Submarine cable status monitoring method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for monitoring the state of a submarine cable. The method comprises: obtaining disturbance data of a submarine cable; processing the disturbance data according to preset characteristic indicators to obtain a disturbance characteristic sequence; inputting the disturbance characteristic sequence into a deep learning model to generate target disturbance sequence data; when the relationship between the target disturbance sequence data and a threshold value satisfies an alarm condition, determining that the state of the submarine cable is an abnormal state and generating an alarm message. The use of this method can avoid interference in the judgment of the state of the submarine cable caused by external factors such as wave scouring and sensor noise, improve the accuracy of the submarine cable state, and thus improve the accuracy of the alarm information.

Description

Technical Field

[0001] The present application relates to the technical field of engineering application of statistical learning, and in particular to a method, apparatus, computer equipment and storage medium for monitoring the status of a submarine cable. Background Art

[0002] The ocean is a treasure trove of resources that is easy for humans to explore. At present, the construction of various offshore and submarine engineering projects is progressing in an orderly manner. Submarine cables (i.e., submarine cables) are an important part of the construction of these sea projects. Once damaged, it is very easy to cause power and communication interruptions, which will have a huge impact on the construction of the project. Therefore, it is necessary to monitor the status of the submarine cable in a timely manner, and when the submarine cable is in an abnormal state, a real-time alarm is required. However, compared with land, the marine environment is more complex, and manual monitoring is more difficult and dangerous.

[0003] In traditional technology, the vibration information of the submarine cable can be collected by sensors, and the vibration information of the submarine cable can be compared and analyzed with the ship identification system and the submarine cable route corridor map to obtain the status of the submarine cable, thereby generating alarm information. However, this method directly judges the status of the submarine cable based on the vibration information collected by the sensor, which is easily interfered by external objective factors such as wave scouring and sensor noise, making the obtained submarine cable status prone to deviation, resulting in low accuracy of alarm information. Summary of the invention

[0004] Based on this, it is necessary to provide a submarine cable status monitoring method, device, computer equipment and storage medium that can improve the accuracy of submarine cable alarm information in response to the above technical problems.

[0005] In a first aspect, an embodiment of the present application provides a method for monitoring the status of a submarine cable, the method comprising:

[0006] Obtain disturbance data of submarine cables;

[0007] Processing the disturbance data according to preset characteristic indicators to obtain a disturbance characteristic sequence;

[0008] Inputting the disturbance feature sequence into a deep learning model to generate target disturbance sequence data;

[0009] When the relationship between the target disturbance sequence data and the threshold satisfies an alarm condition, the state of the submarine cable is determined to be an abnormal state, and an alarm message is generated.

[0010] In one embodiment, the target disturbance sequence data includes a plurality of target disturbance data sorted by occurrence time; the threshold includes a first threshold and a second threshold;

[0011] When the relationship between the target disturbance sequence data and the threshold satisfies an alarm condition, determining that the state of the submarine cable is an abnormal state includes:

[0012] Comparing the target disturbance sequence data with the first threshold, and when the target disturbance sequence data includes the target disturbance data greater than the first threshold, comparing the target disturbance sequence data with the second threshold to determine a first number of occurrences of the target disturbance data greater than the second threshold;

[0013] When the first number is greater than or equal to the first number threshold, it is determined that the alarm condition is met and the state of the submarine cable is determined to be an abnormal state.

[0014] In one of the embodiments, the disturbance data is data collected from multiple observation points of the submarine cable;

[0015] The process of processing the disturbance data according to the preset characteristic index to obtain a disturbance characteristic sequence, inputting the disturbance characteristic sequence into the deep learning model to generate target disturbance sequence data includes:

[0016] Processing the disturbance data of each observation point according to the characteristic index to obtain the disturbance characteristic sequence corresponding to each observation point;

[0017] The disturbance feature sequence corresponding to each of the observation points is input into the deep learning model to generate the target disturbance sequence data for each of the observation points.

[0018] In one of the embodiments, the threshold value further includes a third threshold value;

[0019] When the first number is greater than or equal to the first number threshold, determining that the alarm condition is satisfied and generating that the state of the submarine cable is an abnormal state includes:

[0020] When the first number is greater than or equal to the first number threshold, the target disturbance data of the observation point and the adjacent observation points of the observation point are compared with the third threshold. When it is determined that the target disturbance data of the observation point and the adjacent observation points are greater than the third threshold, it is determined that the alarm condition is met and the state of the submarine cable is determined to be an abnormal state.

[0021] In one of the embodiments, the threshold value further includes a fourth threshold value and / or a fifth threshold value;

[0022] When the first number is greater than or equal to the first number threshold, determining that the alarm condition is satisfied and determining that the state of the submarine cable is an abnormal state includes:

[0023] When the first number is greater than or equal to the first number threshold, when any one of the following situations occurs, it is determined that the state of the submarine cable is an abnormal state:

[0024] Compare the target disturbance data with the fourth threshold, determine a second number of times the target disturbance data greater than the fourth threshold appears, the second number of times being less than or equal to a second number threshold;

[0025] An average value of a plurality of the target disturbance data is obtained, the average value is compared with the fifth threshold value, and it is determined that the average value is greater than the fifth threshold value.

[0026] In one embodiment, obtaining disturbance data of the submarine cable includes:

[0027] Obtaining raw disturbance data collected by multiple different types of sensors;

[0028] Get dimensionless parameter factors;

[0029] The original disturbance data is dimensionally processed according to the dimensionless parameter factor to obtain the disturbance data.

[0030] In one embodiment, the characteristic indicators include multiple;

[0031] The step of processing the disturbance data according to a preset characteristic index to obtain a disturbance characteristic sequence includes:

[0032] Processing the disturbance data according to each of the characteristic indicators to generate a characteristic factor corresponding to each of the characteristic indicators;

[0033] Inputting each of the characteristic factors into a feature selection model to obtain a weight of each of the characteristic factors;

[0034] Screening a preset number of target characteristic factors from the plurality of characteristic factors according to the weight of each characteristic factor;

[0035] The disturbance feature sequence is generated according to the target feature factor.

[0036] In one embodiment, the plurality of characteristic indicators include at least two of a variance indicator, a standard deviation indicator, an average value indicator, a maximum value indicator, and a minimum value indicator.

[0037] In one embodiment, determining that the state of the submarine cable is an abnormal state and generating alarm information includes:

[0038] Get the current electronic chart;

[0039] When the ship's travel track in the current electronic nautical chart matches the state of the submarine cable, the alarm information is generated.

[0040] In one embodiment, the method further comprises:

[0041] Generating and displaying a disturbance curve according to the disturbance data;

[0042] When it is determined that the state of the submarine cable is an abnormal state, the disturbance curve is marked as abnormal and the alarm information is displayed.

[0043] In a second aspect, an embodiment of the present application further provides a submarine cable status monitoring device, the device comprising:

[0044] A data acquisition module, used to acquire disturbance data of the submarine cable;

[0045] A data processing module is used to process the disturbance data according to preset characteristic indicators to obtain a disturbance characteristic sequence, input the disturbance characteristic sequence into a deep learning model, and generate target disturbance sequence data;

[0046] The alarm generating module is used to determine that the state of the submarine cable is an abnormal state and generate alarm information when the relationship between the target disturbance sequence data and the threshold satisfies the alarm condition.

[0047] In a third aspect, an embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for monitoring the status of a submarine cable as described in any one of the embodiments of the first aspect above is implemented.

[0048] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for monitoring the status of a submarine cable as described in any one of the embodiments of the first aspect above is implemented.

[0049] The above-mentioned submarine cable status monitoring method, device, computer equipment and storage medium process the disturbance data through preset characteristic indicators to obtain a disturbance characteristic sequence, input the disturbance characteristic sequence into the deep learning model to generate target disturbance sequence data, and compare and analyze the relationship between the target disturbance sequence data and the threshold with the alarm condition to determine the status of the submarine cable. When the status of the submarine cable is abnormal, an alarm message is generated, which can avoid interference with the judgment of the status of the submarine cable caused by external factors such as wave scouring and sensor noise, improve the accuracy of the submarine cable status, and thus improve the accuracy of the alarm information. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the implementation methods of this specification or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0051] Figure 1 1. is an application environment diagram of a method for monitoring submarine cable status in one embodiment;

[0052] Figure 2 1 is a flow chart of a method for monitoring submarine cable status in one embodiment;

[0053] Figure 3 Schematic diagram of a flow chart of a step of comparing target disturbance sequence data with a threshold value in one embodiment;

[0054] Figure 4 A schematic diagram of a flow chart of a step of obtaining disturbance data in one embodiment;

[0055] Figure 5 A schematic flow chart of the steps of generating a disturbance feature sequence in one embodiment;

[0056] Figure 6 A schematic diagram of a process of monitoring a submarine cable status in another embodiment;

[0057] Figure 7 A structural block diagram of a method for monitoring submarine cable status in one embodiment;

[0058] Figure 8 A schematic diagram of a flow chart of steps for determining a state of a submarine cable in one embodiment;

[0059] Fig. 9 is a structural block diagram of a submarine cable status monitoring device in one embodiment;

[0060] Fig.10a is an internal structure diagram of a computer device in one embodiment;

[0061] Fig.10b FIG. 4 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] The submarine cable status monitoring method provided in the present application can be applied to computer equipment, wherein the computer equipment can be any one of a terminal, a server, and a computer equipment cluster consisting of a terminal and a server. Figure 1 An application environment diagram is shown. Among them, the terminal 102 communicates with the server 104 through a communication network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or deployed on the cloud or other network computer devices. The data storage system pre-stores the characteristic indicator data and the threshold of the alarm condition judgment logic. At least one trained deep learning model and alarm condition judgment logic are deployed in the server 104. The server 104 obtains the disturbance data of the submarine cable, stores the disturbance data of the submarine cable in the data storage system, and displays it on the terminal 102. The server 104 obtains the characteristic indicator data in the data storage system, processes the disturbance data according to the preset characteristic indicators, and obtains the disturbance feature sequence. The server 104 inputs the disturbance feature sequence into the trained deep learning model, generates the target disturbance sequence data, and stores the target disturbance sequence data in the data storage system. The server 104 obtains the threshold of the alarm condition judgment logic in the data storage system, and compares the target disturbance sequence data with the threshold according to the alarm condition judgment logic. When the server 104 monitors that the relationship between the target disturbance sequence data and the threshold meets the alarm condition, it determines that the state of the submarine cable is abnormal, generates alarm information, and displays it on the terminal 102.

[0064] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart TVs, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0065] In one embodiment, Figure 2 As shown, a method for monitoring the status of a submarine cable is provided. Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0066] Step S202, obtaining disturbance data of the submarine cable.

[0067] Among them, the disturbance data can be used to reflect the current disturbance state of the submarine cable. When the external disturbance affects the state of the submarine cable, the disturbance data of the submarine cable changes from zero to non-zero, and when the external disturbance is strengthened, the disturbance data value changes from large to small. The disturbance data can be obtained by preprocessing the original disturbance data collected by the sensor. The data preprocessing may include but is not limited to dimensionless processing of the original disturbance data. The dimensionless processing may include but is not limited to centering processing and scaling processing.

[0068] Specifically, the computer device responds to the submarine cable status monitoring request to obtain the disturbance data of the submarine cable. The submarine cable status monitoring request can be manually triggered by the user, for example, the user clicks the corresponding submarine cable status monitoring button on the page of the computer device; it can also be automatically triggered by the computer device, for example, after the computer device detects the existence of disturbance data of the submarine cable, it automatically triggers the submarine cable status monitoring request; or, the computer device automatically triggers the submarine cable status monitoring request at a preset time to obtain the disturbance data of the submarine cable; or, the computer device automatically triggers the submarine cable status monitoring request within each preset time period to obtain the disturbance data of the submarine cable.

[0069] Step S204: Process the disturbance data according to preset characteristic indicators to obtain a disturbance characteristic sequence.

[0070] Among them, the characteristic index can be used to describe the data distribution characteristics of the disturbance data in statistics. The characteristic index may include but is not limited to the average index, the variation index and the kurtosis index. The average index can be used to reflect the general level of the disturbance data as a whole or the central tendency of the distribution, such as the median, the mean, etc. The variation index can be used to reflect the variation or dispersion of the overall distribution of the disturbance data, such as the variance, the standard deviation, etc. The kurtosis index can be used to reflect the distribution state of the disturbance data as a whole, such as the maximum value, the minimum value, etc. The disturbance feature sequence can be the time series data of the disturbance feature data, and the disturbance feature data is the data obtained by processing the disturbance data according to the preset characteristic index.

[0071] Specifically, the computer device obtains a pre-stored characteristic index, processes disturbance data collected in multiple preset time periods according to the characteristic index, obtains disturbance characteristic data of each preset time period corresponding to the characteristic index, and sorts the disturbance characteristic data according to the order of the disturbance data collection time periods to obtain a disturbance characteristic sequence.

[0072] Step S206: input the disturbance feature sequence into the deep learning model to generate target disturbance sequence data.

[0073] The deep learning model may be any one of the models such as Deep Belief Network (DBN), Stacked AutoEncoder (SAE), Long Short-Term Memory (LSTM), etc. The target disturbance sequence data may be the time series data output by the deep learning model, which is used for comparison and analysis with the alarm condition to determine the current state of the submarine cable.

[0074] Specifically, the computer device inputs the disturbance feature sequence into a pre-deployed deep learning model to generate target disturbance sequence data. The deep learning model can be trained by a number of disturbance feature sequence samples.

[0075] In an example, the deep learning model is taken as a long short-term memory network LSTM model as an example:

[0076] First, the computer device obtains a number of disturbance feature sequence samples to generate a training set. The generation method of each disturbance feature sequence sample can refer to the generation method of the disturbance feature sequence in the above step S204, which will not be specifically described here. According to the disturbance feature sequence samples, the data type and data size of the input data and output data of the LSTM model are defined to construct the LSTM model framework. The disturbance feature sequence samples in the training set are input into the LSTM model framework, and multiple forward calculations and multiple reverse calculations are performed to finally obtain the weight of each row of disturbance feature sequence data, and the predicted disturbance sequence data is obtained according to the weight of the disturbance feature sequence data. According to the preset recall rate and precision rate standards, the predicted disturbance sequence data output by the model is evaluated, and the LSTM model parameters are adjusted until the predicted disturbance sequence data output by the model meets the preset standards to obtain a trained LSTM model. The training process of the above LSTM model can be performed once every preset time period.

[0077] Step S208: When the relationship between the target disturbance sequence data and the threshold satisfies the alarm condition, it is determined that the state of the submarine cable is an abnormal state, and an alarm message is generated.

[0078] The threshold value may be obtained by an alarm condition determination logic pre-deployed in a computer device. The alarm condition determination logic may include, but is not limited to: comparing the target disturbance sequence data with the threshold value of the alarm condition, and determining whether the alarm condition is satisfied according to the comparison result; or determining whether the alarm condition is satisfied according to the number of times the threshold value that satisfies the alarm condition appears in the target disturbance sequence data; or comparing the average value in the target disturbance sequence data within a preset period with the threshold value of the alarm condition, and determining whether the alarm condition is satisfied according to the comparison result.

[0079] Specifically, the computer device obtains a threshold value in the alarm condition determination logic, compares the target disturbance sequence data with the threshold value, and determines whether the target disturbance sequence data meets the alarm condition through the alarm condition determination logic. When the computer device determines that the target disturbance sequence data meets the alarm condition, it determines that the state of the submarine cable is an abnormal state, and generates an alarm message. When the computer device determines that the target disturbance sequence data does not meet the alarm condition, it determines that the state of the submarine cable is a normal state, and does not generate an alarm message.

[0080] In the above-mentioned submarine cable status monitoring method, the disturbance data is processed by the characteristic indicators preset by the computer equipment to obtain the disturbance characteristic sequence, and the disturbance characteristic sequence is input into the deep learning model to generate the target disturbance sequence data. The relationship between the target disturbance sequence data and the threshold is compared and analyzed with the alarm condition to determine the status of the submarine cable. When the status of the submarine cable is abnormal, an alarm message is generated, which can avoid the interference of external factors such as wave scouring and sensor noise on the judgment of the status of the submarine cable, improve the accuracy of the submarine cable status, and thus improve the accuracy of the alarm information.

[0081] In one embodiment, the threshold includes a first threshold and a second threshold. Figure 3 As shown, in step S208, when the relationship between the target disturbance sequence data and the threshold satisfies the alarm condition, it is determined that the state of the submarine cable is an abnormal state, and alarm information is generated, including:

[0082] Step S302: compare the target disturbance sequence data with a first threshold.

[0083] The target disturbance sequence data includes a plurality of target disturbance data sorted according to the occurrence time. The first threshold value can be used to characterize the critical value of the target disturbance data when the state of the submarine cable is an abnormal state. The first threshold value can be determined by a grid search method.

[0084] Specifically, the computer device obtains a pre-stored first threshold, compares each target disturbance data in the target disturbance sequence data with the first threshold in turn, and when there is target disturbance data greater than the first threshold, executes steps S304 to S308; when there is no target disturbance data greater than the first threshold, executes step S310.

[0085] In one example, the inventor found in actual application that the target disturbance sequence data of the submarine cable disturbance caused by sea waves is small and lasts for a long time; the target disturbance sequence data of the submarine cable disturbance caused by overhanging scouring is periodic; the target disturbance data of the submarine cable disturbance caused by anchor hanging has multiple peaks; the submarine cable disturbance caused by anchor hitting lasts for a short time, and the target disturbance sequence data of the submarine cable has only one peak, and this peak is much larger than the first threshold. Therefore, the first threshold, the second threshold and the first number threshold are set.

[0086] In one example, when there is no data greater than a first threshold in the target disturbance sequence data of the submarine cable, the disturbance state of the submarine cable may be caused by sea waves, and the current submarine cable disturbance event is identified as a sea wave event. At this time, the submarine cable is in a normal state and no alarm information is generated.

[0087] In one example, when there is no data greater than a first threshold in the target disturbance sequence data of the submarine cable, the disturbance state of the submarine cable may be caused by a span flushing event, and the current submarine cable disturbance event is identified as a span flushing event. At this time, the submarine cable is in a normal state and no alarm information is generated.

[0088] Step S304: compare the target disturbance sequence data with a second threshold value, and determine a first number of occurrences of the target disturbance data greater than the second threshold value.

[0089] Specifically, the computer device obtains a pre-stored second threshold, compares each target disturbance data in the target disturbance sequence data with the second threshold, and determines a first number of times that the target disturbance data greater than the second threshold appears in the target disturbance sequence data.

[0090] Step S306, comparing the first number with the first number threshold.

[0091] The first threshold value may be used to characterize the minimum number of times the second threshold value appears when the state of the submarine cable is in an abnormal state.

[0092] Specifically, the computer device obtains a pre-stored first number threshold, compares the first number with the first number threshold, and when the first number is greater than or equal to the first number threshold, executes step S308; when the first number is less than the first number threshold, executes step S310.

[0093] Step S308: determine that the alarm condition is met, determine that the state of the submarine cable is abnormal, and generate alarm information.

[0094] The alarm condition may include that, when target disturbance data greater than a first threshold value appears in the target disturbance sequence data, a first number of times that target disturbance data greater than a second threshold value appears in the target disturbance sequence data is greater than a first number threshold value.

[0095] Specifically, the computer device determines that the current target disturbance sequence data meets the alarm condition, determines that the current state of the submarine cable is an abnormal state, generates and displays alarm information.

[0096] In one example, the second threshold value may be equal to the peak value of the target disturbance data that appears multiple times in the target disturbance sequence data when the state of the submarine cable is abnormal. When the first number is greater than the first number threshold, the disturbance state of the submarine cable may be caused by anchor hanging, and the current submarine cable disturbance event is identified as an anchor hanging event. At this time, the submarine cable is in an abnormal state and an alarm needs to be issued in time.

[0097] In one example, the second threshold value may be equal to the target disturbance data value that appears multiple times in the target disturbance sequence data when the state of the submarine cable is in an abnormal state. When the first number is greater than the first number threshold value, and there is only one peak value in the target disturbance sequence data, the disturbance state of the submarine cable may be caused by anchor striking, and the current submarine cable disturbance event is identified as an anchor striking event. At this time, the submarine cable is in an abnormal state, and an alarm message is generated.

[0098] Step S310, determining that the alarm condition is not met and determining that the state of the submarine cable is normal.

[0099] Specifically, the computer device determines that the current target disturbance sequence data does not meet the alarm condition, determines that the current state of the submarine cable is a normal state, and does not generate an alarm message.

[0100] In one example, when the first number of target disturbance data greater than the second threshold appears in the target disturbance sequence data is less than the first number threshold, the disturbance state of the submarine cable may be caused by sensor noise. At this time, the submarine cable is in a normal state and no alarm information is generated.

[0101] In this embodiment, the inventor sets an alarm condition that may include but is not limited to threshold parameters such as a first threshold, a second threshold, and a first number threshold according to the characteristics of the target disturbance sequence data when the submarine cable is disturbed by events such as waves, anchor smashing, anchor hanging, and span scouring. In this embodiment, by comparing the target disturbance sequence data with the threshold and determining the state of the submarine cable according to the comparison result, an interpretation mechanism between the submarine cable target disturbance sequence data and the submarine cable state can be established, submarine cable disturbance events can be identified, the informatization of submarine cable facilities can be realized, and the accuracy of determining the state of the submarine cable can be improved.

[0102] In one embodiment, the disturbance data is data collected from multiple observation points of the submarine cable. The disturbance data is processed according to a preset characteristic index to obtain a disturbance characteristic sequence, and the disturbance characteristic sequence is input into a deep learning model to generate target disturbance sequence data, including: processing the disturbance data of each observation point according to the characteristic index to obtain a disturbance characteristic sequence corresponding to each observation point, and inputting the disturbance characteristic sequence corresponding to the observation point into the deep learning model to generate target disturbance sequence data for each observation point.

[0103] Specifically, the computer device obtains disturbance data collected from multiple observation points of the submarine cable, and performs the following operations on the disturbance data of each observation point: obtains characteristic indicators pre-stored in the computer device, processes the disturbance data of the observation point according to the preset characteristic indicators, obtains the disturbance feature sequence corresponding to the observation point, inputs the disturbance feature sequence corresponding to the observation point into the deep learning model, and generates the target disturbance sequence data of the observation point.

[0104] In this embodiment, by setting multiple observation points on the submarine cable, the disturbance data of the multiple observation points of the submarine cable are collected and processed, and the target disturbance sequence data corresponding to each observation point is generated, so that the obtained disturbance data can cover a wider range and expand the scope of monitoring the status of the submarine cable.

[0105] In one embodiment, the threshold value further includes a third threshold value. When the first number is greater than or equal to the first number threshold value, it is determined that the alarm condition is met, and the state of the submarine cable is generated as an abnormal state, including: when the first number is greater than or equal to the first number threshold value, comparing the target disturbance data of the observation point and the adjacent observation points of the observation point with the third threshold value, and determining that the target disturbance data of the observation point and the adjacent observation points is greater than the third threshold value, it is determined that the alarm condition is met, and the state of the submarine cable is determined to be an abnormal state.

[0106] Specifically, the computer device obtains a pre-stored third threshold value, and compares the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation points of the observation point with the third threshold value respectively; when the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation points of the observation point are both greater than the third threshold value, it is determined that the target disturbance sequence data of the observation point meets the alarm condition, the state of the submarine cable corresponding to the observation point is determined to be an abnormal state, and an alarm message is generated.

[0107] In one example, the inventors found in actual applications that the disturbance of the submarine cable caused by anchoring has a certain range of influence, and both the anchoring point and the surrounding points will be affected. When only a certain point has a series of abnormal values ​​in the target disturbance sequence data, it may be due to a problem with the sensor signal rather than the occurrence of anchor damage. Therefore, a third threshold value related to the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation points of the observation point is set.

[0108] In one example, when the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation points of the observation point are both greater than the third threshold, the disturbance state of the submarine cable may be caused by anchor hanging, and the current submarine cable disturbance event is identified as an anchor hanging event. At this time, the submarine cable is in an abnormal state and an alarm message is generated.

[0109] In this embodiment, the inventor sets a third threshold value related to the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation points of the observation point according to the characteristics of the submarine cable disturbance caused by the anchor. In this embodiment, the state of the submarine cable is determined by comparing the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation points around the observation point with the third threshold value, which can improve the accuracy of determining the state of the submarine cable under the anchor event.

[0110] In one embodiment, the threshold value further includes a fourth threshold value and / or a fifth threshold value. When the first number is greater than or equal to the first number threshold value, it is determined that the alarm condition is met and the state of the submarine cable is determined to be an abnormal state, including: when the first number is greater than or equal to the first number threshold value, when any of the following situations occurs, the state of the submarine cable is determined to be an abnormal state:

[0111] (1) Compare the target disturbance data with a fourth threshold, determine a second number of times the target disturbance data greater than the fourth threshold appears, and the second number is less than or equal to the second number threshold.

[0112] The fourth threshold value can be used to characterize the target disturbance data value that appears multiple times in the target disturbance sequence data of the submarine cable when the sensor causes disturbance of the submarine cable. The second number threshold value can be used to characterize the minimum number of times the fourth threshold value appears in the target disturbance sequence data of the submarine cable when the sensor noise causes disturbance of the submarine cable.

[0113] Specifically, the computer device obtains a pre-stored fourth threshold, compares the target disturbance sequence data within a preset time period with the fourth threshold, determines the second number of target disturbance data greater than the fourth threshold appearing in the target disturbance sequence data, and when the second number is less than or equal to the second number threshold, the computer device determines that the state of the submarine cable is an abnormal state and generates an alarm message.

[0114] In one example, the inventors found in actual applications that in the case of submarine cable disturbance caused by sensor noise, multiple target disturbance data with smaller thresholds will appear in the target disturbance sequence data of the submarine cable, and therefore a fourth threshold related to the sensor noise is set.

[0115] In one example, when the second number is less than the second number threshold, it can be explained that the disturbance state of the submarine cable is not caused by sensor noise. At this time, the submarine cable is in an abnormal state and an alarm message is generated.

[0116] (2) Obtain an average value of the plurality of target disturbance data, compare the average value with a fifth threshold, and determine whether the average value is greater than the fifth threshold.

[0117] Specifically, the computer device obtains a pre-stored fifth threshold and an average value of the target disturbance sequence data within a preset time period, and compares the average value of the target disturbance sequence data with the fifth threshold. When the average value is greater than the fifth threshold, the computer device determines that the state of the submarine cable is an abnormal state and generates an alarm message.

[0118] In one example, the inventors found in actual applications that when the anchor caused the submarine cable to be disturbed, the target disturbance sequence data of the submarine cable increased from small to large and lasted for a long time. When only one point has a series of abnormal values, it may be caused by a problem with the sensor signal rather than the occurrence of anchor damage, so a fifth threshold related to the duration of anchoring is set.

[0119] In one example, when the average value of the target disturbance sequence data within a preset time period is greater than the fifth threshold, the disturbance state of the submarine cable may be caused by anchor hanging, and the current submarine cable disturbance event is identified as an anchor hanging event. At this time, the submarine cable is in an abnormal state and an alarm message is generated.

[0120] In this embodiment, the inventor sets a fourth threshold value related to sensor noise according to the characteristics of submarine cable disturbance caused by sensor noise; and sets a fifth threshold value related to the duration of anchoring according to the characteristics of submarine cable disturbance caused by anchoring. In this embodiment, the accuracy of determining the submarine cable status can be improved by comparing the target disturbance sequence data within a preset time period with the threshold value.

[0121] In one embodiment, Figure 4 As shown, step S202, obtaining disturbance data of the submarine cable, includes:

[0122] Step S402: acquiring original disturbance data collected by multiple different types of sensors.

[0123] Step S404, obtaining dimensionless parameter factors.

[0124] Step S406, performing dimensionless processing on the original disturbance data according to the dimensionless parameter factor to obtain disturbance data.

[0125] The types of sensors may include, but are not limited to, temperature sensors, disturbance sensors, and current sensors. The original disturbance data may be used to characterize the data directly collected by the sensor. The dimensionless parameter factor refers to a constant without a physical unit, which is used to perform dimensionless processing on the data.

[0126] In one example, the inventors found in actual applications that each sensor has certain functions and measurement ranges, and the data from a single sensor reflects the state of the submarine cable from a certain dimension, which has certain limitations. Therefore, more types of sensors can be deployed inside the submarine cable to collect disturbance data in multiple dimensions, reduce the inaccuracy of information, and increase the credibility of information.

[0127] Specifically, the computer device obtains raw disturbance data collected by multiple different types of sensors and dimensionless parameter factors.

[0128] In one example, a dimensionless parameter factor may be subtracted from each original disturbance data, thereby translating the data to a preset position to obtain disturbance data.

[0129] In another example, each original disturbance data may be divided by a dimensionless parameter factor, or the logarithm of each original disturbance data may be taken through the dimensionless parameter factor, so as to fix the data within a preset range and obtain disturbance data.

[0130] In this embodiment, by acquiring data through multiple sensors, the limitations of using a single sensor and the problem of inaccurate collected data caused by a single sensor being susceptible to sensor noise interference can be avoided. Dimensionless processing of the original disturbance data can avoid the influence of a feature with a particularly large value range on the distance calculation of the deep learning model, which helps to improve the model accuracy and thus improve the accuracy of alarm information.

[0131] In one embodiment, the preset characteristic indicators include multiple, such as Figure 5 As shown, step S204, processing the disturbance data according to the preset characteristic index to obtain a disturbance characteristic sequence, including:

[0132] Step S502: Process the disturbance data according to each characteristic index to generate a characteristic factor corresponding to each characteristic index.

[0133] Among them, the characteristic factor can be used to characterize the data distribution characteristics of the disturbance data, and the multiple characteristic indicators can include but are not limited to at least two of the mean value indicator, variance indicator, standard deviation indicator, maximum value indicator, and minimum value indicator.

[0134] Specifically, the computer device obtains a plurality of characteristic indicators, processes disturbance data collected in a plurality of preset time periods according to each characteristic indicator, and generates a characteristic factor corresponding to each characteristic indicator.

[0135] In one example, a computer device processes disturbance data according to a variance index, a standard deviation index, and an average value index to generate a variance factor, a standard deviation factor, and an average value factor of the disturbance data.

[0136] In one example, a computer device processes disturbance data according to a variance index, a standard deviation index, an average index, a maximum index, and a minimum index to generate a variance factor, a standard deviation factor, an average factor, a maximum factor, and a minimum factor of the disturbance data.

[0137] Step S504: input each feature factor into a feature selection model to obtain a weight of each feature factor.

[0138] Step S506: Screening a preset number of target characteristic factors from the plurality of characteristic factors according to the weight of each characteristic factor.

[0139] The feature selection model is a model that has the ability to screen feature factors. The feature selection model can be any one of a support vector machine model (SVM), a regression model, a logistic regression model, and the like.

[0140] In an example, the feature selection model is taken as a logistic regression model to illustrate the training process of the feature selection model:

[0141] First, the computer device obtains several feature factors, inputs the set of several feature factors as the initial feature training set into the feature selection model to be trained, obtains the weight of each feature factor through the objective function in the feature selection model, deletes the feature factor with the smallest weight from the initial feature training set, and obtains a new feature set. The model adjusts the parameters of the objective function through multiple forward searches and backward searches to obtain a new feature selection model. The new feature set is input as a training set into the new feature selection model for training, and the above operation is repeated until the obtained feature set includes a preset number of feature factors, and a trained feature selection model is obtained.

[0142] Specifically, the computer device obtains a trained feature selection model, inputs each feature factor into the feature selection model, obtains the weight of each feature factor, and screens a preset number of target feature factors from multiple feature factors according to the weight of each feature factor.

[0143] Step S508: generating a disturbance feature sequence according to the target feature factor.

[0144] Specifically, the computer device sorts the multiple target characteristic factors according to the order of the collection time periods corresponding to the target characteristic factors to generate a disturbance characteristic sequence.

[0145] In this embodiment, the feature factors generated by the disturbance data are selected through the feature selection model to generate a disturbance feature sequence, which can reduce the amount of data processed by the deep learning model, reduce processing costs, and improve processing efficiency.

[0146] In one embodiment, determining that the state of the submarine cable is abnormal and generating alarm information includes: obtaining a current electronic nautical chart, and generating alarm information when the ship's trajectory in the current electronic nautical chart matches the state of the submarine cable.

[0147] The electronic chart may be a digital chart of a marine vessel traffic management system, which may be used to monitor the position and trajectory of marine vessels.

[0148] Specifically, when the computer device determines that the state of the submarine cable is abnormal, the computer device obtains the current electronic nautical chart, and obtains the positional relationship between the ship's driving track in the current electronic nautical chart and the observation point area of ​​the abnormal state. When the ship's driving track in the current electronic nautical chart and the observation point area of ​​the abnormal state have an overlapping area, it is determined that the ship's driving track matches the state of the submarine cable corresponding to the observation point, and an alarm message is generated; when the ship's driving track in the current electronic nautical chart and the observation point area of ​​the abnormal state do not have an overlapping area, it is determined that the ship's driving track does not match the state of the submarine cable corresponding to the observation point, and the state of the submarine cable corresponding to the observation point is determined to be normal.

[0149] In one example, the state of the submarine cable at the observation point is affected by sensor noise, and the computer device determines that the state of the submarine cable corresponding to the observation point is abnormal. The computer device compares the observation point area in the abnormal state with the ship's track in the current electronic nautical chart, determines that no ship passes through the observation point area, identifies it as a sensor noise event, and determines that the state of the submarine cable is normal.

[0150] In this embodiment, the inventor found in actual application that the presence of a ship's trajectory near the submarine cable is a necessary but insufficient condition for submarine cable early warning. Sometimes the sensor signal may have problems. Although the probability is low, there may be no ship, resulting in a false alarm. A secondary confirmation process for the abnormal state of the submarine cable is set. This embodiment obtains the positional relationship between the ship's trajectory and the observation point area in the current electronic nautical chart, compares the positional relationship with the determined submarine cable state, and confirms the state of the submarine cable, which can improve the accuracy of the determined submarine cable state and reduce the probability of false alarms.

[0151] In one embodiment, the computer device can generate and display a disturbance curve based on the disturbance data. When it is determined that the state of the submarine cable is abnormal, the disturbance curve is marked as abnormal and an alarm message is displayed.

[0152] In one embodiment, Figure 6As shown, a method for monitoring the status of a submarine cable is provided, comprising:

[0153] Step S602: acquiring original disturbance data collected by multiple different types of sensors.

[0154] Specifically, the computer device obtains original disturbance data of multiple observation points collected by the temperature sensor, the disturbance sensor and the current sensor, and performs all the following steps on the original disturbance data collected at each observation point.

[0155] Step S604: Obtain dimensionless parameter factors, perform dimensionless processing on the original disturbance data according to the dimensionless parameter factors, and obtain disturbance data.

[0156] Specifically, the computer device obtains a dimensionless parameter factor, subtracts the dimensionless parameter factor from the original disturbance data, and obtains the disturbance data.

[0157] Step S606: Process the disturbance data according to a plurality of preset characteristic indicators to generate a characteristic factor corresponding to each characteristic indicator.

[0158] Specifically, the computer device processes the disturbance data according to a plurality of characteristic indicators to generate characteristic factors of the disturbance data, wherein the characteristic factors include a variance factor, a standard deviation factor, an average factor, a maximum factor, and a minimum factor.

[0159] Step S608: input each feature factor into a feature selection model to obtain a preset number of target feature factors and generate a disturbance feature sequence.

[0160] Specifically, the computer device inputs each feature factor into the logistic regression model to obtain a preset number of target feature factors, and then generates a perturbation feature sequence. The specific training method of the logistic regression model and the generation method of the perturbation feature sequence are implemented with reference to the method provided in the above embodiment, and will not be elaborated here.

[0161] In one example, the inventors found that in actual applications, the amount of feature factor data generated is large. In order to improve data processing efficiency, it is necessary to select some feature factors that have a greater impact on the model output results from all feature factors. Common feature selection methods mainly include filtering, embedding, and packaging methods.

[0162] The filtering method is generally used as a data preprocessing step. It does not require the use of any machine learning algorithm and only selects features based on scores in various statistical tests and various indicators of correlation. The filtering method uses variance for preliminary filtering, and then obtains correlation based on chi-square, F test and mutual information methods for re-filtering to achieve feature selection.

[0163] The embedding method is trained through machine learning algorithms and models to obtain the weight coefficients of each feature factor, and select features from large to small according to the weight coefficients. These weight coefficients often represent a certain contribution or importance of the feature factor to the model. Compared with the filtering method, the results of the embedding method will be more accurate to the utility of the model itself, and have a better effect on improving the effectiveness of the model. In addition, since the contribution of features to the model is considered, irrelevant features (features that require correlation filtering) and features without discrimination (features that require variance filtering) will be deleted due to their lack of contribution to the model.

[0164] The packaging method is also a method in which feature selection and algorithm training are performed simultaneously, but it is different from the embedding method in that an objective function is used as a black box to select features, rather than the user inputting a threshold of an evaluation index or statistic. The packaging method trains the evaluator (i.e., the logistic regression model) on the initial feature set (i.e., the set of all feature factors), and then prunes the least important features from the current set of features (i.e., deletes the feature factors with the lowest weights from the feature set). The process is repeated recursively on the pruned set until the required number of features to be selected is finally reached (i.e., a preset number of target feature factors are obtained). Unlike the filtering method and the embedding method, which solve all problems with one training, the packaging method uses feature subsets for multiple trainings, so the computational cost it requires is also the highest among several methods, but the feature factors it obtains have the highest model confidence for the subsequent generation of target perturbation sequence data. Therefore, the inventor finally chose to use the packaging method for feature selection.

[0165] Step S610: Input the disturbance feature sequence into the deep learning model to generate target disturbance sequence data. The target disturbance sequence data includes a plurality of target disturbance data sorted by occurrence time.

[0166] Specifically, the computer device inputs the disturbance feature sequence into the LSTM model to generate target disturbance sequence data. The specific training method of the LSTM model is implemented by referring to the method provided in the above embodiment, and will not be elaborated here.

[0167] Step S612: when there is target disturbance data greater than the first threshold, compare the target disturbance sequence data with the second threshold to determine a first number of occurrences of the target disturbance data greater than the second threshold.

[0168] Specifically, the computer device compares the target disturbance sequence data with a first threshold value, and when there is target disturbance data greater than the first threshold value in the target disturbance sequence data, compares the target disturbance sequence data with a second threshold value, and determines a first number of occurrences of target disturbance data greater than the second threshold value.

[0169] Step S614, when the first number is greater than or equal to the first threshold, determine whether the alarm condition is met according to the relationship between the target disturbance sequence data and the third threshold, the fourth threshold and the fifth threshold.

[0170] Specifically, when the first number is greater than or equal to the first threshold, the computer device compares the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation point of the observation point with the third threshold; determines the second number of target disturbance data greater than the fourth threshold appears in the target disturbance sequence data of the observation point, and compares the second number with the second number threshold; obtains the average value of the target disturbance sequence data within a preset time period, and compares the average value with the fifth. When the target disturbance sequence data of the observation point and the target disturbance sequence data of the adjacent observation point of the observation point are respectively greater than the third threshold, and the second number is less than or equal to the second number threshold, and the average value is greater than the fifth threshold, it is determined that the alarm condition is met.

[0171] Step S616: determine that the state of the submarine cable is abnormal and generate an alarm message.

[0172] Specifically, after the computer device determines that the alarm condition is met, it determines that the state of the submarine cable is abnormal. The computer device obtains the current electronic nautical chart, compares the ship's trajectory in the current electronic nautical chart with the observation point area, and determines the current state of the submarine cable. When the computer device determines that the state of the submarine cable is abnormal, an alarm message is generated.

[0173] In this embodiment, original disturbance data is obtained, dimensionless processing is performed on the original disturbance data to obtain disturbance data, disturbance data is processed according to preset characteristic indicators to obtain characteristic factors of disturbance data, characteristic factors are input into a logistic regression model for screening to generate disturbance characteristic sequences, disturbance characteristic sequences are input into an LSTM model to generate target disturbance sequence data, the relationship between the target disturbance sequence data and a threshold is determined and compared with the alarm condition to obtain the state of the submarine cable, the state of the submarine cable is then compared with an electronic nautical chart to determine the state of the submarine cable, and alarm information is generated when the state of the submarine cable is abnormal, which can avoid interference with the judgment of the state of the submarine cable caused by external factors such as wave scouring and sensor noise, make full use of multi-sensor data resources in multiple times and spaces, improve the accuracy of the submarine cable state, and thus improve the accuracy of the alarm information.

[0174] In one embodiment, a structural block diagram of a method for monitoring the status of a submarine cable is also provided. Figure 7As shown, the computer device acquires disturbance data and stores it in a database, processes the disturbance data through a background processing module, stores characteristic indicators in the processing process and characteristic factors corresponding to the characteristic indicators as characteristic data in the database, stores target disturbance sequence data as target data in the database, stores the threshold of the alarm condition as state data in the database, and stores the generated alarm information as alarm data in the database. The front end reads the disturbance data in the database to generate a disturbance curve and displays it, and reads the alarm data to generate alarm information and displays it.

[0175] In this embodiment, data is stored in a database, processed by a background processing module, and displayed on a front end, thereby improving data processing efficiency and providing a visualization function.

[0176] In one embodiment, a data processing flow diagram for monitoring the status of a submarine cable is also provided. Figure 8 As shown, multiple characteristic factors are used as data of the input layer, and the computer device generates a disturbance characteristic sequence according to the characteristic factors at the input layer, and generates target disturbance sequence data according to the disturbance characteristic sequence. Multiple thresholds of the alarm condition are used as data of the hidden layer, and the computer device compares the target disturbance sequence data with multiple thresholds of the alarm condition at the hidden layer, and globally fuses multiple comparison results (that is, when each comparison result meets the alarm condition, the state of the submarine cable is determined to be abnormal, and when at least one of the multiple comparison results does not meet the alarm condition, the state of the submarine cable is determined to be normal), and the state data of the submarine cable is obtained. The state data of the submarine cable is used as data of the output layer, and when the computer device determines that the relationship between the target disturbance sequence data and the multiple thresholds of the alarm condition meets the alarm condition, the state of the output submarine cable is 0 abnormal; when the computer device determines that the relationship between the target disturbance sequence data and the multiple thresholds of the alarm condition does not meet the alarm condition, the state of the output submarine cable is 1 normal.

[0177] In this embodiment, the inventors set an operation of globally fusing multiple comparison results based on the fact that in actual use, the judgment dimensions of each threshold in the alarm condition are different, resulting in different confidence levels of comparison results of multiple thresholds in the alarm condition. This embodiment can improve the accuracy of the determined submarine cable status by globally fusing the relationship between the target disturbance sequence data and multiple thresholds of the alarm condition.

[0178] It should be understood that, although the various steps in the above flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowchart may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0179] Based on the description of the above-mentioned submarine cable status monitoring method embodiment, the present disclosure also provides a submarine cable status monitoring device. The device may include a system (including a distributed system), software (application), module, component, computer equipment, client, etc. using the method described in the embodiment of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided by the embodiment of the present disclosure is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device of the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware of predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0180] In one embodiment, Fig. 9 As shown, a submarine cable status monitoring device 900 is provided, including: a data acquisition module 902, a data processing module 904 and an alarm generation module 906, wherein:

[0181] The data acquisition module 902 is used to acquire disturbance data of the submarine cable.

[0182] The data processing module 904 is used to process the disturbance data according to the preset characteristic index to obtain the disturbance characteristic sequence, input the disturbance characteristic sequence into the deep learning model, and generate the target disturbance sequence data.

[0183] The alarm generating module 906 is used to determine that the state of the submarine cable is an abnormal state and generate alarm information when the relationship between the target disturbance sequence data and the threshold satisfies the alarm condition.

[0184] In one embodiment, the target disturbance sequence data includes a plurality of target disturbance data sorted by occurrence time, and the threshold includes a first threshold and a second threshold. The alarm generation module 906 includes: a first number determination unit, used to compare the target disturbance sequence data with the first threshold, and when there is target disturbance data greater than the first threshold in the target disturbance sequence data, compare the target disturbance sequence data with the second threshold to determine the first number of times the target disturbance data greater than the second threshold appears. A first number alarm unit, used to determine that the alarm condition is met when the first number is greater than or equal to the first number threshold, and determine that the state of the submarine cable is an abnormal state.

[0185] In one embodiment, the disturbance data is data collected from multiple observation points of the submarine cable. The data processing module 904 includes: a disturbance feature sequence generation unit, which is used to process the disturbance data of each observation point according to the feature index to obtain a disturbance feature sequence corresponding to each observation point. A target disturbance sequence data generation unit is used to input the disturbance feature sequence corresponding to each observation point into the deep learning model to generate target disturbance sequence data for each observation point.

[0186] In one embodiment, the threshold also includes a third threshold, and the alarm generation module 906 is also used to: when the first number is greater than or equal to the first number threshold, compare the target disturbance data of the observation point and the adjacent observation points of the observation point with the third threshold, and when it is determined that the target disturbance data of the observation point and the adjacent observation points is greater than the third threshold, determine that the alarm condition is met and determine that the state of the submarine cable is an abnormal state.

[0187] In one embodiment, the threshold value further includes a fourth threshold value and / or a fifth threshold value. When the first number is greater than or equal to the first number threshold value, when any of the following situations occurs, the alarm generation module 906 further includes: a fourth threshold comparison unit, used to compare the target disturbance data with the fourth threshold value, determine the second number of target disturbance data greater than the fourth threshold value, and the second number is less than or equal to the second number threshold value. A fifth threshold comparison unit, used to obtain an average value of multiple target disturbance data, compare the average value with the fifth threshold value, and determine that the average value is greater than the fifth threshold value.

[0188] In one embodiment, the data acquisition module 902 includes: an original disturbance data acquisition unit, which is used to acquire original disturbance data collected by multiple different types of sensors; a data dimensionless unit, which is used to acquire dimensionless parameter factors; and dimensionless processing is performed on the original disturbance data according to the dimensionless parameter factors to obtain disturbance data.

[0189] In one embodiment, the characteristic index includes multiple ones, and the data processing module 904 includes: a characteristic factor generating unit, which is used to process the disturbance data according to each characteristic index and generate a characteristic factor corresponding to each characteristic index. A characteristic factor screening unit, which is used to input each characteristic factor into the feature selection model to obtain the weight of each characteristic factor; and to screen a preset number of target characteristic factors from multiple characteristic factors according to the weight of each characteristic factor. A disturbance characteristic sequence generating unit, which is used to generate a disturbance characteristic sequence according to the target characteristic factor.

[0190] In one embodiment, the plurality of characteristic indicators include at least two of a variance indicator, a standard deviation indicator, an average value indicator, a maximum value indicator, and a minimum value indicator.

[0191] In one embodiment, the alarm generation module 906 is further used to: obtain the current electronic nautical chart, and generate an alarm message when the ship's trajectory in the current electronic nautical chart matches the state of the submarine cable.

[0192] In one embodiment, the submarine cable status monitoring device 900 further includes: a front-end display module, which is used to generate and display a disturbance curve according to the disturbance data; when it is determined that the state of the submarine cable is abnormal, the disturbance curve is marked as abnormal and an alarm message is displayed.

[0193] For the specific definition of the submarine cable status monitoring device, please refer to the definition of the submarine cable status monitoring method above, which will not be repeated here. Each module in the above-mentioned submarine cable status monitoring device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0194] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10a As shown. The computer device includes a processor, a memory, and a network interface 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store disturbance data, characteristic data, target data, status data, and alarm data. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for monitoring the status of a submarine cable is implemented.

[0195] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10b As shown. 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 a computer program. The internal memory provides an environment for the operation of the operating system and the computer program 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 achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for monitoring the status of a submarine cable is implemented. 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 covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0196] Those skilled in the art will understand that Fig.10a and Fig.10b The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0197] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0198] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0199] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application 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 or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0200] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0201] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring submarine cable status, characterized in that: The method comprises: Obtain disturbance data of submarine cables; Processing the disturbance data according to preset characteristic indicators to obtain a disturbance characteristic sequence; Inputting the disturbance feature sequence into a deep learning model to generate target disturbance sequence data; When the relationship between the target disturbance sequence data and the threshold satisfies an alarm condition, determining that the state of the submarine cable is an abnormal state, and generating an alarm message; Wherein, the target disturbance sequence data includes a plurality of target disturbance data sorted by occurrence time; the threshold includes a first threshold and a second threshold; the threshold also includes a fourth threshold and / or a fifth threshold; When the relationship between the target disturbance sequence data and the threshold value satisfies the alarm condition, determining that the state of the submarine cable is an abnormal state includes: Comparing the target disturbance sequence data with the first threshold, and when the target disturbance sequence data includes the target disturbance data greater than the first threshold, comparing the target disturbance sequence data with the second threshold to determine a first number of occurrences of the target disturbance data greater than the second threshold; When the first number is greater than or equal to the first number threshold, determining that the alarm condition is satisfied and determining that the state of the submarine cable is an abnormal state includes: When the first number is greater than or equal to the first number threshold, when any one of the following situations occurs, it is determined that the state of the submarine cable is an abnormal state: Compare the target disturbance data with the fourth threshold, determine a second number of times the target disturbance data greater than the fourth threshold appears, the second number of times being less than or equal to a second number threshold; An average value of a plurality of the target disturbance data is obtained, the average value is compared with the fifth threshold value, and it is determined that the average value is greater than the fifth threshold value.

2. The method according to claim 1, characterized in that The disturbance data is data collected from multiple observation points of the submarine cable; The process of processing the disturbance data according to the preset characteristic index to obtain a disturbance characteristic sequence, inputting the disturbance characteristic sequence into the deep learning model to generate target disturbance sequence data includes: Processing the disturbance data of each observation point according to the characteristic index to obtain the disturbance characteristic sequence corresponding to each observation point; The disturbance feature sequence corresponding to each of the observation points is input into the deep learning model to generate the target disturbance sequence data for each of the observation points.

3. The method according to claim 2, characterized in that The threshold value also includes a third threshold value; When the first number is greater than or equal to the first number threshold, determining that the alarm condition is satisfied and generating that the state of the submarine cable is an abnormal state includes: When the first number is greater than or equal to the first number threshold, the target disturbance data of the observation point and the adjacent observation points of the observation point are compared with the third threshold. When it is determined that the target disturbance data of the observation point and the adjacent observation points are greater than the third threshold, it is determined that the alarm condition is met and the state of the submarine cable is determined to be an abnormal state.

4. The method according to claim 1, characterized in that The characteristic indicators include multiple; The step of processing the disturbance data according to a preset characteristic index to obtain a disturbance characteristic sequence includes: Processing the disturbance data according to each of the characteristic indicators to generate a characteristic factor corresponding to each of the characteristic indicators; Inputting each of the characteristic factors into a feature selection model to obtain a weight of each of the characteristic factors; Screening a preset number of target characteristic factors from the plurality of characteristic factors according to the weight of each characteristic factor; The disturbance feature sequence is generated according to the target feature factor.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Generating and displaying a disturbance curve according to the disturbance data; When it is determined that the state of the submarine cable is an abnormal state, the disturbance curve is marked as abnormal and the alarm information is displayed.

6. A submarine cable status monitoring device, characterized in that: The device comprises: A data acquisition module, used to acquire disturbance data of the submarine cable; A data processing module is used to process the disturbance data according to preset characteristic indicators to obtain a disturbance characteristic sequence, input the disturbance characteristic sequence into a deep learning model, and generate target disturbance sequence data; An alarm generating module, configured to determine that the state of the submarine cable is an abnormal state and generate alarm information when the relationship between the target disturbance sequence data and the threshold satisfies an alarm condition; Wherein, the target disturbance sequence data includes a plurality of target disturbance data sorted by occurrence time; the threshold includes a first threshold and a second threshold; the threshold also includes a fourth threshold and / or a fifth threshold The alarm generation module includes: a first number determination unit, used to compare the target disturbance sequence data with the first threshold value, and when the target disturbance sequence data has the target disturbance data greater than the first threshold value, compare the target disturbance sequence data with the second threshold value to determine the first number of times the target disturbance data greater than the second threshold value appears; a first number alarm unit, used to determine that the alarm condition is satisfied and the state of the submarine cable is an abnormal state when the first number is greater than or equal to the first number threshold value; In the case where the first number is greater than or equal to the first number threshold, when any one of the following situations occurs, the alarm generation module further includes: a fourth threshold comparison unit, used to compare the target disturbance data with the fourth threshold, and determine a second number of the target disturbance data greater than the fourth threshold, and the second number is less than or equal to the second number threshold; a fifth threshold comparison unit, used to obtain an average value of a plurality of the target disturbance data, compare the average value with the fifth threshold, and determine that the average value is greater than the fifth threshold.

7. The device according to claim 6, characterized in that The disturbance data is data collected from multiple observation points of the submarine cable; The data processing module includes: a disturbance feature sequence generation unit, which is used to process the disturbance data of each of the observation points according to the feature index to obtain the disturbance feature sequence corresponding to each of the observation points; and a target disturbance sequence data generation unit, which is used to input the disturbance feature sequence corresponding to each of the observation points into the deep learning model to generate the target disturbance sequence data of each of the observation points.

8. The device according to claim 7, characterized in that The threshold also includes a third threshold, and the alarm generation module is also used to: when the first number is greater than or equal to the first number threshold, compare the target disturbance data of the observation point and the adjacent observation points of the observation point with the third threshold, and when it is determined that the target disturbance data of the observation point and the adjacent observation points are greater than the third threshold, determine that the alarm condition is met and determine that the state of the submarine cable is an abnormal state.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, 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 5 are implemented.

Images