Method and apparatus for trend monitoring of subsea cable disturbance sensor data

Abstract

The present disclosure relates to a method and device for trend monitoring of subsea cable disturbance sensing data. The method comprises: obtaining disturbance sensing data of a subsea cable collected by a plurality of sensors; obtaining target data by performing data preprocessing on the disturbance sensing data in a preset manner; using N algorithms in a pre-set algorithm pool to judge the target data to obtain a probability set with a length of N; selecting M sub-probability sets with a length of n from the probability set with a length of N with replacement, wherein the replacement means that any probability data in the probability set can be repeated as probability data in the sub-probability set; and determining a trend monitoring result of the subsea cable disturbance sensing data according to the M models, so as to monitor the trend of the disturbance data of the subsea cable, realize timely monitoring of the state of the subsea equipment, and reduce the cost of maintenance and repair of the subsea equipment.

Description

Technical Field

[0001] This disclosure relates to the field of submarine cable monitoring technology, and in particular to a method and apparatus for trend monitoring of submarine cable disturbance sensing data. Background Technology

[0002] Marine resources are a relatively easy-to-explore treasure trove for humankind, and the construction of various marine and subsea engineering projects is progressing smoothly. However, compared to land, the difficulties and dangers of working in the underwater environment are much greater, and the monitoring and maintenance of subsea facilities are also more challenging. The marine environment is extremely complex, and subsea facilities are more prone to unexpected risks, while the costs of facility maintenance and repair are exorbitant. Therefore, how to automatically monitor the status of subsea equipment, provide early warnings of potential damage, achieve timely monitoring of the status of subsea equipment, and reduce the costs of maintenance and repair is an urgent issue that needs to be addressed. Summary of the Invention

[0003] Therefore, it is necessary to provide a trend monitoring method and device for submarine cable disturbance sensing data that can automatically monitor the status of submarine equipment, addressing the aforementioned technical problems.

[0004] In one aspect, this disclosure provides a method for trend monitoring of submarine cable disturbance sensing data.

[0005] The method includes:

[0006] Acquire disturbance sensing data of submarine cables collected by multiple sensors;

[0007] After preprocessing the disturbance sensing data according to a preset method, the target data is obtained;

[0008] The target data is judged using N algorithms from a pre-set algorithm pool to obtain a probability set of length N;

[0009] From a probability set of length N, select M sub-probability sets of length n with replacement, wherein the replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set;

[0010] The trend monitoring results of the submarine cable disturbance sensing data are determined based on M models, wherein the M models are obtained from the M sub-probability sets.

[0011] In one embodiment, the step of determining the trend monitoring result of the submarine cable disturbance sensing data based on M models, wherein the M models are obtained based on the M sub-probability sets, including:

[0012] The M sub-probability sets are calculated using a pre-set machine learning algorithm to obtain M models, wherein the pre-set machine learning algorithm includes at least one of a classification algorithm and a regression algorithm;

[0013] The output results of the M models are processed according to a preset value selection algorithm to obtain the trend monitoring results of the submarine cable disturbance sensing data. The preset value selection algorithm includes at least one of taking the average value of the output results of the M models and taking the majority vote of the output results of the M models.

[0014] In one embodiment, the step of using N algorithms from a pre-set algorithm pool to judge the target data and obtain a probability set of length N includes:

[0015] The target data is fitted to a straight line using the least squares method;

[0016] The target data is judged based on the slope of the straight line to obtain probability data;

[0017] Based on the probability data, a probability set of length N is obtained.

[0018] In one embodiment, the step of using N algorithms from a pre-set algorithm pool to judge the target data and obtain a probability set of length N includes:

[0019] The data at a specific location in the target data is compared with the data at the next adjacent location in the target data to obtain the comparison result;

[0020] The target data is judged based on the sign of the comparison result to obtain probability data;

[0021] Based on the probability data, a probability set of length N is obtained.

[0022] In one embodiment, the step of preprocessing the disturbance sensing data according to a preset method to obtain the target data includes:

[0023] The disturbance sensing data is resampled to obtain resampled data. The resampling includes at least one of resampling by day, resampling by week, and resampling by month.

[0024] The resampled data is then subjected to outlier filtering to obtain outlier filtered data.

[0025] The outlier filtering data is subjected to dimensionless processing to obtain the target data. The dimensionless processing includes at least one of linear dimensionless processing and nonlinear dimensionless processing.

[0026] In one embodiment, the step of filtering outliers from the resampled data to obtain outlier-filtered data includes:

[0027] The resampled data is subjected to rule calculation 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.

[0028] The absolute value of the difference between the resampled data and the rule-calculated data is taken to obtain the deviation data;

[0029] Compare the target deviation data in the deviation data with a preset deviation threshold;

[0030] If the target deviation data is greater than the preset deviation threshold, the resampled data corresponding to the target deviation data is set as an outlier and the outlier is removed from the resampled data to obtain outlier filtered data.

[0031] Secondly, this disclosure also provides a trend monitoring device for submarine cable disturbance sensing data. The device includes:

[0032] The data acquisition module is used to acquire disturbance sensing data of the submarine cable collected by multiple sensors;

[0033] The target data module is used to preprocess the disturbance sensing data according to a preset method to obtain target data;

[0034] The probability set module is used to judge the target data using N algorithms in a pre-set algorithm pool to obtain a probability set of length N;

[0035] The sub-probability set module is used to select M sub-probability sets of length n from a probability set of length N with replacement, wherein replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set;

[0036] The monitoring result determination module is used to determine the trend monitoring result of the submarine cable disturbance sensing data based on M models, wherein the M models are obtained based on the M sub-probability sets.

[0037] Thirdly, this disclosure also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the methods described in any embodiment of this disclosure.

[0038] Fourthly, this disclosure also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the methods described in any embodiment of this disclosure.

[0039] Fifthly, this disclosure also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the methods described in any embodiment of this disclosure.

[0040] The aforementioned method and apparatus for trend monitoring of submarine cable disturbance sensing data acquires disturbance sensing data of submarine cables collected by multiple sensors; preprocesses the disturbance sensing data according to a preset method to obtain target data; uses N algorithms from a pre-set algorithm pool to judge the target data, obtaining a probability set of length N; selects M sub-probability sets of length n with replacement from the probability set of length N, where replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set; and determines the trend monitoring result of the submarine cable disturbance sensing data based on the M models. This allows for monitoring of the trend of submarine cable disturbance data, enabling timely monitoring of the status of submarine equipment and reducing the cost of submarine equipment maintenance and repair. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is an application environment diagram of a trend monitoring method for submarine cable disturbance sensing data in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0044] Figure 3 This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0045] Figure 4 This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0046] Figure 5This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0047] Figure 6 This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0048] Figure 7 This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0049] Figure 8 This is a flowchart illustrating a method for trend monitoring of submarine cable disturbance sensing data in one embodiment.

[0050] Figure 9 This is a schematic diagram illustrating the principle of a trend monitoring method for submarine cable disturbance sensing data in one embodiment.

[0051] Figure 10 This is a schematic diagram of a trend monitoring system for submarine cable disturbance sensor data in one embodiment;

[0052] Figure 11 This is a structural block diagram of a device for monitoring trends in submarine cable disturbance sensing data in one embodiment;

[0053] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this disclosure.

[0055] The method provided in this disclosure can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Terminal 102 acquires disturbance sensing data of the submarine cable collected by multiple sensors, preprocesses the disturbance sensing data according to a preset method, and obtains target data. Terminal 102 or server 104 uses N algorithms from a pre-set algorithm pool to judge the target data, obtaining a probability set of length N. From the probability set of length N, M sub-probability sets of length n are selected with replacement. The trend monitoring results of the submarine cable disturbance sensing data are determined based on the M models, wherein the M models are obtained based on the M sub-probability sets. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0056] In one embodiment, such as Figure 2 As shown, a method for trend monitoring of submarine cable disturbance sensing data is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps:

[0057] S202. Acquire disturbance sensing data of the submarine cable collected by multiple sensors.

[0058] The sensing data may include data sensed, measured, and transmitted by a sensing device or a sensor. The sensing device or sensor may include one or more sensors.

[0059] Specifically, values ​​from multiple sensors used to measure disturbance sensing data of submarine cables can be obtained.

[0060] S204. After preprocessing the disturbance sensing data according to a preset method, the target data is obtained.

[0061] Data preprocessing can include some processing of the data before the main processing. For example, before transforming or enhancing most geophysical area observation data, irregularly distributed survey networks are first converted into regular networks through interpolation to facilitate computer computation.

[0062] Specifically, the disturbance sensing data can be preprocessed according to a preset method before predicting the trend of the data, and the target data can be obtained after the disturbance sensing data is preprocessed.

[0063] S206. Use N algorithms from a pre-set algorithm pool to judge the target data and obtain a probability set of length N.

[0064] The algorithm pool can include a collection of algorithms consisting of multiple different algorithms. The probability set can include a collection of probability data consisting of multiple probability data sets.

[0065] Specifically, the target data can be evaluated using N algorithms from a pre-set algorithm pool. Each algorithm in the pool outputs a probability value after evaluating the target data. Therefore, the N algorithms in the pool will produce N probability values ​​after evaluating the target data. These N probability values ​​can be combined to form a probability set of length N.

[0066] S208. Select M sub-probability sets of length n from a probability set of length N with replacement, wherein replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set.

[0067] Where n takes values ​​in the range of 1 ≤ n ≤ N. With replacement can include any probability data in the probability set being repeatedly used as probability data in a sub-probability set. For example, the probability data in a sub-probability set can include two or more identical probability data; the probability data in any two sub-probability sets can also include identical probability data.

[0068] Specifically, this can be achieved by selecting M sub-probability sets of length n with replacement from a probability set of length N.

[0069] S210. Determine the trend monitoring results of the submarine cable disturbance sensing data based on M models, wherein the M models are obtained based on the M sub-probability sets.

[0070] The trend monitoring results of submarine cable disturbance sensing data can include any of the following: an upward trend, a downward trend, or no trend.

[0071] Specifically, M models can be obtained from M sub-probability sets, and then the trend monitoring results of the submarine cable disturbance sensing data can be determined based on the M models.

[0072] In the aforementioned trend monitoring method for submarine cable disturbance sensing data, disturbance sensing data of the submarine cable collected by multiple sensors is acquired; the disturbance sensing data is preprocessed according to a preset method to obtain target data; the target data is judged using N algorithms in a pre-set algorithm pool to obtain a probability set of length N; M sub-probability sets of length n are selected from the probability set of length N with replacement, where replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set; the trend monitoring result of the submarine cable disturbance sensing data is determined according to the M models, which can monitor the trend of submarine cable disturbance data, realize timely monitoring of the status of submarine equipment, and reduce the cost of submarine equipment maintenance and repair.

[0073] In one embodiment, such as Figure 3 As shown, step S210 determines the trend monitoring results of the submarine cable disturbance sensing data based on M models, wherein the M models are obtained based on the M sub-probability sets, including the following steps:

[0074] S302. Calculate the M sub-probability sets using a pre-set machine learning algorithm to obtain M models, wherein the pre-set machine learning algorithm includes at least one of a classification algorithm and a regression algorithm.

[0075] The purpose of classification can include determining the category of a point, specifically identifying which categories are known. A commonly used algorithm is KNN (k-nearest neighbors algorithm), a type of supervised learning. Regression algorithms can include linear regression, which can be trained extensively to obtain a model that best fits the data.

[0076] Specifically, M models can be obtained by calculating the M sub-probability sets using a pre-set machine learning algorithm. For example, the M models can be obtained by calculating the M sub-probability sets using a pre-set classification algorithm, regression algorithm, etc.

[0077] S304. The output results of the M models are processed according to a preset value-taking algorithm to obtain the trend monitoring results of the submarine cable disturbance sensing data. The preset value-taking algorithm includes at least one of taking the average value of the output results of the M models and taking the majority vote of the output results of the M models.

[0078] A majority vote, also known as "majority consent," can be one of the voting rules. A decision requires more than half of the votes to pass.

[0079] Specifically, the trend monitoring results of submarine cable disturbance sensing data can be obtained by processing the output results of the M models according to a preset value-taking algorithm. In some embodiments, the trend monitoring results of submarine cable disturbance sensing data can be obtained by processing the output results of the M models according to one of the following methods: averaging the output results of the M models or taking the majority vote of the output results of the M models.

[0080] In this embodiment, M sub-probability sets are calculated using pre-set classification and regression algorithms to obtain M models. The output results of the M models are processed according to one of two methods: averaging the output results of the M models or taking the majority vote of the output results of the M models. This yields trend monitoring results of submarine cable disturbance sensing data, enabling monitoring of the trend of submarine cable disturbance data, achieving timely monitoring of the status of submarine equipment, and reducing the cost of submarine equipment maintenance and repair.

[0081] In one embodiment, such as Figure 4 As shown, step S206 uses N algorithms from a pre-set algorithm pool to judge the target data and obtain a probability set of length N, including the following steps:

[0082] S402. Use the least squares method to fit the target data into a straight line.

[0083] The least squares method is the most commonly used method for solving curve fitting problems. It finds the best function fit for the data by minimizing the square of the error. The least squares method can be used to easily obtain unknown data and minimize the sum of the squares of the errors between the obtained data and the actual data.

[0084] Specifically, the target data can be fitted to a straight line using the least squares method.

[0085] S404. The target data is judged based on the slope of the straight line to obtain probability data.

[0086] Specifically, the slope of a straight line can be used to determine the target data and obtain probability data. In some implementations, the slope method can be used to determine the target data and obtain probability data. The specific process of using the slope method is as follows: the slope of the straight line obtained by using the least squares method is used to obtain probability data: the trend of the target data is determined based on the slope of the straight line. If a positive number is returned, it indicates positive growth; if a negative number is returned, it indicates a decline; if it is 0, it indicates no trend.

[0087] S406. Obtain a probability set of length N based on the probability data.

[0088] Specifically, the obtained probability data can be combined into a probability set of length N.

[0089] In this embodiment, the target data is fitted into a straight line using the least squares method. The slope of the straight line is used to judge the target data to obtain probability data. Based on the probability data, a probability set of length N is obtained, which can monitor the trend of disturbance data of submarine cables.

[0090] In one embodiment, such as Figure 5 As shown, step S206 uses N algorithms from a pre-set algorithm pool to judge the target data and obtain a probability set of length N, including the following steps:

[0091] S502. Compare the data at a specific position in the target data with the data at the next adjacent position in the target data to obtain a comparison result.

[0092] Specifically, a comparison result can be obtained by comparing the data at a specific position in the target data with the data at the next adjacent position in the target data. This comparison may include subtracting the data at the specific position in the target data from the data at the next adjacent position in the target data. The comparison result can be a positive number or a negative number.

[0093] S504. The target data is judged based on the sign of the comparison result to obtain probability data.

[0094] Specifically, the target data can be judged based on the sign of the comparison result to obtain probability data. In some implementations, the Cox-Stuart test can be used to judge the target data. This can be done by directly considering the trend of the target data. If the target data has an upward trend, the value of the data after it is ranked higher than the value of the data before it is ranked higher; conversely, if the target data has a downward trend, the value of the data after it is ranked lower than the value of the data before it is ranked higher. The overall trend of the target data is judged by the sign of the difference between different data in two periods. For example, the Mann-Kendall test can be used to judge the target data: this algorithm does not require the target data to follow a certain distribution and is not affected by a few outliers. For the statistic, a value greater than 0 indicates an upward trend, and a value less than 0 indicates a downward trend. A monotonically increasing or decreasing trend indicates that the variable increases or decreases over time. However, this trend can be linear or non-linear.

[0095] S506. Obtain a probability set of length N based on the probability data.

[0096] Specifically, the obtained probability data can be combined into a probability set of length N.

[0097] In this embodiment, a comparison result is obtained by comparing the data at a specific position in the target data with the data at the next adjacent position in the target data; the target data is judged based on the positive or negative sign of the comparison result to obtain probability data; a probability set of length N is obtained based on the probability data, which can monitor the trend of disturbance data of submarine cables.

[0098] In one embodiment, such as Figure 6 As shown, step S204, after preprocessing the disturbance sensing data according to a preset method to obtain the target data, includes the following steps:

[0099] S602. The disturbance sensing data is resampled to obtain resampled data. The resampling includes at least one of resampling by day, resampling by week, and resampling by month.

[0100] Resampling can be used to address the issue that disturbance sensing data collected by sensors is often non-uniform or discontinuous, thus requiring resampling of the data. Depending on the dimension of trend analysis, resampling is typically performed on a daily, weekly, or monthly basis.

[0101] Specifically, resampled data can be obtained by resampling the disturbance sensing data according to one of the following dimensions: day, week, or month.

[0102] S604. Perform outlier filtering on the resampled data to obtain outlier filtered data.

[0103] Specifically, outlier-filtered data can be obtained by filtering resampled data for outliers. In some implementations, outliers can be filtered using programmatic filtering.

[0104] S606. Perform dimensionless processing on the outlier filtering data to obtain the target data. The dimensionless processing includes at least one of linear dimensionless processing and nonlinear dimensionless processing.

[0105] Dimensionless processing can help the system improve the accuracy of the model, thereby avoiding the impact of a particularly large range of values ​​on distance calculation.

[0106] Specifically, the outlier filtering data can be dimensionless to obtain the target data. Dimensionless data processing can be linear or non-linear. Linear dimensionless processing includes centering and scaling. Centering essentially involves subtracting a fixed value from all records, essentially shifting the data sample to a certain position. Scaling essentially involves dividing by a fixed value to fix the data within a certain range; scaling can also include taking the logarithm.

[0107] In this embodiment, by resampling the disturbance sensing data to obtain resampled data, filtering outliers from the resampled data to obtain outlier filtered data, and then performing dimensionless processing on the outlier filtered data to obtain target data, the trend monitoring results of the disturbance data of submarine cables can be made more accurate.

[0108] In one embodiment, such as Figure 7 As shown, step S604 involves filtering outliers from the resampled data to obtain outlier-filtered data, which includes the following steps:

[0109] S702. 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.

[0110] Specifically, rule-based calculation data can be obtained by either averaging the resampled data or calculating the variance of the resampled data.

[0111] S704. Take the absolute value of the difference between the resampled data and the rule-calculated data to obtain the deviation data.

[0112] Specifically, the bias data can be obtained by subtracting the resampled data from the rule-calculated data and taking the absolute value of the difference.

[0113] S706. Compare the target deviation data in the deviation data with the preset deviation threshold.

[0114] Specifically, the target deviation data in the deviation data can be compared with a pre-set deviation threshold.

[0115] S708. If the target deviation data is greater than the preset deviation threshold, the resampled data corresponding to the target deviation data is set as an outlier and the outlier is removed from the resampled data to obtain outlier filtered data.

[0116] Specifically, if the target deviation data is greater than a preset deviation threshold, the resampled data corresponding to the target deviation data is set as an outlier and the outlier is removed from the resampled data to obtain outlier filtered data.

[0117] In this embodiment, by filtering outliers from the resampled data to obtain outlier-filtered data, the trend monitoring results of submarine cable disturbance data can be made more accurate.

[0118] In one embodiment, such as Figure 8 As shown, a method for trend monitoring of submarine cable disturbance sensing data is provided, including the following steps:

[0119] S802. Acquire disturbance sensing data of the submarine cable collected by multiple sensors.

[0120] S804. The disturbance sensing data is resampled to obtain resampled data. The resampling includes at least one of resampling by day, resampling by week, and resampling by month.

[0121] S806. 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.

[0122] S808. Take the absolute value of the difference between the resampled data and the rule-calculated data to obtain the deviation data.

[0123] S810. Compare the target deviation data in the deviation data with the preset deviation threshold.

[0124] S812. If the target deviation data is greater than the preset deviation threshold, the resampled data corresponding to the target deviation data is set as an outlier and the outlier is removed from the resampled data to obtain outlier filtered data.

[0125] S814. Perform dimensionless processing on the outlier filtering data to obtain the target data. The dimensionless processing includes at least one of linear dimensionless processing and nonlinear dimensionless processing.

[0126] S816. Fit the target data into a straight line using the least squares method.

[0127] S818. The target data is judged based on the slope of the straight line to obtain probability data.

[0128] S820. Obtain a probability set of length N based on the probability data.

[0129] S822. Compare the data at a specific position in the target data with the data at the next adjacent position in the target data to obtain a comparison result.

[0130] S824. The target data is judged based on the sign of the comparison result to obtain probability data.

[0131] S826. Obtain a probability set of length N based on the probability data.

[0132] S828. Select M sub-probability sets of length n from a probability set of length N with replacement, wherein replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set.

[0133] S830. Calculate the M sub-probability sets using a pre-set machine learning algorithm to obtain M models, wherein the pre-set machine learning algorithm includes at least one of a classification algorithm and a regression algorithm.

[0134] S832. The output results of the M models are processed according to a preset value-taking algorithm to obtain the trend monitoring results of the submarine cable disturbance sensing data. The preset value-taking algorithm includes at least one of taking the average value of the output results of the M models and taking the majority vote of the output results of the M models.

[0135] In one embodiment, such as Figure 9 The diagram illustrates the principle flowchart of a trend monitoring method for submarine cable disturbance sensing data. The method involves normalizing, resampling, and standardizing the raw data collected by the sensors. The preprocessed data is then processed using the slope method, Mann-Kendall test, and Cox-Stuart test, respectively. The resulting data is used as input to the Bagging algorithm, which outputs the trend of the submarine cable disturbance sensing data. This trend can include an upward trend, a downward trend, or no trend.

[0136] In one embodiment, such as Figure 10As shown, a trend monitoring system for submarine cable disturbance sensing data is provided. The system consists of a strategy module 1002, a database 1004, and a front-end 1006. The strategy module 1002 is used to read raw data from the database 1004, determine and output trend indicators based on the raw data. The database 1004 is used to store the raw data and also to receive and store the trend indicators output by the strategy module 1002. The front-end 1006 is used to read the trend indicators from the database 1004, obtain a trend intensity curve using the trend indicators, and obtain a data trend monitoring result based on the trend intensity curve. The strategy module 1002 is also used to: read the raw data from the database 1004, perform data preprocessing on the raw data to obtain time-series data; determine trend indicators based on the time-series data; and send the trend indicators to the database 1004. The front-end 1006 is also used to read the raw data from the database 1004, obtain a disturbance curve based on the raw data, and use the disturbance curve to monitor the trend of submarine cable disturbance sensing data. The front end 1006 is also used to read alarm data in the database 1004, obtain alarm messages based on the alarm data, and issue alarm messages when the trend of submarine cable disturbance sensing data is in an abnormal state.

[0137] It should be understood that, although Figures 2-8 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 2-8 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0138] Based on the same inventive concept, this disclosure also provides a submarine cable disturbance sensing data trend monitoring device for implementing the above-described submarine cable disturbance sensing data trend monitoring method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more submarine cable disturbance sensing data trend monitoring device embodiments provided below can be found in the limitations of the submarine cable disturbance sensing data trend monitoring method described above, and will not be repeated here.

[0139] In one embodiment, such as Figure 11As shown, a trend monitoring device 1100 for submarine cable disturbance sensing data is provided, comprising: a data acquisition module 1102, a target data module 1104, a probability set module 1106, a sub-probability set module 1108, and a monitoring result determination module 1110, wherein:

[0140] The data acquisition module 1102 is used to acquire disturbance sensing data of the submarine cable collected by multiple sensors.

[0141] The target data module 1104 is used to preprocess the disturbance sensing data according to a preset method to obtain target data.

[0142] The probability set module 1106 is used to judge the target data using N algorithms in a pre-set algorithm pool to obtain a probability set of length N.

[0143] The sub-probability set module 1108 is used to select M sub-probability sets of length n from a probability set of length N with replacement, wherein replacement means that any probability data in the probability set can be repeatedly used as probability data in the sub-probability set.

[0144] The monitoring result determination module 1110 is used to determine the trend monitoring result of the submarine cable disturbance sensing data based on M models, wherein the M models are obtained based on the M sub-probability sets.

[0145] The modules in the aforementioned trend monitoring device for submarine cable disturbance sensing data can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0146] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the 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 media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for trend monitoring of submarine cable disturbance sensing data. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0147] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0148] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0149] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0150] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0151] 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 used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this disclosure can include at least one of non-volatile and volatile memory. 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), magnetic 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 take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this disclosure may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this disclosure may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0153] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0154] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the appended claims.

Claims

1. A method of trend monitoring of subsea cable disturbance sensor data, characterized in that, The method comprises: acquiring disturbance sensing data of a submarine cable collected by a plurality of sensors; after data preprocessing of the disturbance sensing data in a preset manner, obtaining target data; using N algorithms in a preset algorithm pool to judge the target data, obtaining a probability set with a length of N; selecting M sub-probability sets with a length of n from the probability set with a length of N with replacement, wherein the replacement means that any probability data in the probability set can be repeated as probability data in the sub-probability set, 1≤n≤N; determining a trend monitoring result of the disturbance sensing data of the submarine cable according to M models, wherein the M models are obtained according to the M sub-probability sets, and the trend monitoring result comprises: calculating the M sub-probability sets by using a preset machine learning algorithm to obtain M models, wherein the preset machine learning algorithm at least includes one of a classification algorithm and a regression algorithm; and processing output results of the M models according to a preset value algorithm to obtain the trend monitoring result of the disturbance sensing data of the submarine cable, wherein the preset value algorithm at least includes one of taking an average value of the output results of the M models and taking a majority vote of the output results of the M models.

2. The method of claim 1, wherein, The use of N algorithms in a preset algorithm pool to judge the target data to obtain a probability set with a length of N comprises: fitting the target data into a straight line by using a least squares method; judging the target data according to the slope of the straight line to obtain probability data; obtaining a probability set with a length of N according to the probability data.

3. The method of claim 1, wherein, The use of N algorithms in a preset algorithm pool to judge the target data to obtain a probability set with a length of N comprises: comparing data in the target data with data at a next position adjacent to the position of the data to obtain a comparison result; judging the target data according to the positive and negative of the comparison result to obtain probability data; obtaining a probability set with a length of N according to the probability data.

4. The method of claim 1, wherein, The data preprocessing of the disturbance sensing data in a preset manner to obtain target data comprises: resampling the disturbance sensing data to obtain resampled data, wherein the resampling at least includes 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; performing dimensionless processing on the outlier filtered data to obtain target data, wherein the dimensionless processing at least includes one of linear dimensionless processing and nonlinear dimensionless processing.

5. The method of claim 4, wherein, The data outlier filtering of the resampled data to obtain outlier filtered data comprises: performing rule calculation on the resampled data to obtain rule calculation data, wherein the rule calculation at least includes one of averaging the resampled data and calculating the variance of the resampled data; taking an absolute value of a difference between the resampled data and the rule calculation data to obtain deviation data; Comparing target deviation data in the deviation data with a preset deviation threshold value; If the target deviation data is greater than the preset deviation threshold value, setting the resampling data corresponding to the target deviation data as an abnormal value and eliminating the abnormal value from the resampling data to obtain abnormal value filtered data.

6. A device for trend monitoring of subsea cable disturbance sensor data, characterized in that The device comprises: A data acquisition module configured to acquire disturbance sensing data of a submarine cable collected by a plurality of sensors; A target data module configured to obtain target data by performing data preprocessing on the disturbance sensing data in a preset manner; A probability set module configured to obtain a probability set with a length of N by using N algorithms in a preset algorithm pool to judge the target data; A sub-probability set module configured to select M sub-probability sets with a length of n from the probability set with the length of N with replacement, wherein the replacement means that any probability data in the probability set can be repeated as probability data in the sub-probability set, and 1≤n≤N; A monitoring result determination module configured to determine a trend monitoring result of the disturbance sensing data of the submarine cable according to M models, wherein the M models are obtained according to the M sub-probability sets, and the M models comprise: calculating the M sub-probability sets by using a preset machine learning algorithm to obtain M models, wherein the preset machine learning algorithm at least comprises one of a classification algorithm and a regression algorithm; and processing output results of the M models according to a preset value algorithm to obtain the trend monitoring result of the disturbance sensing data of the submarine cable, wherein the preset value algorithm at least comprises one of averaging the output results of the M models and taking a majority vote of the output results of the M models. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 5. The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 5.

Images