Periodic Monitoring Method and Device for Submarine Cable Disturbance Sensing Data

Abstract

The present disclosure relates to a method and device for periodically monitoring submarine cable disturbance sensing data. Target data is obtained by acquiring disturbance sensing data of a submarine cable collected by a plurality of sensors and performing data preprocessing. N algorithms in a pre-set algorithm pool are used to judge the target data to obtain a periodic data set with a length of N; M periodic data subsets are selected from the periodic data set with a length of N, and the M periodic data subsets respectively correspond to M base classifiers. According to the base classifiers whose results meet a preset threshold and the weights of the base classifiers whose results meet the preset threshold, a target classifier is obtained. According to the output result of the target classifier, the periodic result of the submarine cable disturbance sensing data is determined, and the state of submarine equipment and the periodic monitoring of submarine cable disturbance sensing data can be automatically monitored.

Description

Technical Field

[0001] The present disclosure relates to the technical field of submarine cable monitoring, and particularly to a method and device for periodically monitoring submarine cable disturbance sensing data. Background Art

[0002] Marine resources are a treasure trove of resources that are relatively easy for humans to explore. Currently, the construction of various offshore and submarine engineering projects is progressing in an orderly manner. However, compared to land, the difficulties and risks of human work in the underwater environment are higher, and the difficulty of monitoring and maintaining submarine facilities is also greater. The marine environment is extremely complex, and submarine facilities are more likely to encounter accidental risks. However, the costs of facility maintenance and repair are high. Therefore, how to automatically monitor the status of submarine equipment and periodically monitor the submarine cable disturbance sensing data, early warning of possible damages to submarine equipment, and timely monitoring of the status of submarine equipment to reduce the costs of submarine equipment maintenance and repair is an urgent matter to be solved. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method and device for periodically monitoring submarine cable disturbance sensing data that can automatically monitor the status of submarine equipment.

[0004] In a first aspect, the present disclosure provides a method for periodically monitoring submarine cable disturbance sensing data.

[0005] The method includes:

[0006] Obtaining the disturbance sensing data of the submarine cable collected by a plurality of sensors;

[0007] After preprocessing the disturbance sensing data in a preset manner, obtaining target data;

[0008] Using N algorithms in a pre-set algorithm pool to judge the target data, obtaining a set of periodic data with a length of N;

[0009] Selecting M subsets of periodic data from the set of periodic data with a length of N, where the M subsets of periodic data respectively correspond to M base classifiers, and the weights of the M base classifiers are equal;

[0010] If the output result of the base classifier does not meet the preset threshold, the weight of the base classifier whose output result does not meet the preset threshold is increased according to a preset rule until the output result of the base classifier meets the preset threshold;

[0011] Obtain a target classifier based on the base classifiers whose results meet the preset threshold and the weights of the base classifiers whose results meet the preset threshold, and determine the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

[0012] In one embodiment, the using N algorithms in a pre-set algorithm pool to judge the target data to obtain a periodic data set of length N includes:

[0013] Expand the target data into a linear combination of trigonometric functions;

[0014] Determine the term with the largest coefficient in the linear combination of trigonometric functions;

[0015] Obtain a periodic data set of length N according to the term with the largest coefficient.

[0016] In one embodiment, the method further includes:

[0017] Determine a set of terms with the largest coefficients according to the term with the largest coefficient in the linear combination of trigonometric functions;

[0018] Determine the autocorrelation coefficient of a subset in the set of terms with the largest coefficients;

[0019] Compare the autocorrelation coefficient of the subset with a preset autocorrelation coefficient threshold;

[0020] Determine the subsets whose autocorrelation coefficients of the subsets are greater than or equal to the preset autocorrelation coefficient threshold;

[0021] Determine the period of the set of terms with the largest coefficients according to the subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold.

[0022] In one embodiment, the determining the period of the set of terms with the largest coefficients according to the subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold includes:

[0023] Determine any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold;

[0024] Perform a difference operation on the start times of the any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold and take the absolute value to obtain the period of the set of terms with the largest coefficients.

[0025] In one embodiment, the obtaining the target data after preprocessing the disturbance sensing data in a preset manner includes:

[0026] Resample the disturbance sensing data to obtain resampled data. The resampling includes at least one of resampling by day dimension, resampling by week dimension, and resampling by month dimension;

[0027] Filter data outliers from the resampled data to obtain outlier-filtered data;

[0028] Perform dimensionless processing on the outlier-filtered data to obtain target data. The dimensionless processing includes at least one of linear dimensionless processing and non-linear dimensionless processing.

[0029] In one embodiment, the filtering data outliers from the resampled data to obtain outlier-filtered data includes:

[0030] Perform rule calculation on the resampled data to obtain rule calculation data. The rule calculation includes at least one of calculating the average value of the resampled data and calculating the variance of the resampled data;

[0031] Take the absolute value of the difference between the resampled data and the rule calculation data to obtain deviation data;

[0032] Compare the target deviation data in the deviation data with a preset deviation threshold;

[0033] If the target deviation data is greater than the preset deviation threshold, set the resampled data corresponding to the target deviation data as an outlier and remove the outlier from the resampled data to obtain outlier-filtered data.

[0034] In a second aspect, the present disclosure also provides a periodic monitoring device for submarine cable disturbance sensing data. The device includes:

[0035] A data acquisition module for acquiring disturbance sensing data of a submarine cable collected by a plurality of sensors;

[0036] A target data module for obtaining target data after preprocessing the disturbance sensing data in a preset manner;

[0037] A periodic data set module for judging the target data by using N algorithms in a preset algorithm pool to obtain a periodic data set of length N;

[0038] A subset module for selecting M periodic data subsets from the periodic data set of length N. The M periodic data subsets respectively correspond to M base classifiers, where the weights of the M base classifiers are equal;

[0039] A weight adjustment module, configured to, if the output result of the base classifier does not meet a preset threshold, increase the weight of the base classifier whose output result does not meet the preset threshold according to a preset rule until the output result of the base classifier meets the preset threshold;

[0040] A result determination module, configured to obtain a target classifier according to the base classifiers whose results meet the preset threshold and the weights of the base classifiers whose results meet the preset threshold, and determine the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

[0041] In a third aspect, the present disclosure further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of the present disclosure is implemented.

[0042] In a fourth aspect, the present disclosure further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0043] In a fifth aspect, the present disclosure further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0044] The above-mentioned periodic monitoring method and device for submarine cable disturbance sensing data obtain the disturbance sensing data of the submarine cable collected by multiple sensors; after performing data preprocessing on the disturbance sensing data in a preset manner, target data is obtained; N algorithms in a pre-set algorithm pool are used to judge the target data to obtain a set of periodic data with a length of N; M subsets of periodic data are selected from the set of periodic data with a length of N, and the M subsets of periodic data respectively correspond to M base classifiers, where the weights of the M base classifiers are equal; if the output result of the base classifier does not meet the preset threshold, the weight of the base classifier whose output result does not meet the preset threshold is increased according to a preset rule until the output result of the base classifier meets the preset threshold; a target classifier is obtained according to the base classifiers whose results meet the preset threshold and the weights of the base classifiers whose results meet the preset threshold, and the periodic result of the submarine cable disturbance sensing data is determined according to the output result of the target classifier, which can automatically monitor the state of submarine equipment and the periodic monitoring of submarine cable disturbance sensing data, give early warnings of possible damages to submarine equipment in advance, realize timely monitoring of the state of submarine equipment, and reduce the costs of maintenance and repair of submarine equipment. Description of the Drawings

[0045] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is an application environment diagram of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0047] Figure 2 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0048] Figure 3 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0049] Figure 4 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0050] Figure 5 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0051] Figure 6 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0052] Figure 7 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0053] Figure 8 It is a schematic flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0054] Figure 9 It is a schematic principle flowchart of the periodic monitoring method for submarine cable disturbance sensing data in an embodiment;

[0055] Figure 10 It is a schematic diagram of the periodic monitoring system for submarine cable disturbance sensing data in an embodiment;

[0056] Figure 11 It is a structural block diagram of the periodic monitoring device for submarine cable disturbance sensing data in an embodiment;

[0057] Figure 12 It is an internal structure diagram of a computer device in an embodiment. Specific embodiments

[0058] In order to make the objectives, technical solutions, and advantages of the present disclosure more clear and understandable, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not used to limit the present disclosure.

[0059] The periodic monitoring method for submarine cable disturbance sensing data provided by an embodiment of the present disclosure can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. The terminal 102 acquires the disturbance sensing data of the submarine cable collected by multiple sensors; after the server 104 or the terminal 102 preprocesses the disturbance sensing data in a preset manner, target data is obtained; N algorithms in a preset algorithm pool are used to judge the target data to obtain a set of periodic data with a length of N; M periodic data subsets are selected from the set of periodic data with a length of N, and the M periodic data subsets respectively correspond to M base classifiers, where the weights of the M base classifiers are equal; if the output result of the base classifier does not meet the preset threshold, the weight of the base classifier whose output result does not meet the preset threshold is increased according to a preset rule until the output result of the base classifier meets the preset threshold; according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold, a target classifier is obtained, and the periodic result of the submarine cable disturbance sensing data is determined according to the output result of the target classifier. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0060] In one embodiment, as Figure 2 shown, a periodic monitoring method for submarine cable disturbance sensing data is provided. Taking the method applied to the Figure 1 terminal as an example, the method includes the following steps:

[0061] S202. Acquire the disturbance sensing data of the submarine cable collected by multiple sensors.

[0062] Among them, the sensing data may include data sensed, measured, and transmitted by a sensing device or a sensor device. The sensing device or the sensor device may include one or more sensors.

[0063] Specifically, values of multiple sensors for measuring the disturbance sensing data of the submarine cable can be obtained.

[0064] S204. After preprocessing the disturbance sensing data in a preset manner, target data is obtained.

[0065] Among them, data preprocessing may include some processing of data before main processing. For example, for most geophysical areal observation data, before conversion or enhancement processing, the irregularly distributed survey network is first interpolated and converted into a regular network for the convenience of computer operation.

[0066] Specifically, the disturbance sensing data can be preprocessed in a preset manner before predicting the trend of the data, and the target data is obtained after the disturbance sensing data is preprocessed.

[0067] S206. Use N algorithms in a pre-set algorithm pool to judge the target data, and obtain a set of periodic data with a length of N.

[0068] Among them, the N algorithms in the pre-set algorithm pool may include Fourier transform and may also include the autocorrelation coefficient method. The pre-set algorithm pool may include an ensemble learning algorithm.

[0069] Specifically, the target data can be judged by using algorithms such as Fourier transform and autocorrelation coefficient method in the pre-set algorithm pool to obtain a set of periodic data with a length of N.

[0070] S208. Select M periodic data subsets from the set of periodic data with a length of N. The M periodic data subsets respectively correspond to M base classifiers, where the weights of the M base classifiers are equal.

[0071] Among them, the equal weights of the base classifiers may include that the proportions of the M base classifiers in the total base classifiers are equal. For example, the proportions of the M base classifiers are all 1 / M.

[0072] Specifically, M periodic data subsets can be selected from the set of periodic data with a length of N. The M periodic data subsets respectively correspond to M base classifiers and the weights of the M base classifiers are equal.

[0073] S210. If the output result of the base classifier does not meet the preset threshold, increase the weight of the base classifier whose output result does not meet the preset threshold according to the preset rule until the output result of the base classifier meets the preset threshold.

[0074] Among them, the preset threshold can be a value set in advance according to experience, etc., and can be, for example, 0.2, 0.8, etc. The preset rule can include the value of weight increase set according to experience or actual situation. For example, the weight of the base classifier that does not meet the preset threshold can be increased by 3%, 8%, etc.

[0075] Specifically, when the output result of the base classifier does not meet the preset threshold, increase the weight of the base classifier whose output result does not meet the preset threshold according to the preset rule until the output result of the base classifier meets the preset threshold.

[0076] S212. Obtain a target classifier according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold, and determine the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

[0077] Among them, the periodic result of the submarine cable disturbance sensing data can include that the submarine cable disturbance sensing data has no periodicity, or can include periodicity. Exemplarily, the period of periodicity can include 1 week, etc.

[0078] Specifically, a target classifier can be obtained according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold; Exemplarily, the result of the base classifier can be multiplied by the weight of the base classifier to obtain a multiplication value, and then all the multiplication values are added to obtain the output result of the target classifier. Determine the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

[0079] In the above method for periodically monitoring submarine cable disturbance sensing data, the disturbance sensing data of the submarine cable collected by multiple sensors is obtained; after preprocessing the disturbance sensing data in a preset manner, target data is obtained; N algorithms in a preset algorithm pool are used to judge the target data to obtain a set of periodic data with a length of N; M subsets of periodic data are selected from the set of periodic data with a length of N, and the M subsets of periodic data respectively correspond to M base classifiers, where the weights of the M base classifiers are equal; if the output result of the base classifier does not meet the preset threshold, the weight of the base classifier whose output result does not meet the preset threshold is increased according to a preset rule until the output result of the base classifier meets the preset threshold; according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold, a target classifier is obtained, and according to the output result of the target classifier, the periodic result of the submarine cable disturbance sensing data is determined, which can automatically monitor the state of submarine equipment and the periodic monitoring of submarine cable disturbance sensing data, give early warnings of possible damages to submarine equipment, realize timely monitoring of the state of submarine equipment, and reduce the maintenance and repair costs of submarine equipment.

[0080] In one embodiment, as Figure 3 shown, step S206 uses N algorithms in a preset algorithm pool to judge the target data to obtain a set of periodic data with a length of N, including the following steps:

[0081] S302. Expand the target data into a linear combination of trigonometric functions.

[0082] Among them, expanding the target data into a linear combination of trigonometric functions may include Fourier transform.

[0083] Specifically, the target data can be expanded into a linear combination of trigonometric functions through Fourier transform or the like.

[0084] S304. Determine the term with the largest coefficient in the linear combination of trigonometric functions.

[0085] Among them, the term with the largest coefficient in the linear combination of trigonometric functions may include the maximum value in Fourier coefficients.

[0086] Specifically, the term with the largest coefficient in the linear combination of trigonometric functions can be determined through Fourier coefficients.

[0087] S306. Obtain a set of periodic data with a length of N according to the term with the largest coefficient.

[0088] Among them, the term with the largest coefficient may include periodic data.

[0089] Specifically, a periodic data set of length N can be obtained according to the maximum term of the coefficients, such as the maximum value of the Fourier coefficients.

[0090] In this embodiment, by expanding the target data into a linear combination of trigonometric functions, determining the maximum term of the coefficients in the linear combination of trigonometric functions, and then obtaining a periodic data set of length N according to the maximum term of the coefficients, the state of the subsea equipment can be automatically monitored and the periodic monitoring of the subsea cable disturbance sensing data can be achieved.

[0091] In one embodiment, as Figure 4 shown, the method further includes the following steps:

[0092] S402. Determine a set of maximum coefficient terms according to the maximum coefficient terms in the linear combination of trigonometric functions.

[0093] Among them, the set of maximum coefficient terms may include the maximum coefficient terms in the linear combination of all trigonometric functions.

[0094] Specifically, a set of maximum coefficient terms can be determined according to the maximum coefficient terms in the linear combination of trigonometric functions.

[0095] S404. Determine the autocorrelation coefficient of the subset in the set of maximum coefficient terms.

[0096] Among them, the autocorrelation coefficient can be calculated according to the Pearson correlation coefficient method (Pearson Correlation Coefficient).

[0097] Specifically, the Pearson correlation coefficient method can be used to determine the autocorrelation coefficient of the subset in the set of maximum coefficient terms.

[0098] S406. Compare the autocorrelation coefficient of the subset with a preset autocorrelation coefficient threshold.

[0099] Among them, the autocorrelation coefficient threshold can be a value preset according to experience, etc.

[0100] Specifically, the autocorrelation coefficient of the subset can be compared with the preset autocorrelation coefficient threshold.

[0101] S408. Determine the subset whose autocorrelation coefficient of the subset is greater than or equal to the preset autocorrelation coefficient threshold.

[0102] Specifically, the subset whose autocorrelation coefficient of the subset is greater than or equal to the preset autocorrelation coefficient threshold can be determined.

[0103] S410. Determine the period of the set of maximum coefficient terms according to the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold.

[0104] Specifically, the period of the set of maximum coefficient terms can be determined by the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold.

[0105] In this embodiment, the set of maximum coefficient terms is determined by the maximum coefficient term in the linear combination of the trigonometric functions; the autocorrelation coefficient of the subset in the set of maximum coefficient terms is determined; the autocorrelation coefficient of the subset is compared with the preset autocorrelation coefficient threshold; the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold is determined; and the period of the set of maximum coefficient terms is determined by the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold, so as to automatically monitor the state of the subsea equipment and the periodic monitoring of the subsea cable disturbance sensing data.

[0106] In one embodiment, as Figure 5 shown, step S410 of determining the period of the set of maximum coefficient terms according to the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold includes the following steps:

[0107] S502. Determine any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold.

[0108] Among them, any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold may include determining any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold determined by the autocorrelation coefficient method.

[0109] Specifically, any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold can be determined by using the autocorrelation coefficient method.

[0110] S504. Perform a difference operation on the start times of the any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold and take the absolute value to obtain the period of the set of maximum coefficient terms.

[0111] Specifically, the period of the set of maximum coefficient terms can be obtained by performing a difference operation on the start times of the any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold and taking the absolute value.

[0112] In this embodiment, by determining any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold; performing a difference operation on the start times of the any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold and taking the absolute value to obtain the period of the set of maximum coefficient terms, the state of the subsea equipment can be automatically monitored and the periodic monitoring of the subsea cable disturbance sensing data can be performed.

[0113] In one embodiment, as Figure 6 shown, after preprocessing the disturbance sensing data in a preset manner in step S204, obtaining the target data includes the following steps:

[0114] S602. Resample the disturbance sensing data to obtain resampled data. The resampling includes at least one of resampling according to the dimension of days, resampling according to the dimension of weeks, and resampling according to the dimension of months.

[0115] Among them, resampling may include that since the disturbance sensing data collected by the sensor is usually uneven or discontinuous, the disturbance sensing data needs to be resampled. According to the dimension of trend analysis, resampling is generally performed for the dimensions of days, weeks, and months.

[0116] Specifically, the disturbance sensing data can be resampled by one of resampling according to the dimension of days, resampling according to the dimension of weeks, and resampling according to the dimension of months to obtain resampled data.

[0117] S604. Filter data outliers from the resampled data to obtain outlier-filtered data.

[0118] Specifically, data outliers can be filtered from the resampled data to obtain outlier-filtered data. In some embodiments, a program judgment filtering method can be used to filter outliers.

[0119] S606. Perform dimensionless processing on the outlier-filtered data to obtain target data. The dimensionless processing includes at least one of linear dimensionless processing and non-linear dimensionless processing.

[0120] Among them, dimensionless processing can help the system improve the accuracy of the model, and thus avoid the influence of data with a particularly large value range on distance calculation.

[0121] Specifically, the outlier-filtered data can be subjected to dimensionless processing to obtain target data. The dimensionless processing of data can be linear or non-linear. Linear dimensionless processing includes centering processing and scaling processing. The essence of centering can include subtracting a fixed value from all records, that is, translating the data sample data to a certain position. The essence of scaling can be to divide by a fixed value to fix the data within a certain range. The scaling processing can also include taking logarithms.

[0122] In this embodiment, by performing resampling processing on the disturbance sensing data, resampled data is obtained; by filtering data outliers from the resampled data, outlier-filtered data is obtained; by performing dimensionless processing on the outlier-filtered data, target data is obtained, which can make the result of the periodic monitoring of the disturbance data of the submarine cable more accurate.

[0123] In one embodiment, as Figure 7 shown, step S604 of filtering data outliers from the resampled data to obtain outlier-filtered data includes the following steps:

[0124] S702. Perform rule calculation on the resampled data to obtain rule calculation data, where the rule calculation includes at least one of calculating the average value of the resampled data and calculating the variance of the resampled data.

[0125] Specifically, rule calculation data can be obtained by performing one of calculating the average value of the resampled data and calculating the variance of the resampled data.

[0126] S704. Take the absolute value of the difference between the resampled data and the rule calculation data to obtain deviation data.

[0127] Specifically, deviation data can be obtained by subtracting the rule calculation data from the resampled data and taking the absolute value of the subtracted difference.

[0128] S706. Compare the target deviation data in the deviation data with a preset deviation threshold.

[0129] Specifically, the target deviation data in the deviation data can be compared with a preset deviation threshold.

[0130] S708. If the target deviation data is greater than the preset deviation threshold, set the resampled data corresponding to the target deviation data as an outlier and remove the outlier from the resampled data to obtain outlier-filtered data.

[0131] Specifically, if the target deviation data is greater than the preset deviation threshold, the resampled data corresponding to the target deviation data can be set as an outlier and the outlier can be removed from the resampled data to obtain outlier-filtered data.

[0132] In this embodiment, by filtering data outliers from the resampled data to obtain outlier-filtered data, the result of the periodic monitoring of the disturbance data of the submarine cable can be made more accurate.

[0133] In one embodiment, as Figure 8As shown, a method for periodically monitoring submarine cable disturbance sensing data is provided, and the method includes the following steps:

[0134] S802. Obtain the disturbance sensing data of the submarine cable collected by multiple sensors.

[0135] S804. Perform resampling processing on the disturbance sensing data to obtain resampled data, and the resampling includes at least one of resampling according to the dimension of days, resampling according to the dimension of weeks, and resampling according to the dimension of months.

[0136] S806. Perform rule calculation on the resampled data to obtain rule calculation data, and the rule calculation includes at least one of calculating the average value of the resampled data and calculating the variance of the resampled data.

[0137] S808. Take the absolute value of the difference between the resampled data and the rule calculation data to obtain deviation data.

[0138] S810. Compare the target deviation data in the deviation data with a preset deviation threshold.

[0139] S812. If the target deviation data is greater than the preset deviation threshold, set the resampled data corresponding to the target deviation data as an outlier and remove the outlier from the resampled data to obtain outlier-filtered data.

[0140] S814. Perform dimensionless processing on the outlier-filtered data to obtain target data, and the dimensionless processing includes at least one of linear dimensionless processing and non-linear dimensionless processing.

[0141] S816. Expand the target data into a linear combination of trigonometric functions.

[0142] S818. Determine the term with the largest coefficient in the linear combination of trigonometric functions.

[0143] S820. Determine a set of terms with the largest coefficients according to the term with the largest coefficient in the linear combination of trigonometric functions.

[0144] S822. Determine the autocorrelation coefficient of the subset in the set of terms with the largest coefficients.

[0145] S824. Compare the autocorrelation coefficient of the subset with a preset autocorrelation coefficient threshold.

[0146] S826. Determine the subsets whose autocorrelation coefficients of the subsets are greater than or equal to the preset autocorrelation coefficient threshold.

[0147] S828. Determine any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold.

[0148] S830. Perform a difference operation on the start times of the any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold and take the absolute value to obtain the period of the coefficient maximum term set.

[0149] S832. Obtain a periodic data set of length N according to the coefficient maximum term.

[0150] S834. Select M periodic data subsets from the periodic data set of length N. The M periodic data subsets respectively correspond to M base classifiers, where the weights of the M base classifiers are equal.

[0151] S836. If the output result of the base classifier does not meet the preset threshold, increase the weight of the base classifier whose output result does not meet the preset threshold according to the preset rule until the output result of the base classifier meets the preset threshold.

[0152] S838. Obtain a target classifier according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold, and determine the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

[0153] In one embodiment, as Figure 9 shown, a principle flowchart of a method for periodically monitoring submarine cable disturbance sensing data is provided. By performing normalization preprocessing, resampling preprocessing, and standardization preprocessing on the original data collected by the sensor, using the Fourier transform (FFT) on the preprocessed data, and then using the autocorrelation coefficient method (ACF) for processing, the obtained data is used as the input of the Boosting ensemble learning algorithm, and the output of the Boosting ensemble learning algorithm is the specific period value or aperiodic result of the submarine cable disturbance sensing data.

[0154] In one embodiment, as Figure 10As shown, a periodic monitoring system for submarine cable disturbance sensing data is provided. The system consists of a policy module 1002, a database 1004, and a front end 1006. The policy module 1002 is used to read the original data in the database 1004 and determine and output periodic indicators according to the original data. The database 1004 is used to store the original data and also to receive and store the periodic indicators output by the policy module 1002. The front end 1006 is used to read the periodic indicators in the database 1004, obtain a periodic intensity curve using the periodic indicators, and obtain a data periodic monitoring result according to the periodic intensity curve. The policy module 1002 is further used to: read the original data in the database 1004, perform data preprocessing on the original data to obtain time series data; determine periodic indicators according to the time series data; and send the periodic indicators to the database 1004. The front end 1006 is further used to read the original data in the database 1004, obtain a disturbance curve according to the original data, and perform periodic monitoring of submarine cable disturbance sensing data using the disturbance curve. The front end 1006 is further used to read the alarm data in the database 1004, obtain an alarm message according to the alarm data, and send out an alarm message when the submarine cable disturbance sensing data is in an abnormal state.

[0155] It should be understood that although Figures 2 to 8 the steps in the flowchart of Figures 2 to 8 are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0156] Based on the same inventive concept, the embodiments of the present disclosure also provide a periodic monitoring device for submarine cable disturbance sensing data for implementing the above-mentioned periodic monitoring method for submarine cable disturbance sensing data. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the periodic monitoring device for submarine cable disturbance sensing data provided below can refer to the limitations on the periodic monitoring method for submarine cable disturbance sensing data in the above text, and will not be repeated here.

[0157] In one embodiment, as Figure 11As shown in the figure, a periodic monitoring device 1100 for submarine cable disturbance sensing data is provided, including: a data acquisition module 1102, a target data module 1104, a periodic data set module 1106, a subset module 1108, a weight adjustment module 1110, and a result determination module 1112, where:

[0158] The data acquisition module 1102 is configured to acquire the disturbance sensing data of the submarine cable collected by multiple sensors.

[0159] The target data module 1104 is configured to obtain target data after preprocessing the disturbance sensing data in a preset manner.

[0160] The periodic data set module 1106 is configured to use N algorithms in a pre-set algorithm pool to judge the target data, and obtain a periodic data set with a length of N.

[0161] The subset module 1108 is configured to select M periodic data subsets from the periodic data set with a length of N. The M periodic data subsets respectively correspond to M base classifiers, where the weights of the M base classifiers are equal.

[0162] The weight adjustment module 1110 is configured to, if the output result of the base classifier does not meet the preset threshold, increase the weight of the base classifier whose output result does not meet the preset threshold according to a preset rule until the output result of the base classifier meets the preset threshold.

[0163] The result determination module 1112 is configured to obtain a target classifier according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold, and determine the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

[0164] Each module in the above-mentioned periodic monitoring device for submarine cable disturbance sensing data can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0165] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 12As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a method for periodically monitoring submarine cable disturbance sensing data. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0166] Those skilled in the art can understand that Figure 12 the structure shown in the figure is only a block diagram of some structures related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0167] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are realized.

[0168] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are realized.

[0169] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are realized.

[0170] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties.

[0171] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided by the present disclosure can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided by the present disclosure can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0172] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0173] The above-described embodiments merely represent several implementation manners of the present disclosure. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent of the present disclosure. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present disclosure, several modifications and improvements can still be made, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the appended claims.

Claims

1. A method for periodic monitoring of submarine cable disturbance sensor data, It is characterized in that The method comprises: Acquiring disturbance sensing data from submarine cables collected by multiple sensors; After preprocessing the disturbance sensing data in a preset manner, target data is obtained; Expanding the target data into a linear combination of trigonometric functions; Determining the maximum coefficient term in the linear combination of the trigonometric functions; Obtaining a periodic data set with a length of N according to the maximum term of the coefficient; Determining a set of maximum coefficient terms according to the maximum coefficient terms in the linear combination of the trigonometric functions; Determining the autocorrelation coefficient of the subset in the maximum coefficient term set; comparing the autocorrelation coefficient of the subset with a preset autocorrelation coefficient threshold; Determine a subset whose autocorrelation coefficient of the subset is greater than or equal to the preset autocorrelation coefficient threshold; Determining the period of the maximum coefficient term set according to the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold; Selecting M periodic data subsets from a periodic data set of length N, wherein the M periodic data subsets correspond to M base classifiers respectively, wherein the weights of the M base classifiers are equal; If the output result of the base classifier does not meet the preset threshold, the weight of the base classifier whose output result does not meet the preset threshold is increased according to the preset rule until the output result of the base classifier meets the preset threshold; A target classifier is obtained according to the base classifiers whose results meet the preset threshold and the weights of the base classifiers whose results meet the preset threshold, and the periodic results of the submarine cable disturbance sensing data are determined according to the output results of the target classifier.

2. The method according to claim 1, It is characterized in that The step of determining the period of the maximum coefficient term set according to the subset whose autocorrelation coefficient is greater than or equal to the preset autocorrelation coefficient threshold comprises: Determine a subset of any two autocorrelation coefficients that are greater than or equal to the preset autocorrelation coefficient threshold; The start times of any two subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold are subjected to a difference operation and the absolute value is taken to obtain the period of the maximum coefficient item set.

3. The method according to claim 1, It is characterized in that After the disturbance sensing data is preprocessed in a preset manner, the target data is obtained, including: Resampling the disturbance sensing data to obtain resampled data, wherein the resampling includes at least one of resampling according to a day dimension, resampling according to a week dimension, and resampling according to a month dimension; Performing data outlier filtering on the resampled data to obtain outlier filtered data; The abnormal value filtered data is dimensionally processed to obtain target data, wherein the dimensionally processed data includes at least one of linear dimensionally processed data and nonlinear dimensionally processed data.

4. The method according to claim 3, It is characterized in that The performing data outlier filtering on the resampled data to obtain outlier filtered data comprises: Perform regular calculations on the resampled data to obtain regular calculation data, where the regular calculations include at least one of calculating the average value of the resampled data and calculating the variance of the resampled data; Take the absolute value of the difference between the resampled data and the regular calculation data to obtain deviation data; Compare the target deviation data in the deviation data with a preset deviation threshold; If the target deviation data is greater than the preset deviation threshold, set the resampled data corresponding to the target deviation data as an outlier and remove the outlier from the resampled data to obtain outlier-filtered data.

5. A periodic monitoring device for submarine cable disturbance sensing data, Characterized in that, The device includes: A data acquisition module for acquiring disturbance sensing data of a submarine cable collected by a plurality of sensors; A target data module for obtaining target data after preprocessing the disturbance sensing data in a preset manner; A periodic data set module for expanding the target data into a linear combination of trigonometric functions; Determine the term with the largest coefficient in the linear combination of the trigonometric functions; Obtain a periodic data set of length N according to the term with the largest coefficient; Determine a coefficient maximum term set according to the term with the largest coefficient in the linear combination of the trigonometric functions; Determine the autocorrelation coefficient of a subset in the coefficient maximum term set; Compare the autocorrelation coefficient of the subset with a preset autocorrelation coefficient threshold; Determine the subsets whose autocorrelation coefficients of the subsets are greater than or equal to the preset autocorrelation coefficient threshold; Determine the period of the coefficient maximum term set according to the subsets whose autocorrelation coefficients are greater than or equal to the preset autocorrelation coefficient threshold; A subset module for selecting M periodic data subsets from the periodic data set of length N, where the M periodic data subsets respectively correspond to M base classifiers, and the weights of the M base classifiers are equal; A weight adjustment module for, if the output result of the base classifier does not meet the preset threshold, adjusting the weight of the base classifier whose output result does not meet the preset threshold upward according to a preset rule until the output result of the base classifier meets the preset threshold; A result determination module for obtaining a target classifier according to the base classifier whose result meets the preset threshold and the weight of the base classifier whose result meets the preset threshold, and determining the periodic result of the submarine cable disturbance sensing data according to the output result of the target classifier.

6. A computer device, including a memory and a processor, the memory stores a computer program, Characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, on which a computer program is stored, Characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product, including a computer program, Characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images