value and the length coordinates of the temperature detection points of the distributed optical fiber. The absolute height of the detection points can be calculated using technologies such as sonar scanning and GPS positioning. For example, GPS positioning can determine the absolute height of the probe vessel, and combined with sonar scanning and DAS detection, the height difference between the detection point and the probe vessel can be determined, thus estimating the absolute height of the detection point. Alternatively, during the cable laying phase, latitude, longitude, and absolute height can be marked at the detection points of the submarine cable using seabed detectors or manually.

[0121] Obtain the length coordinates of the spatial sampling points. Specifically, based on the sampling frequency and refractive index of the fiber optic sensing device, and combined with OTDR optical time-domain analysis, determine the step size between spatial sampling points, thereby determining the length coordinates of the spatial sampling points.

[0122] Obtain the length coordinates of spatial sampling points. For example, in the second submarine cable integrated distributed optical fiber, the length coordinates of the corresponding spatial sampling points of the distributed optical fiber can be obtained through a DTS distributed optical fiber sensing device. For instance, the length coordinates of a spatial sampling point can be "0 meters, 1 meter, 2 meters…50 meters…129 meters," where each value represents the location of a spatial sampling point. Specifically, based on the sampling frequency and refractive index of the optical fiber sensing device, combined with OTDR optical time-domain analysis, the step size between spatial sampling points is determined, thereby determining the length coordinates of the spatial sampling points. The latitude and longitude data of the spatial sampling starting point can be the latitude and longitude data of the location of the distributed optical fiber sensing device.

[0123] Both the detection points and spatial sampling points are distributed along the second submarine cable, and the length coordinates of both are calculated from 0 meters. However, the starting point of the detection at the detection point and the starting point of the spatial sampling at the spatial sampling point may not be the same point (i.e., the origins of their length coordinate systems are different). Therefore, it is necessary to align the length coordinates of the detection points and the spatial sampling points. Alignment refers to the process of unifying the reference systems of the length coordinates of the detection points and the spatial sampling points. For example, due to the varying depths of the seawater, some points along the second submarine cable may not be detected. Therefore, the starting point of the detection at the detection point (0 meters) is the first point detected; the starting point of the spatial sampling at the spatial sampling point (0 meters) is the first spatial sampling point in the distributed optical fiber. Because the starting points are different, even if the length coordinates of the detection points and the spatial sampling points are the same before alignment, they represent different spatial locations in practice.

[0124] The alignment process can be as follows: Based on the latitude and longitude data of the detection starting point in the detection points and the latitude and longitude data of the spatial sampling starting point in the spatial sampling points, determine the distance between the detection starting point and the spatial sampling starting point. Add this distance to the length coordinate of each detection point to obtain the aligned length coordinate of the detection point. In this way, the aligned length coordinates of the detection points and the length coordinates of the spatial sampling points are aligned, meaning that both are based on the spatial sampling starting point in the spatial sampling points. The aligned length coordinates of the detection points are consistent with the length coordinates of the spatial sampling points, representing the same location or region. The latitude and longitude data of the spatial sampling starting point in the spatial sampling points can be the latitude and longitude data of the location of the distributed fiber optic sensing device.

[0125] Based on the aligned length coordinates of the detection points and the length coordinates of the spatial sampling points, interpolation calculations are performed using the measured burial depth values ​​of the detection points (interpolation methods can include linear interpolation, spline interpolation, Lagrange interpolation, etc.) to obtain the measured burial depth values ​​of the spatial sampling points. For example, for each spatial sampling point, the two nearest detection points on either side of it are found (i.e., detection points whose length coordinates are less than and greater than the sampling point coordinates), and the measured burial depth value of the spatial sampling point is calculated using the interpolation formula based on the two nearest detection points on either side.

[0126] Understandably, through the above interpolation process, the measured burial depth values ​​of all spatial sampling points whose length coordinates overlap with those of the detection point can be calculated. During regression modeling, spatial sampling points with already calculated measured burial depth values ​​and their historical feature sets can be selected for regression modeling to obtain the burial depth monitoring model.

[0127] In the implementation of the above embodiments: after aligning the length coordinates of the detection point and the length coordinates of the spatial sampling point, the measured burial depth value of the spatial sampling point is obtained by interpolation, which eliminates the need to spend a lot of time and resources to measure the burial depth value for each spatial sampling point separately, thereby improving the efficiency of obtaining the measured burial depth value.

[0128] Please see Figure 3 The diagram shows a framework of the burial depth monitoring system provided in an embodiment of this application.

[0129] In one optional embodiment, the burial depth monitoring system can be built on a submarine cable monitoring platform, and the burial depth calculation function can be implemented through an embedded burial depth calculation service. The operation of the burial depth monitoring system can be divided into two steps: first, the initialization process is completed, and only after the initialization is completed can the burial depth calculation function be implemented.

[0130] In the initialization process: First, the historical base temperature data and measured burial depth values ​​of the spatial sampling points of the second submarine cable for each unit time period are received. The historical base temperature data includes historical soil temperature data and historical ambient temperature data. This data is then forwarded to the burial depth calculation service through the internal communication of the submarine cable monitoring platform.

[0131] After receiving the raw data, the burial depth calculation service first extracts features to obtain a historical feature set, and then uses the historical feature set of spatial sampling points and the measured burial depth value to perform regression modeling to obtain a burial depth monitoring model.

[0132] In the burial depth calculation function, the data of the burial depth to be calculated is received, and the above-mentioned submarine cable burial depth monitoring method is executed to obtain the burial depth data of the spatial point to be measured.

[0133] Based on the burial depth data calculated by the burial depth calculation service, the data is transmitted through the internal communication of the submarine cable monitoring platform. This enables subsequent burial depth alarm services and visualization functions. For example, the alarm service includes burial depth threshold alarms and burial depth change rate alarms. The visualization displays real-time submarine cable burial depth curves and historical burial depth maps. The alarm information and visualization content can be displayed to users through the client.

[0134] Please see Figure 4 The diagram shown is a structural schematic of the submarine cable burial depth monitoring device provided in this application embodiment; this application embodiment provides a submarine cable burial depth monitoring device 200, including:

[0135] The data acquisition module 210 is used to acquire the basic temperature data of the spatial point to be measured in the first submarine cable in each unit time of a preset time period; the basic temperature data includes soil temperature data.

[0136] Feature module 220 is used to obtain the feature set of the spatial points to be measured based on the basic temperature data;

[0137] The monitoring module 230 is used to input the feature set into the burial depth monitoring model to obtain the burial depth data of the spatial point to be measured; the burial depth monitoring model is obtained by regression modeling of the historical feature set and the measured burial depth value corresponding to the spatial sampling point.

[0138] Optionally, in this embodiment of the application, the submarine cable burial depth monitoring device 200 includes ambient temperature data as its basic temperature data; the feature module 220 is specifically used to extract features from the soil temperature data to obtain feature parameters of the spatial point to be measured; the feature parameters are used to reflect the periodic changes in the soil temperature of the spatial point to be measured; the feature parameters and the ambient temperature data are spliced ​​together to obtain the feature set of the spatial point to be measured.

[0139] Optionally, in this embodiment of the application, the submarine cable burial depth monitoring device 200 has a preset time period including at least one preset cycle, which is the cycle of mud temperature change; the feature module 220 is specifically used to determine the parameter corresponding to the objective function that characterizes the mud temperature change according to the preset cycle based on the mud temperature data, as the feature parameter of the spatial point to be measured within at least one preset cycle.

[0140] Optionally, in the embodiments of this application, the feature module 220 in the submarine cable burial depth monitoring device 200 is specifically used to construct the objective function in Fourier expansion form based on the soil temperature data, and use the parameters in the objective function as the feature parameters of the spatial point to be measured within a preset period; or, based on the soil temperature data, fit an objective function characterizing the change of soil temperature according to a preset period, and use the parameters of the objective function as the feature parameters of the spatial point to be measured within a preset period.

[0141] Optionally, in this embodiment of the application, the ambient temperature data in the submarine cable burial depth monitoring device 200 includes the average air temperature data and / or average water temperature data of the spatial point to be measured.

[0142] Optionally, in this embodiment of the application, in the submarine cable burial depth monitoring device 200, the data acquisition module 210 is specifically used to acquire the soil temperature data as temperature data obtained by sensing the temperature of each of the space points to be measured through the sensing optical fiber; and / or, acquire the temperature measurement data of the space points to be measured in the first submarine cable in each unit time of a preset time period; calculate the initial temperature measurement data of the space points to be measured in each unit time of the preset time period based on the temperature measurement data of the space points to be measured in each unit time of the preset time period; filter the data representing high-frequency fluctuations in the initial temperature measurement data to obtain the soil temperature data of the space points to be measured in each unit time of the preset time period.

[0143] Optionally, in this embodiment of the application, the submarine cable burial depth monitoring device 200 further includes a data preprocessing module, used to acquire historical base temperature data and measured burial depth values ​​of the spatial sampling points of the second submarine cable in each unit time period of the historical time period; the historical base temperature data includes historical soil temperature data; based on the historical base temperature data, a historical feature set of the spatial sampling points is obtained; regression modeling is performed using the historical feature set of the spatial sampling points and the measured burial depth values ​​to obtain a burial depth monitoring model.

[0144] Optionally, in this embodiment of the application, in the submarine cable burial depth monitoring device 200, the pattern generation module is specifically used to obtain at least one preset period of historical base temperature data subset from the historical base temperature data of the spatial sampling point in each unit time of the historical period; the preset period is the period of mud temperature change; based on the historical base temperature data subset, determine the parameter corresponding to the objective function characterizing the mud temperature change according to the preset period, as the historical feature parameter of the spatial sampling point in at least one preset period; and concatenate the historical feature parameter in at least one preset period with the historical ambient temperature data in the corresponding preset period to obtain the historical feature set of the spatial sampling point in at least one preset period.

[0145] Optionally, in the embodiments of this application, in the submarine cable burial depth monitoring device 200, if at least one preset period is multiple preset periods, then the time between the multiple preset periods overlaps; and / or, the historical environmental temperature data includes historical average air temperature data and / or historical average water temperature data of spatial sampling points.

[0146] Optionally, in this embodiment of the application, in the submarine cable burial depth monitoring device 200, the pattern generation module is specifically used to obtain the latitude and longitude data and the measured burial depth value of the detection point for the second submarine cable using the measured burial depth method; determine the length coordinates of the detection point using the latitude and longitude data of the detection point; obtain the length coordinates of the spatial sampling point; calculate the distance between the detection starting point and the spatial sampling starting point based on the latitude and longitude data of the detection starting point in the detection point and the spatial sampling starting point in the spatial sampling point, thereby aligning the length coordinates of the detection point and the length coordinates of the spatial sampling point; and perform interpolation calculation using the measured burial depth value of the detection point based on the aligned length coordinates of the detection point and the length coordinates of the spatial sampling point to obtain the measured burial depth value of the spatial sampling point.

[0147] It should be understood that this device corresponds to the above-described embodiment of the submarine cable burial depth monitoring method and is capable of performing the various steps involved in the above-described embodiment. The specific functions of this device can be found in the description above, and detailed descriptions are omitted here to avoid repetition. The device includes at least one software functional module that can be stored in memory or embedded in the device's operating system (OS) in the form of software or firmware.

[0148] Please see Figure 5 The diagram shows a structural schematic of the device provided in an embodiment of this application. An electronic device 300 provided in this application includes a processor 310 and a memory 320. The memory 320 stores machine-readable instructions executable by the processor 310. When the machine-readable instructions are executed by the processor 310, the method described above is performed. The electronic device 300 can be a burial depth monitoring system, or a submarine cable monitoring platform, system, or device that includes a burial depth monitoring system.

[0149] This application also provides a storage medium storing a computer program, which is executed by a processor to perform the above-described method.

[0150] The 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 Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0151] This application also provides a computer program product, which includes computer program instructions. When the computer program instructions are run by a processor, they execute the submarine cable burial depth monitoring method as described in any of the above embodiments.

[0152] It should be understood that the disclosed apparatus and methods can also be implemented in other ways, given the several embodiments provided in this application. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0153] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0154] The above description is only an optional implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application.

Claims

1. A method for monitoring the burial depth of submarine cables, characterized in that, include: Acquire the baseline temperature data of the spatial point to be measured in the first submarine cable for each unit time period within a preset time period; The basic temperature data includes soil temperature data; Based on the basic temperature data, the feature set of the spatial points to be measured is obtained; The feature set is input into the burial depth monitoring model to obtain the burial depth data of the spatial point to be measured; the burial depth monitoring model is obtained by regression modeling of the historical feature set and the measured burial depth value corresponding to the spatial sampling point.

2. The method according to claim 1, characterized in that, The basic temperature data also includes ambient temperature data; obtaining the feature set of the spatial points to be measured based on the basic temperature data includes: Feature extraction is performed on the soil temperature data to obtain feature parameters of the spatial point to be measured; the feature parameters are used to reflect the periodic changes in soil temperature of the spatial point to be measured. The feature parameters and the ambient temperature data are concatenated to obtain the feature set of the spatial point to be measured.

3. The method according to claim 2, characterized in that, The preset time period includes at least one preset period, where the preset period is the period of mud temperature change; the step of extracting features from the mud temperature data to obtain the feature parameters of the spatial point to be measured includes: Based on the soil temperature data, the parameters corresponding to the objective function characterizing the change of soil temperature according to the preset period are determined, and the parameters corresponding to the objective function are used as the characteristic parameters of the spatial point to be measured within the at least one preset period.

4. The method according to claim 3, characterized in that, The step of determining the parameters corresponding to the objective function characterizing the change of mud temperature according to the preset period based on the soil temperature data, and using the parameters corresponding to the objective function as the characteristic parameters of the spatial point to be measured within the at least one preset period, includes: Based on the soil temperature data, the objective function in Fourier expansion form is constructed, and the parameters in the objective function are used as the characteristic parameters of the spatial point to be measured within the preset period. or, Based on the soil temperature data, a target function characterizing the change of soil temperature according to the preset period is fitted, and the parameters of the target function are used as the feature parameters of the spatial point to be measured within the preset period.

5. The method according to claim 1, characterized in that, Acquire soil temperature data for each unit time period of the target spatial point in the first submarine cable within a preset time period, including: Acquire temperature measurement data of the space point to be measured in each unit time period of the preset time period; Based on the temperature measurement data of the space point to be measured in each unit time of the preset time period, the initial temperature measurement data of the space point to be measured in each unit time of the preset time period is calculated. The initial temperature measurement data is the mean, median or minimum value calculated based on the temperature measurement data in each unit time. After obtaining the initial temperature measurement data, the initial temperature measurement data for each unit time period is used as the soil temperature data of the spatial point to be measured for each unit time period in the preset time period; or, after obtaining the initial temperature measurement data, the data representing high-frequency fluctuations in the initial temperature measurement data corresponding to each unit time period are filtered to obtain the soil temperature data of the spatial point to be measured for each unit time period in the preset time period. The filtering method includes low-pass filtering, or using a sliding window to extract the minimum value of each initial temperature measurement data within the time window length in the preset time period, then filtering other initial temperature measurement data, and then replacing the filtered initial temperature measurement data with interpolation according to the smooth transition trend formed by each minimum value.

6. The method according to claim 1, characterized in that, Before inputting the feature set into the burial depth monitoring model to obtain the burial depth data of the spatial point to be measured, the method further includes: The historical base temperature data and the measured burial depth of the spatial sampling points of the second submarine cable are obtained for each unit time period in the historical time period; the historical base temperature data includes historical soil temperature data. Based on the historical baseline temperature data, the historical feature set of the spatial sampling points is obtained; The burial depth monitoring model is obtained by using the historical feature set of the spatial sampling points and the measured burial depth values ​​for regression modeling.

7. The method according to claim 6, characterized in that, The historical baseline temperature data also includes historical ambient temperature data; obtaining the historical feature set of the spatial sampling points based on the historical baseline temperature data includes: From the historical baseline temperature data of the spatial sampling point in each unit time period of the historical period, at least one subset of historical baseline temperature data for a preset period is obtained; the preset period is the period of mud temperature change. Based on the subset of historical baseline temperature data, the parameters corresponding to the objective function characterizing the change of mud temperature according to the preset period are determined, and used as the historical characteristic parameters of the spatial sampling points within the at least one preset period. By concatenating the historical feature parameters within the at least one preset period with the historical ambient temperature data within the corresponding preset period, a historical feature set of the spatial sampling points within the at least one preset period is obtained.

8. The method according to claim 7, characterized in that, If the at least one preset period is multiple preset periods, then there is an overlap in time between the multiple preset periods; and / or, the historical environmental temperature data includes historical average air temperature data and / or historical average water temperature data of spatial sampling points.

9. The method according to claim 6, characterized in that, The steps for obtaining the measured burial depth value of the spatial sampling point include: The latitude and longitude data and measured burial depth values ​​of the detection points for the second submarine cable were obtained using the measured burial depth method; The length coordinates of the detection point are determined using the latitude and longitude data of the detection point; Obtain the length coordinates of the spatial sampling points; Based on the latitude and longitude data of the detection starting point in the detection point and the latitude and longitude data of the spatial sampling starting point in the spatial sampling point, the distance between the detection starting point and the spatial sampling starting point is calculated, thereby aligning the length coordinates of the detection point and the length coordinates of the spatial sampling point. Based on the length coordinates of the aligned detection points and the length coordinates of the spatial sampling points, interpolation calculations are performed using the measured burial depth values ​​of the detection points to obtain the measured burial depth values ​​of the spatial sampling points.

10. A computer program product, characterized in that, It includes computer program instructions that are executed by a processor to perform the method as described in any one of claims 1 to 9.

11. An electronic device, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, perform the method as described in any one of claims 1 to 9.

Images