Method and system for positioning multiple leakage points of oil-filled cable

Abstract

The invention discloses an oil-filled cable multi-leakage-point positioning method and system, and relates to the technical field of oil-filled cable leakage point localization, monitoring parameters and cable parameters of a to-be-detected oil-filled cable are acquired, state information of the to-be-detected oil-filled cable is determined according to the monitoring parameters, and when the state information is cable leakage, the to-be-detected oil-filled cable is detected. If yes, leakage point positioning is conducted on the oil-filled cable to be detected, a single leakage point position is obtained, a multi-leakage-point digital twinborn model is constructed by combining cable parameters, multi-leakage-point leakage working condition monitoring is conducted on the multi-leakage-point digital twinborn model through the monitoring parameters, and when the monitoring result is that the oil-filled cable leaks for the second time, the single leakage point position is obtained; if yes, the multi-leakage-point digital twinborn model, the monitoring parameters and a preset feedforward network model are adopted for leakage point positioning, a second leakage point position is obtained, the second leakage point position is adopted for updating the multi-leakage-point digital twinborn model, and the step of monitoring the multi-leakage-point leakage working condition of the multi-leakage-point digital twinborn model through the monitoring parameters is skipped to be executed. The technical problem that multiple leakage points cannot be positioned in the prior art is solved.

Description

Technical Field

[0001] The invention relates to the technical field of oil-filled cable leakage point positioning, and in particular to a method and system for positioning multiple leakage points of an oil-filled cable. Background Art

[0002] In the field of long-distance submarine high-voltage oil-filled cables, locating leaks is an important technical challenge. Due to the complexity of the submarine environment, manual surveys are difficult to implement. The cost of using underwater robots to troubleshoot faults is extremely high, which limits their application in large-scale submarine cable detection. At the same time, although advanced sensor technology can monitor the cable status in real time and improve the accuracy and real-time performance of leakage detection, the special structure of oil-filled submarine cables limits their application, making it difficult to identify the location of oil-filled cable leaks through sensor technology.

[0003] At present, the current technology mainly relates the flow rate and pressure loss of the cable through Poiseuille's law, and assumes that the pressure on the left and right sides of the leak is equal to obtain the distance between the leak and the oil supply end of the oil-filled cable through simultaneous equations, thereby determining the location of the leak. However, if there are multiple leaks in the oil-filled cable, it is impossible to accurately locate the leak. Summary of the invention

[0004] The present invention provides a method and system for locating multiple leakage points of an oil-filled cable, which solves the technical problem that the existing technology mainly relates the flow rate and pressure loss of the cable through Poiseuille's law, and assumes that the pressures on the left and right sides of the leakage point are equal to obtain the distance between the leakage point and the oil supply end of the oil-filled cable through simultaneous equations, thereby determining the position of the leakage point; however, if there are multiple leakage points in the oil-filled cable, the leakage points cannot be accurately located.

[0005] A first aspect of the present invention provides a method for locating multiple leakage points of an oil-filled cable, comprising:

[0006] Acquire monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determine status information of the oil-filled cable to be detected according to the monitoring parameters;

[0007] When the state information is cable leakage, a single leakage point location method is used to locate the leakage point of the oil-filled cable to be detected, and a corresponding single leakage point is obtained;

[0008] Building a multi-leakage point digital twin model based on the single leakage point and the cable parameters, and using the monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results;

[0009] When the monitoring result is a secondary leakage of the oil-filled cable, the multi-leakage point digital twin model, the monitoring parameters and the preset feedforward network model are used to locate the leakage point to obtain the second leakage point;

[0010] The multi-leakage point digital twin model is updated using the second leakage point, and based on the updated multi-leakage point digital twin model, the step of performing multi-leakage point leakage condition monitoring on the multi-leakage point digital twin model using the monitoring parameters is jumped to obtain corresponding monitoring results.

[0011] Optionally, the step of determining the status information of the oil-filled cable to be detected according to the monitoring parameters includes:

[0012] Determining whether the end pressure value of the monitoring parameter is within a preset pressure holding range;

[0013] If the end pressure value is within the pressure-maintaining interval, it is determined that the state information of the oil-filled cable to be tested is that the cable is operating normally;

[0014] If the end pressure value is not within the pressure maintaining interval, it is determined that the state information of the oil-filled cable to be detected is a cable leakage.

[0015] Optionally, the step of using the monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results includes:

[0016] The multi-leakage point digital twin model is used to predict the leakage condition of the oil-filled cable to be tested, so as to obtain the predicted insulating oil flow rate;

[0017] Performing difference processing on the predicted insulating oil flow and the insulating oil flow of the monitoring parameter, a first difference;

[0018] Determining whether the first difference is greater than or equal to a preset flow difference threshold;

[0019] If the first difference is less than the flow difference threshold, obtaining the leakage condition parameters of the multi-leakage point digital twin model at the current moment as the monitoring result;

[0020] If the first difference is greater than or equal to the flow difference threshold, a monitoring result of secondary leakage of the oil-filled cable is generated.

[0021] Optionally, the step of using the multi-leakage point digital twin model, the monitoring parameters and a preset feedforward network model to locate the leakage point to obtain the second leakage point position includes:

[0022] The multi-leakage point digital twin model is used to perform a multi-leakage point simulation test to obtain a cable working condition data set;

[0023] Using the cable working condition data to train a preset feedforward network model to obtain a target feedforward network model;

[0024] The monitoring parameters are input into the target feedforward network model to locate the leakage point, thereby obtaining a second leakage point.

[0025] Optionally, the step of constructing a multi-leakage point digital twin model based on the single leakage point and the cable parameters includes:

[0026] Inputting the cable parameters into a preset one-dimensional Poiseuille model to obtain a target cable model;

[0027] Inputting the single leakage point into a preset initial double-layer pipeline flow model to obtain a double-layer pipeline flow model;

[0028] The target cable model, the double-layer pipeline flow model and the preset reduced-order model are coupled to obtain a multi-leakage point digital twin model.

[0029] Optionally, the step of using the cable operating condition data to train a preset feedforward network model to obtain a target feedforward network model includes:

[0030] Performing data preprocessing on the cable operating condition data to generate a cable feature set;

[0031] The cable feature set is used to input a preset feedforward network model for training, and training leakage point data is output;

[0032] Calculate the training loss function value of the cable feature set according to the training leakage point data;

[0033] When the training loss function value is greater than or equal to a preset standard loss function value, adjusting the network parameters of the feedforward network model until the training loss function value is less than the preset standard loss function value;

[0034] When the training loss function value is less than the preset standard loss function value, a target feedforward network model is generated.

[0035] A second aspect of the present invention provides an oil-filled cable multiple leakage point positioning system, comprising:

[0036] A monitoring module, used for acquiring monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determining the status information of the oil-filled cable to be detected according to the monitoring parameters;

[0037] A positioning module, used for locating the leakage point of the oil-filled cable to be detected by using a single leakage point positioning method when the status information is cable leakage, so as to obtain a corresponding single leakage point position;

[0038] A first analysis module is used to construct a multi-leakage point digital twin model based on the single leakage point and the cable parameters, and use the monitoring parameters to perform multi-leakage point leakage condition monitoring on the multi-leakage point digital twin model to obtain corresponding monitoring results;

[0039] A second analysis module is used to locate the leakage point by using the multi-leakage point digital twin model, the monitoring parameters and the preset feedforward network model to obtain the second leakage point when the monitoring result is a secondary leakage of the oil-filled cable;

[0040] An updating module is used to update the multi-leakage point digital twin model using the second leakage point, and based on the updated multi-leakage point digital twin model, jump to execute the step of monitoring the multi-leakage point leakage condition of the multi-leakage point digital twin model using the monitoring parameters to obtain corresponding monitoring results.

[0041] A third aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for locating multiple leaks in an oil-filled cable as described in any one of the above items.

[0042] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, the method for locating multiple leakage points of an oil-filled cable as described in any one of the above items is implemented.

[0043] A fifth aspect of the present invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the method for locating multiple leaks in an oil-filled cable as described in any one of the above items.

[0044] It can be seen from the above technical solutions that the present invention has the following advantages:

[0045] The present invention obtains the monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and quickly determines whether there is a leak in the oil-filled cable to be detected through the monitoring parameters. When it is determined that the oil-filled cable to be detected is leaking, the leak point of the oil-filled cable to be detected is located, the corresponding single leak point is obtained, and a multi-leakage point digital twin model is constructed in combination with the cable parameters, so that the multi-leakage point digital twin model and the monitoring parameters can be used to continuously locate the multiple leak points of the oil-filled cable to be detected. Compared with the traditional single leak point location method, the present invention realizes the identification and location of multiple leak points of the submarine oil-filled cable, and improves the operating safety and maintenance efficiency of the submarine cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 A flowchart of a method for locating multiple leaks in an oil-filled cable provided in Embodiment 1 of the present invention;

[0048] Figure 2 A flowchart of a method for locating multiple leaks in an oil-filled cable provided in Embodiment 2 of the present invention;

[0049] Figure 3 A schematic diagram of the structure of a double-layer pipe flow model provided in the second embodiment of the present invention;

[0050] Figure 4 A schematic diagram of the structure of a reduced-order model provided in Embodiment 2 of the present invention;

[0051] Figure 5 A schematic diagram of the structure of a feedforward deep neural network provided in Embodiment 2 of the present invention;

[0052] Figure 6 A structural block diagram of a system for locating multiple leakage points of an oil-filled cable provided in Embodiment 3 of the present invention;

[0053] Figure 7 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0054] The embodiment of the present invention provides a method and system for locating multiple leaks in an oil-filled cable, which is used to solve the technical problem that the current technology mainly relates the flow rate and pressure loss of the cable through Poiseuille's law, and assumes that the pressures on the left and right sides of the leak are equal to obtain the distance between the leak and the oil supply end of the oil-filled cable through simultaneous equations, thereby determining the position of the leak. However, if there are multiple leaks in the oil-filled cable, the leak cannot be accurately located.

[0055] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] See also Figure 1 , Figure 1 A flowchart of the steps of a method for locating multiple leak points in an oil-filled cable provided in Example 1 of the present invention.

[0057] The present invention provides a method for locating multiple leakage points of an oil-filled cable, comprising:

[0058] Step 101, acquiring monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determining state information of the oil-filled cable to be detected according to the monitoring parameters;

[0059] The oil-filled cable to be tested refers to the submarine oil-filled cable to be monitored.

[0060] The status information refers to the operating status of the oil-filled cable to be tested, and the operating status includes normal operation of the cable and cable leakage.

[0061] In an embodiment of the present invention, the flow and pressure at both ends of the normally operating oil-filled cable to be tested are monitored in real time to obtain monitoring parameters and cable parameters of the oil-filled cable to be tested, and whether the oil-filled cable to be tested is leaking is determined based on the monitoring parameters.

[0062] Step 102: When the status information is cable leakage, a single leakage point location method is used to locate the leakage point of the oil-filled cable to be tested, and a corresponding single leakage point is obtained;

[0063] In the embodiment of the present invention, when the oil-filled cable to be detected leaks, the existing single leak point positioning method is used to locate the leak point of the oil-filled cable to be detected, and the corresponding single leak point position is obtained.

[0064] It should be noted that the single leak location method can be an oil flow method, which is specifically as follows: 1. First, it is necessary to ensure that both ends of the cable are closed to prevent oil from flowing out from the other end of the cable. Then, inject pressure oil at one end of the cable to make the pressure inside the cable reach a certain level. 2. Monitor the oil pressure: Install oil pressure monitoring equipment at the other end of the cable or other appropriate locations to monitor the oil pressure changes inside the cable in real time. 3. Determine the leak point: When a leak occurs inside the cable, oil will leak from the leak point into the seawater, causing the pressure inside the cable to drop. By monitoring the changes in oil pressure, the time point and speed of the oil pressure drop can be determined. 4. Calculate the leak point location: According to the time of oil pressure drop and the flow speed of oil in the cable, the distance from the leak point to the oil pressure monitoring point can be calculated. Usually, this method requires the oil flow speed of the cable and the layout diagram of the cable to be known in advance. 5. Locate the leak point: Through the above calculations, the location of the leak point can be roughly determined. Then, use equipment such as a submersible or remotely operated vehicle (ROV) to inspect the submarine cable to accurately find the leak point.

[0065] Step 103: construct a multi-leakage point digital twin model based on the single leakage point and cable parameters, and use monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results;

[0066] In an embodiment of the present invention, a multi-leakage point digital twin model is constructed based on a single leakage point and cable parameters, and the multi-leakage point digital twin model is used to monitor the leakage condition of the oil-filled cable to be detected, and the corresponding predicted insulating oil flow rate is obtained. The predicted insulating oil flow rate is compared with the insulating oil flow rate of the monitoring parameter. When the difference between the predicted insulating oil flow rate and the insulating oil flow rate of the monitoring parameter increases slowly, the monitoring result of the secondary leakage of the oil-filled cable is generated. When the difference between the predicted insulating oil flow rate and the insulating oil flow rate of the monitoring parameter does not change, the leakage condition parameters of the multi-leakage point digital twin model at the current moment are obtained as the monitoring result.

[0067] Step 104: When the monitoring result is a secondary leakage of the oil-filled cable, the multi-leakage point digital twin model, monitoring parameters and a preset feedforward network model are used to locate the leakage point to obtain the second leakage point;

[0068] In an embodiment of the present invention, when the monitoring result is a secondary leakage of the oil-filled cable, a multi-leakage point digital twin model is used to simulate the cable conditions at different second leakage points to obtain a cable condition data set. The cable condition data set is used to train a preset feedforward network model to obtain a target feedforward network model. The monitoring parameters are input into the target feedforward network model to obtain the second leakage point.

[0069] Step 105: Use the second leakage point to update the multi-leakage point digital twin model, and based on the updated multi-leakage point digital twin model, jump to execute the step of using monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results.

[0070] In an embodiment of the present invention, the multi-leakage point digital twin model is adjusted according to the second leakage point, and based on the adjusted multi-leakage point digital twin model, the step of jumping to execute the multi-leakage point leakage condition monitoring of the multi-leakage point digital twin model using monitoring parameters is performed to obtain corresponding monitoring results.

[0071] In another embodiment, the flow and pressure at both ends of the oil-filled cable to be tested that is in normal operation are monitored in real time, the monitoring parameters and cable parameters of the oil-filled cable to be tested are obtained, and it is determined whether the oil-filled cable to be tested is leaking based on the monitoring parameters. When it is determined that the oil-filled cable is leaking, the single leakage point positioning method is used to locate the leakage point of the oil-filled cable to be tested, and the corresponding single leakage point is obtained. A multi-leakage point digital twin model is constructed based on the single leakage point and cable parameters (the multi-leakage point digital twin model initially established is a leakage flow digital twin model, which is used to continuously monitor a single leakage point), and the multi-leakage point digital twin model is used to monitor the leakage condition of the oil-filled cable to be tested to determine whether a secondary leakage occurs. When a secondary leakage of the oil-filled cable occurs, a simulation test is carried out through a multi-leakage point digital twin model based on the determined leakage points and assumed unknown leakage points to obtain a cable operating condition data set (i.e., leakage flow data under a large number of multiple leakage points). The cable operating condition data set is used to train the preset multi-leakage point neural network to obtain a target feedforward neural network. The monitoring parameters acquired in real time are input into the target feedforward neural network to obtain newly added leakage points. The newly added leakage points are used to update the multi-leakage point digital twin model, and the updated multi-leakage point digital twin model is used to continuously monitor each leakage point.

[0072] In the embodiment of the present invention, the present invention obtains the monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and quickly determines whether the oil-filled cable to be detected has a leak through the monitoring parameters. When it is determined that the oil-filled cable to be detected has a leak, the leak point of the oil-filled cable to be detected is located, the corresponding single leak point is obtained, and a multi-leakage point digital twin model is constructed in combination with the cable parameters, so that the multi-leakage point digital twin model and the monitoring parameters can be used to continuously locate the multiple leak points of the oil-filled cable to be detected. Compared with the traditional single leak point location method, the present invention realizes the identification and location of multiple leak points of the submarine oil-filled cable, and improves the operating safety and maintenance efficiency of the submarine cable.

[0073] See also Figure 2 , Figure 2 A flowchart of the steps of a method for locating multiple leakage points in an oil-filled cable provided in Embodiment 2 of the present invention.

[0074] The present invention provides a method for locating multiple leakage points of an oil-filled cable, comprising:

[0075] Step 201, acquiring monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determining state information of the oil-filled cable to be detected according to the monitoring parameters;

[0076] Furthermore, step 201 includes the following sub-steps:

[0077] S11, acquiring monitoring parameters and cable parameters of the oil-filled cable to be tested in real time, and determining whether the end pressure value of the monitoring parameter is within a preset pressure-maintaining range;

[0078] In an embodiment of the present invention, the flow and pressure at both ends of the normally operating oil-filled cable to be tested are monitored in real time to obtain the monitoring parameters and cable parameters of the oil-filled cable to be tested, and to determine whether the end pressure value of the monitoring parameter is within a preset pressure maintenance range.

[0079] S12, if the end pressure value is in the pressure maintaining range, it is determined that the state information of the oil-filled cable to be tested is that the cable is operating normally;

[0080] In an embodiment of the present invention, when the end pressure value is in the pressure maintaining range, it means that the oil pumps at both ends of the submarine oil-filled cable can maintain pressure continuously under the pressure-injection state, and the status information of the oil-filled cable to be tested is determined to be that the cable is operating normally.

[0081] S13. If the end pressure value is not in the pressure maintaining range, it is determined that the state information of the oil-filled cable to be tested is a cable leakage.

[0082] In the embodiment of the present invention, when the end pressure value is not in the pressure maintaining range, it means that the submarine oil-filled cable cannot maintain pressure and leaks, and the state information of the oil-filled cable to be detected is determined to be cable leakage.

[0083] Step 202: When the status information is cable leakage, a single leakage point location method is used to locate the leakage point of the oil-filled cable to be tested, and a corresponding single leakage point is obtained;

[0084] In an embodiment of the present invention, when the status information is a cable leakage, any one of the acoustic positioning method, oil flow method, chemical tracer method, temperature gradient method, and electromagnetic positioning method is used to locate the leakage point of the oil-filled cable to be tested, and the leakage point is verified by an underwater robot (ROV) or a diver to obtain a corresponding single leakage point.

[0085] It should be noted that the acoustic positioning method specifically uses sonar or underwater microphones to detect and locate the sound generated by oil leaks. When the cable leaks oil, the oil in contact with seawater may generate specific sound waves, which can propagate in the water and be detected. By analyzing the propagation time and intensity of the sound waves, the location of the leak can be determined. The chemical tracer method specifically adds specific chemical tracers to the oil in the cable. When a leak occurs, the tracer will leak into the seawater along with the oil. By sampling and analyzing the concentration distribution of the tracer in the seawater, the location of the leak can be inferred. The temperature gradient method specifically refers to the temperature difference between the oil and seawater when the cable leaks oil, which may cause local temperature changes. By monitoring the temperature distribution on the seabed, the temperature abnormality area caused by the oil leak can be identified, thereby locating the leak. The electromagnetic positioning method specifically uses the electromagnetic properties of the cable to locate the leak. When the cable leaks oil, its electromagnetic field may change. By monitoring these changes, the location of the leak can be inferred.

[0086] Step 203, inputting the cable parameters into a preset one-dimensional Poiseuille model to obtain a target cable model;

[0087] In the embodiment of the present invention, based on the cable parameters, the one-dimensional Poiseuille law is used to describe the relationship between the flow rate and the pressure drop in the oil channel of the oil-filled cable far away from the leak point, so as to obtain the target cable model.

[0088] It should be noted that the target cable model is specifically:

[0089] ;

[0090] in, is the pressure drop, is the insulating oil flow rate, is the diameter of the oil-filled cable, is the length of the oil-filled cable, is the dynamic viscosity.

[0091] It should be noted that submarine oil-filled cables usually extend for tens of kilometers, and it is very difficult to perform direct computational fluid modeling on such long cables. Model reduction methods need to be applied to maintain the controllability of the calculation. Since the flow away from the leak is laminar and uniform, the one-dimensional Poiseuille law can be used to theoretically describe the relationship between flow and pressure drop.

[0092] Step 204: input the single leakage point into the preset initial double-layer pipeline flow model to obtain the double-layer pipeline flow model;

[0093] In the embodiment of the present invention, the preset initial double-layer pipeline flow model is adjusted according to the single leakage point to obtain the double-layer pipeline flow model.

[0094] It should be noted that, see Figure 3As shown, for the flow near the leakage point, the multi-physics field calculation software COMSOL is used to construct an initial double-layer pipe flow model and a circular leakage outlet with a diameter of 5 mm is set at the bottom of the outer layer. The porous medium single-phase flow module is used for calculation. The inner layer is set as the free flow area and the outer layer is set as the porous medium area. The leakage flow resistance can be equivalent to the permeability of the porous medium.

[0095] Step 205: Couple the target cable model, the double-layer pipeline flow model and the preset reduced-order model to obtain a multi-leakage point digital twin model.

[0096] In an embodiment of the present invention, based on a preset reduced-order model, the target cable model and the double-layer pipeline flow model are coupled to obtain a multi-leakage point digital twin model.

[0097] In another embodiment, see Figure 4 As shown, the target cable model and the double-layer pipe flow model are integrated through the pressure continuity boundary condition to simulate the flow of insulating oil from the cable terminal to the vicinity of the leakage point, and a reduced-order model is constructed. The permeability in the reduced-order model is used to approximate the insulating oil flow obtained by on-site monitoring, and the permeability coefficient in the model is updated to complete the establishment of the digital twin model of multiple leakage points.

[0098] It should be noted that the reduced-order model is specifically:

[0099] ;

[0100] ;

[0101] in, is the pressure at the first end of the cable, is the pressure at the second end of the cable, is the first boundary condition of the CFD calculation domain, is the second boundary condition of the CFD calculation domain, is the first hydrostatic pressure of the insulating oil inside the oil-filled cable, is the second hydrostatic pressure of the insulating oil inside the oil-filled cable, is the first voltage drop from the cable end to the leak point, is the second voltage drop from the end of the cable to the leak point.

[0102] Step 206: Use monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results;

[0103] Further, step 206 includes the following sub-steps:

[0104] S21. Use a multi-leakage point digital twin model to predict the leakage condition of the oil-filled cable to be tested, and obtain the predicted insulating oil flow rate;

[0105] In an embodiment of the present invention, a multi-leakage point digital twin model is used to predict the leakage condition of the oil-filled cable to be tested, and a corresponding predicted insulating oil flow rate is obtained.

[0106] S22, performing difference processing between the predicted insulating oil flow and the insulating oil flow of the monitoring parameter, a first difference;

[0107] In the embodiment of the present invention, the insulating oil flow rate difference between the predicted insulating oil flow rate and the insulating oil flow rate of the monitoring parameter is calculated.

[0108] S23, determining whether the first difference is greater than or equal to a preset flow difference threshold;

[0109] In the embodiment of the present invention, it is determined whether the insulating oil flow difference is greater than or equal to a preset flow difference threshold.

[0110] S24. If the first difference is less than the flow difference threshold, the leakage condition parameters of the multi-leakage point digital twin model at the current moment are obtained as the monitoring result;

[0111] In an embodiment of the present invention, when the insulating oil flow difference is less than the flow difference threshold, the leakage damping parameters of the leakage points and the predicted insulating oil flow of the multi-leakage point digital twin model at the current moment are obtained as monitoring results.

[0112] It should be noted that the leakage condition parameters include but are not limited to leakage damping parameters of the leakage point and predicted insulating oil flow rate.

[0113] S25. If the first difference is greater than or equal to the flow difference threshold, a monitoring result of secondary leakage of the oil-filled cable is generated.

[0114] In the embodiment of the present invention, when the insulating oil flow difference is greater than or equal to the flow difference threshold, a monitoring result of secondary leakage of the oil-filled cable is generated.

[0115] Step 207: When the monitoring result is a secondary leakage of the oil-filled cable, the multi-leakage point digital twin model, monitoring parameters and a preset feedforward network model are used to locate the leakage point to obtain the second leakage point;

[0116] Further, step 207 includes the following sub-steps:

[0117] S31. When the monitoring result is secondary leakage of the oil-filled cable, a multi-leakage point digital twin model is used to perform a multi-leakage point simulation test to obtain a cable working condition data set;

[0118] In an embodiment of the present invention, when the monitoring result is a secondary leakage of the oil-filled cable, a multi-leakage point digital twin model is used to simulate the operating conditions of the oil-filled cable at different second leakage points to obtain a cable condition data set.

[0119] S32, using the cable working condition data to train the preset feedforward network model to obtain a target feedforward network model;

[0120] Further, S32 includes the following sub-steps:

[0121] S321, preprocessing the cable working condition data to generate a cable feature set;

[0122] In an embodiment of the present invention, data preprocessing is performed on the cable operating condition data to obtain a cable feature set.

[0123] S322, using the cable feature set to input a preset feedforward network model for training, and outputting training leakage point data;

[0124] It should be noted that, see Figure 5 As shown, the feedforward deep neural network uses 3 hidden layers, 128 units in each layer, the learning rate is set to 0.01, the activation function is ReLu, and the optimizer is Adam.

[0125] In an embodiment of the present invention, the cable feature set is input into a preset feedforward network model for training, and the training leakage point data is output.

[0126] S323, calculating the training loss function value of the cable feature set according to the training leakage point data;

[0127] In an embodiment of the present invention, target leakage point data corresponding to the training leakage point data are selected from the cable feature set, and a deviation value between the training leakage point data and the target leakage point data is calculated as a training loss function value.

[0128] S324, when the training loss function value is greater than or equal to the preset standard loss function value, adjusting the network parameters of the feedforward network model until the training loss function value is less than the preset standard loss function value;

[0129] S325. When the training loss function value is less than the preset standard loss function value, a target feedforward network model is generated.

[0130] In an embodiment of the present invention, when the training loss function value is greater than or equal to the preset standard loss function value, a grid search method, a gradient descent method or a random search method is used to adjust the network parameters of the feedforward network model until the training loss function value is less than the preset standard loss function value. When the training loss function value is less than the preset standard loss function value, a target feedforward network model is generated.

[0131] S336, input the monitoring parameters into the target feedforward network model to locate the leakage point, and obtain the second leakage point.

[0132] In an embodiment of the present invention, the monitoring parameters are input into the target feedforward network model to locate the leakage point, obtain the second leakage point, and verify the leakage point by combining with an underwater robot (ROV) or a diver.

[0133] Step 208: Use the second leakage point to update the multi-leakage point digital twin model, and based on the updated multi-leakage point digital twin model, jump to execute the step of using monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results.

[0134] In an embodiment of the present invention, the multi-leakage point digital twin model is updated through the second leakage point, and based on the updated multi-leakage point digital twin model, the multi-leakage point digital twin model is jumped to execute the step of using monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results.

[0135] In the embodiment of the present invention, the present invention obtains the monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and quickly determines whether the oil-filled cable to be detected has a leak through the monitoring parameters. When it is determined that the oil-filled cable to be detected has a leak, the leak point of the oil-filled cable to be detected is located, the corresponding single leak point is obtained, and a multi-leakage point digital twin model is constructed in combination with the cable parameters, so that the multi-leakage point digital twin model and the monitoring parameters can be used to continuously locate the multiple leak points of the oil-filled cable to be detected. Compared with the traditional single leak point location method, the present invention realizes the identification and location of multiple leak points of the submarine oil-filled cable, and improves the operating safety and maintenance efficiency of the submarine cable.

[0136] See also Figure 6 , Figure 6 This is a structural block diagram of a system for locating multiple leak points in an oil-filled cable provided in Embodiment 3 of the present invention.

[0137] The present invention provides an oil-filled cable multiple leakage point positioning system, comprising:

[0138] The monitoring module 301 is used to obtain monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determine the status information of the oil-filled cable to be detected according to the monitoring parameters;

[0139] The positioning module 302 is used to locate the leakage point of the oil-filled cable to be tested by using a single leakage point positioning method when the status information is cable leakage, and obtain the corresponding single leakage point position;

[0140] The first analysis module 303 is used to construct a multi-leakage point digital twin model based on a single leakage point and cable parameters, and use monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results;

[0141] The second analysis module 304 is used to locate the leakage point by using the multi-leakage point digital twin model, monitoring parameters and a preset feedforward network model to obtain the second leakage point when the monitoring result is a secondary leakage of the oil-filled cable;

[0142] The updating module 305 is used to update the multi-leakage point digital twin model using the second leakage point, and based on the updated multi-leakage point digital twin model, jump to execute the step of using monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results.

[0143] Furthermore, the monitoring module 301 includes:

[0144] The monitoring submodule is used to determine whether the end pressure value of the monitoring parameter is within a preset pressure holding range;

[0145] The first analysis submodule is used to determine that the state information of the oil-filled cable to be tested is that the cable is operating normally if the end pressure value is in the pressure maintenance interval;

[0146] The second analysis submodule is used to determine that the state information of the oil-filled cable to be detected is a cable leakage if the end pressure value is not in the pressure maintenance interval.

[0147] Furthermore, the first analysis module 303 includes:

[0148] The prediction submodule is used to predict the leakage condition of the oil-filled cable to be tested using a multi-leakage point digital twin model to obtain the predicted insulating oil flow rate;

[0149] A third analysis submodule is used to perform difference processing between the predicted insulating oil flow and the insulating oil flow of the monitoring parameter, a first difference;

[0150] A fourth analysis submodule, used to determine whether the first difference is greater than or equal to a preset flow difference threshold;

[0151] If the first difference is less than the flow difference threshold, the leakage condition parameters of the multi-leakage point digital twin model at the current moment are obtained as the monitoring result;

[0152] If the first difference is greater than or equal to the flow difference threshold, a monitoring result of secondary leakage of the oil-filled cable is generated.

[0153] Furthermore, the second analysis module 304 includes:

[0154] The simulation submodule is used to conduct multi-leakage point simulation tests using a multi-leakage point digital twin model to obtain a cable operating condition data set;

[0155] A training submodule is used to train a preset feedforward network model using cable operating data to obtain a target feedforward network model;

[0156] The positioning submodule is used to input the monitoring parameters into the target feedforward network model to locate the leakage point and obtain the second leakage point.

[0157] Furthermore, the first analysis module 303 further includes:

[0158] The first construction submodule is used to input the cable parameters into a preset one-dimensional Poiseuille model to obtain a target cable model;

[0159] The second construction submodule is used to input a single leakage point into a preset initial double-layer pipeline flow model to obtain a double-layer pipeline flow model;

[0160] The coupling submodule is used to couple the target cable model, the double-layer pipeline flow model and the preset reduced-order model to obtain a multi-leakage point digital twin model.

[0161] Furthermore, the training submodule includes:

[0162] A preprocessing unit, used for preprocessing the cable working condition data and generating a cable feature set;

[0163] A training unit, used for training a preset feedforward network model using a cable feature set as input, and outputting training leakage point data;

[0164] Calculate the training loss function value of the cable feature set based on the training leakage point data;

[0165] When the training loss function value is greater than or equal to the preset standard loss function value, adjusting the network parameters of the feedforward network model until the training loss function value is less than the preset standard loss function value;

[0166] When the training loss function value is less than the preset standard loss function value, the target feedforward network model is generated.

[0167] See also Figure 7 , Figure 7 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention.

[0168] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 402 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes the method for locating multiple leak points in an oil-filled cable as described in any of the above embodiments.

[0169] The memory 401 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 401 has a storage space 403 for a program code 413 for executing any method step in the above method. For example, the storage space 403 for the program code may include individual program codes 413 for implementing the various steps in the above method, respectively. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program code may be compressed, for example, in an appropriate form. When these codes are run by a computing and processing device, the computing and processing device performs the various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program code may be compressed, for example, in an appropriate form. When these codes are executed by a computing and processing device, the computing and processing device is caused to execute the various steps of the method for locating multiple leakage points in an oil-filled cable described above.

[0170] Embodiment 5 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for locating multiple leakage points in an oil-filled cable as described in any of the above embodiments is implemented.

[0171] Embodiment 6 of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method for locating multiple leak points in an oil-filled cable as described in any of the above embodiments.

[0172] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0174] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0176] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0177] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for locating multiple leakage points of an oil-filled cable, characterized in that: include: Acquire monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determine status information of the oil-filled cable to be detected according to the monitoring parameters; When the state information is cable leakage, a single leakage point location method is used to locate the leakage point of the oil-filled cable to be detected, and a corresponding single leakage point is obtained; Building a multi-leakage point digital twin model based on the single leakage point and the cable parameters, and using the monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results; When the monitoring result is a secondary leakage of the oil-filled cable, the multi-leakage point digital twin model, the monitoring parameters and the preset feedforward network model are used to locate the leakage point to obtain the second leakage point; The multi-leakage point digital twin model is updated using the second leakage point, and based on the updated multi-leakage point digital twin model, the step of performing multi-leakage point leakage condition monitoring on the multi-leakage point digital twin model using the monitoring parameters is jumped to obtain corresponding monitoring results.

2. The method for locating multiple leakage points of oil-filled cables according to claim 1 is characterized in that: The step of determining the status information of the oil-filled cable to be detected according to the monitoring parameters comprises: Determining whether the end pressure value of the monitoring parameter is within a preset pressure holding range; If the end pressure value is within the pressure-maintaining interval, it is determined that the state information of the oil-filled cable to be tested is that the cable is operating normally; If the end pressure value is not within the pressure maintaining interval, it is determined that the state information of the oil-filled cable to be detected is a cable leakage.

3. The method for locating multiple leakage points of oil-filled cables according to claim 1 is characterized in that: The step of using the monitoring parameters to monitor the multi-leakage point leakage conditions of the multi-leakage point digital twin model to obtain corresponding monitoring results includes: The multi-leakage point digital twin model is used to predict the leakage condition of the oil-filled cable to be tested, so as to obtain the predicted insulating oil flow rate; Performing difference processing on the predicted insulating oil flow and the insulating oil flow of the monitoring parameter, a first difference; Determining whether the first difference is greater than or equal to a preset flow difference threshold; If the first difference is less than the flow difference threshold, obtaining the leakage condition parameters of the multi-leakage point digital twin model at the current moment as the monitoring result; If the first difference is greater than or equal to the flow difference threshold, a monitoring result of secondary leakage of the oil-filled cable is generated.

4. The method for locating multiple leakage points of oil-filled cables according to claim 1 is characterized in that: The step of using the multi-leakage point digital twin model, the monitoring parameters and the preset feedforward network model to locate the leakage point to obtain the second leakage point position includes: The multi-leakage point digital twin model is used to perform a multi-leakage point simulation test to obtain a cable working condition data set; Using the cable working condition data to train a preset feedforward network model to obtain a target feedforward network model; The monitoring parameters are input into the target feedforward network model to locate the leakage point, thereby obtaining a second leakage point.

5. The method for locating multiple leakage points of oil-filled cables according to claim 1 is characterized in that: The step of constructing a multi-leakage point digital twin model based on the single leakage point and the cable parameters includes: Inputting the cable parameters into a preset one-dimensional Poiseuille model to obtain a target cable model; Inputting the single leakage point into a preset initial double-layer pipeline flow model to obtain a double-layer pipeline flow model; The target cable model, the double-layer pipeline flow model and the preset reduced-order model are coupled to obtain a multi-leakage point digital twin model.

6. The method for locating multiple leakage points of oil-filled cables according to claim 4 is characterized in that: The step of using the cable working condition data to train a preset feedforward network model to obtain a target feedforward network model includes: Performing data preprocessing on the cable operating condition data to generate a cable feature set; The cable feature set is used to input a preset feedforward network model for training, and training leakage point data is output; Calculate the training loss function value of the cable feature set according to the training leakage point data; When the training loss function value is greater than or equal to a preset standard loss function value, adjusting the network parameters of the feedforward network model until the training loss function value is less than the preset standard loss function value; When the training loss function value is less than the preset standard loss function value, a target feedforward network model is generated.

7. An oil-filled cable multi-leakage point positioning system, characterized in that: include: A monitoring module, used for acquiring monitoring parameters and cable parameters of the oil-filled cable to be detected in real time, and determining the status information of the oil-filled cable to be detected according to the monitoring parameters; A positioning module, used for locating the leakage point of the oil-filled cable to be detected by using a single leakage point positioning method when the status information is cable leakage, so as to obtain a corresponding single leakage point position; A first analysis module is used to construct a multi-leakage point digital twin model based on the single leakage point and the cable parameters, and use the monitoring parameters to perform multi-leakage point leakage condition monitoring on the multi-leakage point digital twin model to obtain corresponding monitoring results; A second analysis module is used to locate the leakage point by using the multi-leakage point digital twin model, the monitoring parameters and the preset feedforward network model to obtain the second leakage point when the monitoring result is a secondary leakage of the oil-filled cable; An updating module is used to update the multi-leakage point digital twin model using the second leakage point, and based on the updated multi-leakage point digital twin model, jump to execute the step of monitoring the multi-leakage point leakage condition of the multi-leakage point digital twin model using the monitoring parameters to obtain corresponding monitoring results.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for locating multiple leakage points of an oil-filled cable as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for locating multiple leakage points in an oil-filled cable as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the method for locating multiple leak points in an oil-filled cable as described in any one of claims 1-6.

Images