A method and system for locating leakage and identifying leakage degree of submarine oil-filled cable

Abstract

The present invention relates to the technical field of oil-filled cable leakage detection, and discloses a method and system for locating and identifying leakage degree of a submarine oil-filled cable. The method simulates the cable end insulating oil flow of a historical submarine oil-filled cable under a preset cable end pressure value by using a reduced-order computational fluid dynamics model, and obtains a large amount of characteristic data of cable end pressure value, leakage point location, leakage state value and cable end insulating oil flow by loading different cable working condition data into the reduced-order computational fluid dynamics model and performing simulation calculations. A deep neural network is trained by using the characteristic data, and the leakage point location and leakage state value of a submarine oil-filled cable to be detected are identified by using the trained submarine oil-filled cable leakage identification model, so that the leakage point of the submarine oil-filled cable can be accurately located, and the leakage damping at the leakage point can be determined by the leakage state value, so as to facilitate the identification of the leakage degree at the leakage point of the submarine oil-filled cable.

Description

Technical Field

[0001] The present invention relates to the technical field of oil-filled cable leakage detection, and in particular to a method and system for locating leakage and identifying leakage degree of a submarine oil-filled cable. Background Art

[0002] At present, compared with terrestrial oil-filled cables, submarine oil-filled cables face many challenges in finding leakage points. First, due to the complexity of the submarine environment, manual investigation is difficult to achieve. The cost of using underwater robots to troubleshoot faults is extremely high, which limits its 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, due to the special structure of oil-filled submarine cables, it is difficult to deploy distributed optical fiber sensors that can be used to monitor leakage vibration signals or pressure sensors that can monitor negative pressure waves in submarine oil-filled cables.

[0003] At present, the submarine oil-filled cables in service are generally only equipped with pressure gauges and flow meters at both ends, and it is difficult to accurately identify the leakage point of the submarine oil-filled cables. The existing means of detecting submarine oil-filled cable leakage mainly rely on the analysis of the flow state of insulating oil, but the current means of detecting submarine oil-filled cable leakage are difficult to accurately locate the leakage point of the submarine oil-filled cable. At the same time, it is difficult to identify the leakage damping at the leakage point, and thus it is difficult to effectively identify the leakage degree at the leakage point of the submarine oil-filled cable. Summary of the invention

[0004] The present invention provides a method and system for locating leakage and identifying the leakage degree of a submarine oil-filled cable, which solves the technical problem that the current detection means for submarine oil-filled cable leakage is difficult to accurately locate the leakage point of the submarine oil-filled cable, and at the same time, it is difficult to identify the leakage damping at the leakage point, thereby making it difficult to effectively identify the leakage degree at the leakage point of the submarine oil-filled cable.

[0005] In view of this, a first aspect of the present invention provides a method for locating leakage and identifying leakage degree of a submarine oil-filled cable, comprising the following steps:

[0006] A reduced-order computational fluid dynamics model is constructed according to the insulating oil flow distribution of the historical submarine oil-filled cable, wherein the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value, wherein the historical submarine oil-filled cable includes a predetermined leakage point position and a predetermined leakage state value;

[0007] By loading different cable operating condition data into the reduced-order computational fluid dynamics model and performing simulation calculations, the insulating oil flow rate at the cable end of the historical submarine oil-filled cable under each of the cable operating condition data is obtained, wherein the cable operating condition data includes a cable end pressure value, a leakage point location, and a leakage state value;

[0008] Constructing a data set according to the cable working condition data and the insulating oil flow rate at the cable end;

[0009] The deep neural network is trained by the data set. During the training process, the pressure value at the cable end and the insulating oil flow rate at the cable end are used as inputs, and the leakage point position and the leakage state value are used as outputs for training, so as to obtain a submarine oil-filled cable leakage identification model;

[0010] In response to a leakage detection request for a submarine oil-filled cable, a cable end pressure value and a cable end insulating oil flow rate of the submarine oil-filled cable to be detected are obtained;

[0011] The cable end pressure value and the cable end insulating oil flow rate of the submarine oil-filled cable to be detected are input into the submarine oil-filled cable leakage identification model for identification, and the leakage point position and leakage status value of the submarine oil-filled cable to be detected are output.

[0012] Preferably, the step of constructing a reduced-order computational fluid dynamics model according to the insulating oil flow distribution of the historical submarine oil-filled cable, wherein the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow rate at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value, wherein the historical submarine oil-filled cable includes a predetermined leakage point position and a predetermined leakage state value, specifically includes:

[0013] Dividing the historical submarine oil-filled cable into a leaking cable section and a non-leaking cable section along the length direction of the historical submarine oil-filled cable, wherein the leaking cable section includes the predetermined leakage point location and the predetermined leakage state value, and the non-leaking cable section is a cable section far away from the predetermined leakage point location;

[0014] constructing a one-dimensional pipeline laminar flow model according to the route elevation change curve of the non-leaking cable section;

[0015] The one-dimensional pipeline laminar flow model is discretized by finite element mesh nodes, and a plurality of valve nodes are set in the discretized one-dimensional pipeline laminar flow model to obtain an optimized one-dimensional pipeline laminar flow model, wherein the valve nodes are used to equivalently simulate flow resistance;

[0016] A three-dimensional laminar flow model is constructed according to the leaking cable section, wherein the three-dimensional laminar flow model is a double-layer pipe structure, wherein the inner layer of the double-layer pipe structure is a free flow layer, and the outer layer of the double-layer pipe structure is a permeable flow layer composed of porous materials, and the permeability of the permeable flow layer is equivalent to the insulation oil leakage resistance, and a leakage point is set in the outer layer of the double-layer pipe structure, wherein the permeability of the permeable flow layer is used to characterize the leakage state value;

[0017] The optimized one-dimensional pipeline laminar flow model and the three-dimensional laminar flow model are coupled, boundary conditions at the coupling point are set, and a reduced-order computational fluid dynamics model is constructed. The reduced-order computational fluid dynamics model is used to simulate the cable end insulating oil flow of the historical submarine oil-filled cable under a preset cable end pressure value.

[0018] Preferably, the boundary conditions at the coupling point include a pressure continuity boundary condition and a flow continuity boundary condition.

[0019] Preferably, the method further comprises:

[0020] The boundary condition of the outer layer in the double-layer pipe structure is set to a non-slip flow boundary condition.

[0021] Preferably, the method further comprises:

[0022] The boundary condition of the predetermined leakage point position is set to a zero pressure boundary condition.

[0023] Preferably, the deep neural network is a BP neural network.

[0024] Preferably, the step of responding to a leakage detection request for a submarine oil-filled cable and obtaining a cable end pressure value and a cable end insulating oil flow rate of the submarine oil-filled cable to be detected specifically comprises:

[0025] In response to a leakage detection request for a submarine oil-filled cable, a constant pressure value is applied to a cable end of the submarine oil-filled cable to be detected, and the insulating oil flow rate of the cable end of the submarine oil-filled cable to be detected is measured.

[0026] In a second aspect, the present invention further provides a submarine oil-filled cable leakage location and leakage degree identification system, comprising:

[0027] A modeling module, for constructing a reduced-order computational fluid dynamics model according to the insulating oil flow distribution of a historical submarine oil-filled cable, wherein the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value, wherein the historical submarine oil-filled cable includes a predetermined leakage point location and a predetermined leakage state value;

[0028] A data loading module, used for loading different cable operating condition data into the reduced-order computational fluid dynamics model and performing simulation calculations to obtain the insulating oil flow rate at the cable end of the historical submarine oil-filled cable under each of the cable operating condition data, wherein the cable operating condition data includes a cable end pressure value, a leakage point location, and a leakage state value;

[0029] A data set construction module, used to construct a data set according to the cable working condition data and the insulating oil flow rate at the cable end;

[0030] A model training module is used to train a deep neural network using the data set. During the training process, the cable end pressure value and the cable end insulating oil flow rate are used as inputs, and the leakage point position and the leakage state value are used as outputs for training to obtain a submarine oil-filled cable leakage recognition model.

[0031] A data response module is used to respond to a leakage detection request for a submarine oil-filled cable and obtain a cable end pressure value and a cable end insulating oil flow rate of the submarine oil-filled cable to be detected;

[0032] The leakage identification module is used to input the cable end pressure value and the cable end insulating oil flow rate of the submarine oil-filled cable to be detected into the submarine oil-filled cable leakage identification model for identification, and output the leakage point position and leakage status value of the submarine oil-filled cable to be detected.

[0033] In a third aspect, the present invention further provides an electronic device, the electronic device comprising a memory and a processor;

[0034] The memory is used to store programs;

[0035] The processor executes the program to implement the above method.

[0036] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0037] It can be seen from the above technical solutions that the present invention has the following advantages:

[0038] The present invention simulates the cable end insulating oil flow of historical submarine oil-filled cables under preset cable end pressure values ​​through a reduced-order computational fluid dynamics model, and obtains a large amount of characteristic data of cable end pressure values, leakage point positions, leakage state values ​​and cable end insulating oil flow through loading different cable operating condition data into the reduced-order computational fluid dynamics model and performing simulation calculations. The deep neural network is trained through the characteristic data, and the leakage point position and leakage state value of the submarine oil-filled cable to be detected are identified using the trained submarine oil-filled cable leakage identification model, so that the leakage point of the submarine oil-filled cable can be accurately located. At the same time, the leakage damping at the leakage point can be determined through the leakage state value, so as to facilitate the identification of the leakage degree at the leakage point of the submarine oil-filled cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of a method for locating leakage and identifying leakage degree of a submarine oil-filled cable provided in an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of the section division of a submarine oil-filled cable provided in an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of a double-layer pipeline structure provided by an embodiment of the present invention;

[0042] Figure 4 A grid diagram of a three-dimensional laminar flow model provided by an embodiment of the present invention;

[0043] Figure 5 A schematic structural diagram of a submarine oil-filled cable leakage locating and leakage degree identifying system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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.

[0045] It should be noted that the terms "including" and "having" and any variations thereof in the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0046] This embodiment can be applied to the situation of locating leakage and identifying the extent of leakage of a submarine oil-filled cable. The method can be executed by a submarine oil-filled cable leakage locating and leakage extent identification device. The submarine oil-filled cable leakage locating and leakage extent identification device can be implemented in the form of hardware and / or software. The submarine oil-filled cable leakage locating and leakage extent identification device can be configured in a computer device.

[0047] The internal conductor of the current submarine oil-filled cable is made of a spirally wound copper strip to form a hollow pipe. The gaps on the surface of the conductor allow the insulating oil to pass freely. When the submarine oil-filled cable is working, the two sides of the submarine oil-filled cable are pressurized and the inside of the pipe is filled with insulating oil. If the submarine oil-filled cable leaks, the pressure inside the oil channel will squeeze the insulating oil out of the leak point, thereby preventing seawater from entering the cable and causing a short circuit in the conductor.

[0048] In view of this, the present invention provides a method for locating leakage and identifying leakage degree of a submarine oil-filled cable, such as Figure 1 As shown, Figure 1 The present invention illustrates a process of a method for locating leakage and identifying the degree of leakage of a submarine oil-filled cable.

[0049] The present invention provides a method for locating leakage and identifying leakage degree of a submarine oil-filled cable, comprising the following steps:

[0050] Step S1, constructing a reduced-order computational fluid dynamics model according to the insulating oil flow distribution of the historical submarine oil-filled cable, the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value, and the historical submarine oil-filled cable includes a predetermined leakage point location and a predetermined leakage state value.

[0051] It should be noted that, usually, leakage of submarine oil-filled cables is caused by cracks near the lead sheath. The insulating oil flows out along the gaps in the oil channel wall due to the pressure at both ends of the oil channel, penetrates through the insulating oil paper, and finally leaks out of the cable along the cracks. The entire process usually has a low flow rate, and this leakage flow can be considered as laminar flow. Therefore, using COMSOL software to construct a fluid mechanics model to replace the turbulence model to simulate the flow of insulating oil in the cable can be closer to the actual situation.

[0052] At the same time, the distance of submarine oil-filled cables can usually reach several thousand meters, so it is difficult to directly perform computational fluid modeling on cable oil channels of such lengths. It is necessary to use model reduction methods to make the amount of calculation controllable.

[0053] The cable end pressure value may include the pressure values ​​at both ends of the cable and the pressure values ​​at both ends of the cable are equal. The cable end insulating oil flow rate may include the insulating oil flow rates at both ends of the cable.

[0054] Step S2, by loading different cable operating condition data into the reduced-order computational fluid dynamics model and performing simulation calculations, the cable end insulating oil flow of the historical submarine oil-filled cable under each cable operating condition data is obtained, and the cable operating condition data includes the cable end pressure value, the leakage point location and the leakage state value.

[0055] It can be understood that by continuously changing the cable operating condition data and loading it into the reduced-order computational fluid dynamics model for simulation calculation, the cable end insulating oil flow of the historical submarine oil-filled cable under each cable operating condition data can be obtained, and a large amount of characteristic data of different cable end pressure values, leakage point locations, leakage state values ​​and cable end insulating oil flow can be collected.

[0056] The leakage state value is used to characterize the leakage degree of the submarine oil-filled cable, and the leakage state value can be characterized by the leakage resistance of the insulating oil.

[0057] Step S3: construct a data set based on the cable operating condition data and the insulating oil flow at the cable end.

[0058] In one example, the dataset is normalized and preprocessed using StandardScaler.

[0059] Step S4, training the deep neural network through the data set. During the training process, the cable end pressure value and the cable end insulating oil flow rate are used as input, and the leakage point location and leakage state value are used as output for training to obtain a submarine oil-filled cable leakage recognition model.

[0060] Among them, the deep neural network can be a BP neural network.

[0061] In one example, a BP deep neural network was established in the Python programming environment JupyterNotebook using the open source deep learning software library TensorFlow, and trained with the cable end pressure value and the cable end insulating oil flow rate as inputs and the leakage point location and leakage status value as outputs.

[0062] Step S5: respond to a leakage detection request for the submarine oil-filled cable, and obtain the cable end pressure value and the insulating oil flow rate at the cable end of the submarine oil-filled cable to be detected.

[0063] Specifically, step S5 specifically includes: responding to a leakage detection request for the submarine oil-filled cable, applying a constant pressure value to the cable end of the submarine oil-filled cable to be detected, and measuring the insulating oil flow rate at the cable end of the submarine oil-filled cable to be detected.

[0064] Among them, a flow measuring instrument is set at the cable end of the submarine oil-filled cable.

[0065] Step S6: input the cable end pressure value and the cable end insulating oil flow rate of the submarine oil-filled cable to be detected into the submarine oil-filled cable leakage identification model for identification, and output the leakage point position and leakage status value of the submarine oil-filled cable to be detected.

[0066] It should be noted that the present invention simulates the cable end insulating oil flow of the historical submarine oil-filled cable under the preset cable end pressure value through the reduced-order computational fluid dynamics model, and obtains a large amount of characteristic data of the cable end pressure value, the leakage point position, the leakage state value and the cable end insulating oil flow through the reduced-order computational fluid dynamics model and performs simulation calculations. The deep neural network is trained through the characteristic data, and the leakage point position and leakage state value of the submarine oil-filled cable to be detected are identified using the trained submarine oil-filled cable leakage identification model, so that the leakage point of the submarine oil-filled cable can be accurately located. At the same time, the leakage damping at the leakage point can be determined through the leakage state value, so as to facilitate the identification of the leakage degree at the leakage point of the submarine oil-filled cable.

[0067] It should also be noted that the present invention can accurately locate the leakage point of the submarine oil-filled cable without relying on sensors other than the flow meter and pressure gauge at the cable end, thereby greatly saving the cost of finding the leakage point. At the same time, this method is not only suitable for high-pressure oil-filled submarine cables, but can also be extended to leakage detection applications of other types of pipelines such as oil and gas pipelines.

[0068] In a specific embodiment, step S1 specifically includes the following steps S101-S105:

[0069] Step S101, dividing the historical submarine oil-filled cable into a leaking cable section and a non-leaking cable section along the length direction of the historical submarine oil-filled cable, the leaking cable section including a predetermined leakage point location and a predetermined leakage state value, and the non-leaking cable section being a cable section far away from the predetermined leakage point location.

[0070] It should be noted that the distance of submarine oil-filled cables can usually reach several thousand meters. The flow of insulating oil is in the laminar range, and the flow away from the leak point is uniform. The length of the leaking cable section can be determined through experiments. In an example, Figure 2 As shown, Figure 2 The segment division of the submarine oil-filled cable is illustrated. The length of the leaking cable segment is set to 0.25 meters so that the non-uniform flow near the leak point can develop into a uniform flow at the simulation boundary.

[0071] Step S102: construct a one-dimensional pipeline laminar flow model according to the route elevation change curve of the non-leaking cable section.

[0072] Among them, the insulating oil flow in the non-leakage cable section is in the laminar flow range, and the flow in the non-leakage cable section is a uniform flow. The one-dimensional pipe flow model in COMSOL can be used to simulate the insulating oil flow state far away from the leakage point, thereby describing the relationship between the flow velocity and pressure drop in the non-leakage cable section.

[0073] Step S103, discretizing the finite element mesh nodes of the one-dimensional pipeline laminar flow model, and setting a plurality of valve nodes in the discretized one-dimensional pipeline laminar flow model to obtain an optimized one-dimensional pipeline laminar flow model, wherein the valve nodes are used to equivalently simulate the flow resistance.

[0074] The one-dimensional pipeline laminar flow model is also a numerical model based on finite elements. The cable in the non-leaking cable section is meshed using one-dimensional line elements to capture the elevation changes of the cable, so that the model can take into account the changes in cable elevation.

[0075] Among them, by setting multiple valve nodes in the discretized one-dimensional pipeline laminar flow model, the flow resistance caused by the oil flow restrictor can be simulated.

[0076] Step S104, constructing a three-dimensional laminar flow model according to the leaking cable section, the three-dimensional laminar flow model is a double-layer pipe structure, wherein the inner layer of the double-layer pipe structure is a free flow layer, and the outer layer of the double-layer pipe structure is a permeable flow layer composed of porous materials, and the permeability of the permeable flow layer is equivalent to the insulating oil leakage resistance, and a leakage point is set in the outer layer of the double-layer pipe structure, wherein the permeability of the permeable flow layer is used to characterize the leakage state value.

[0077] Among them, since the flow near the leakage point is non-uniform and asymmetric, the flow of insulating oil can be simulated by adopting a three-dimensional laminar flow model simulation method. In this embodiment, in order to consider the penetration process of insulating oil in the cable, a model is constructed as follows: Figure 3 In the double-layer pipe structure shown in the figure, a circular leakage outlet with a diameter of 5 mm can be set at the bottom of the outer layer in the three-dimensional laminar flow model; the porous medium single-phase flow module (Free and Porous Media Flow) in COMSOL is used for calculation, and the inner layer is set as a free flow layer, and the outer layer is set as a permeable flow layer composed of porous materials, so as to simulate the leakage flow of the multi-layer cable structure. At the same time, in the COMSOL modeling, the outer layer is set as a porous medium layer, and the permeability of the outer layer can be adjusted by changing the permeability of this layer.

[0078] The permeability of the porous medium layer of the outer layer of the three-dimensional laminar flow model is used to characterize the insulation oil leakage resistance of the leakage point (i.e., the same leakage flow rate as the actual cable leakage point under the same oil pressure conditions), and is set as a parameter representing the properties of the leakage point. By using the permeability of the porous medium layer to be equivalent to the flow damping caused by multi-layer cables and different leakage point shapes, it is helpful to perform digital twinning of the leakage flow, thereby continuously monitoring the status of the leakage point.

[0079] In terms of spatial discretization, tetrahedron units are used to divide the double-layer pipeline structure, and hexahedron units are used to divide the junction between the inner and outer pipelines and the vicinity of the pipeline outer wall, so as to obtain the following Figure 4 Mesh diagram of the illustrated 3D laminar flow model.

[0080] Step S105, coupling the optimized one-dimensional pipeline laminar flow model and the three-dimensional laminar flow model, setting boundary conditions at the coupling point, and constructing a reduced-order computational fluid dynamics model, which is used to simulate the cable end insulating oil flow of the historical submarine oil-filled cable under a preset cable end pressure value.

[0081] The boundary conditions at the coupling point include pressure continuity boundary conditions and flow continuity boundary conditions.

[0082] In one example, the boundary condition of the outer layer in the double-layer pipe structure can be set as a non-slip flow boundary condition, that is, the fluid velocity vector at the wall is zero, and the boundary condition at the predetermined leakage point position can also be set as a zero pressure boundary condition.

[0083] The above is a detailed description of an embodiment of a method for locating leakage and identifying leakage degree of a submarine oil-filled cable provided by the present invention. The following is a detailed description of an embodiment of a system for locating leakage and identifying leakage degree of a submarine oil-filled cable provided by the present invention.

[0084] For easier understanding, see Figure 5 The present invention also provides a submarine oil-filled cable leakage location and leakage degree identification system, comprising:

[0085] A modeling module 100 is used to construct a reduced-order computational fluid dynamics model according to the insulating oil flow distribution of the historical submarine oil-filled cable, the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow of the cable end of the historical submarine oil-filled cable under a preset cable end pressure value, and the historical submarine oil-filled cable includes a predetermined leakage point location and a predetermined leakage state value;

[0086] The data loading module 200 is used to load different cable operating condition data into the reduced-order computational fluid dynamics model and perform simulation calculations to obtain the insulating oil flow rate at the cable end of the historical submarine oil-filled cable under each cable operating condition data, wherein the cable operating condition data includes the cable end pressure value, the leakage point location and the leakage state value;

[0087] A data set construction module 300 is used to construct a data set according to the cable working condition data and the insulating oil flow rate at the cable end;

[0088] The model training module 400 is used to train the deep neural network through the data set. During the training process, the pressure value at the cable end and the insulating oil flow rate at the cable end are used as inputs, and the leakage point location and leakage state value are used as outputs for training to obtain a submarine oil-filled cable leakage recognition model;

[0089] The data response module 500 is used to respond to the leakage detection request for the submarine oil-filled cable and obtain the cable end pressure value and the insulating oil flow rate of the submarine oil-filled cable to be detected;

[0090] The leakage identification module 600 is used to input the cable end pressure value and the cable end insulating oil flow rate of the submarine oil-filled cable to be detected into the submarine oil-filled cable leakage identification model for identification, and output the leakage point position and leakage status value of the submarine oil-filled cable to be detected.

[0091] The present invention also provides an electronic device, the electronic device comprising a memory and a processor;

[0092] The memory is used to store programs;

[0093] The processor executes the program to implement the above method.

[0094] The present invention also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0095] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, electronic device and computer storage medium can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0096] In several embodiments provided by the present invention, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and a part of a module, a program segment or a code includes one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0097] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, electronic devices, computer storage media 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.

[0098] 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.

[0099] 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.

[0100] 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 is essentially 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 executing all or part of the steps of the method described in each embodiment of the present invention through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0101] 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 leakage and identifying leakage degree of a submarine oil-filled cable, characterized in that: The following steps are involved: A reduced-order computational fluid dynamics model is constructed according to the insulating oil flow distribution of the historical submarine oil-filled cable. The reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value. The historical submarine oil-filled cable includes a predetermined leakage point position and a predetermined leakage state value, specifically including: Dividing the historical submarine oil-filled cable into a leaking cable section and a non-leaking cable section along the length direction of the historical submarine oil-filled cable, wherein the leaking cable section includes the predetermined leakage point location and the predetermined leakage state value, and the non-leaking cable section is a cable section far away from the predetermined leakage point location; constructing a one-dimensional pipeline laminar flow model according to the route elevation change curve of the non-leaking cable section; The one-dimensional pipeline laminar flow model is discretized by finite element mesh nodes, and a plurality of valve nodes are set in the discretized one-dimensional pipeline laminar flow model to obtain an optimized one-dimensional pipeline laminar flow model, wherein the valve nodes are used to equivalently simulate flow resistance; A three-dimensional laminar flow model is constructed according to the leaking cable section, wherein the three-dimensional laminar flow model is a double-layer pipe structure, wherein the inner layer of the double-layer pipe structure is a free flow layer, and the outer layer of the double-layer pipe structure is a permeable flow layer composed of porous materials, and the permeability of the permeable flow layer is equivalent to the insulation oil leakage resistance, and a leakage point is set in the outer layer of the double-layer pipe structure, wherein the permeability of the permeable flow layer is used to characterize the leakage state value; The optimized one-dimensional pipeline laminar flow model and the three-dimensional laminar flow model are coupled, boundary conditions at the coupling point are set, and a reduced-order computational fluid dynamics model is constructed, wherein the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value; By loading different cable operating condition data into the reduced-order computational fluid dynamics model and performing simulation calculations, the insulating oil flow rate at the cable end of the historical submarine oil-filled cable under each of the cable operating condition data is obtained, wherein the cable operating condition data includes a cable end pressure value, a leakage point location, and a leakage state value; Constructing a data set according to the cable working condition data and the insulating oil flow rate at the cable end; The deep neural network is trained by the data set. During the training process, the pressure value at the cable end and the insulating oil flow rate at the cable end are used as inputs, and the leakage point position and the leakage state value are used as outputs for training, so as to obtain a submarine oil-filled cable leakage identification model; In response to a leakage detection request for a submarine oil-filled cable, a cable end pressure value and a cable end insulating oil flow rate of the submarine oil-filled cable to be detected are obtained; The cable end pressure value and the cable end insulating oil flow rate of the submarine oil-filled cable to be detected are input into the submarine oil-filled cable leakage identification model for identification, and the leakage point position and leakage status value of the submarine oil-filled cable to be detected are output.

2. The method for locating leakage and identifying leakage degree of a submarine oil-filled cable according to claim 1 is characterized in that: The boundary conditions at the coupling point include a pressure continuity boundary condition and a flow continuity boundary condition.

3. The method for locating leakage and identifying leakage degree of a submarine oil-filled cable according to claim 1 is characterized in that: Also includes: The boundary condition of the outer layer in the double-layer pipe structure is set to a non-slip flow boundary condition.

4. The method for locating leakage and identifying leakage degree of a submarine oil-filled cable according to claim 1, characterized in that: Also includes: The boundary condition of the predetermined leakage point position is set to a zero pressure boundary condition.

5. The method for locating leakage and identifying leakage degree of submarine oil-filled cable according to claim 1, characterized in that: The deep neural network is a BP neural network.

6. The method for locating leakage and identifying leakage degree of a submarine oil-filled cable according to claim 1, characterized in that: The step of responding to a leakage detection request for a submarine oil-filled cable and obtaining a cable end pressure value and a cable end insulating oil flow rate of the submarine oil-filled cable to be detected specifically includes: In response to a leakage detection request for a submarine oil-filled cable, a constant pressure value is applied to a cable end of the submarine oil-filled cable to be detected, and the insulating oil flow rate of the cable end of the submarine oil-filled cable to be detected is measured.

7. A submarine oil-filled cable leakage location and leakage degree identification system, characterized in that: include: A modeling module is used to construct a reduced-order computational fluid dynamics model according to the insulating oil flow distribution of the historical submarine oil-filled cable, wherein the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value, wherein the historical submarine oil-filled cable includes a predetermined leakage point position and a predetermined leakage state value, specifically including: Dividing the historical submarine oil-filled cable into a leaking cable section and a non-leaking cable section along the length direction of the historical submarine oil-filled cable, wherein the leaking cable section includes the predetermined leakage point location and the predetermined leakage state value, and the non-leaking cable section is a cable section far away from the predetermined leakage point location; constructing a one-dimensional pipeline laminar flow model according to the route elevation change curve of the non-leaking cable section; The one-dimensional pipeline laminar flow model is discretized by finite element mesh nodes, and a plurality of valve nodes are set in the discretized one-dimensional pipeline laminar flow model to obtain an optimized one-dimensional pipeline laminar flow model, wherein the valve nodes are used to equivalently simulate flow resistance; A three-dimensional laminar flow model is constructed according to the leaking cable section, wherein the three-dimensional laminar flow model is a double-layer pipe structure, wherein the inner layer of the double-layer pipe structure is a free flow layer, and the outer layer of the double-layer pipe structure is a permeable flow layer composed of porous materials, and the permeability of the permeable flow layer is equivalent to the insulation oil leakage resistance, and a leakage point is set in the outer layer of the double-layer pipe structure, wherein the permeability of the permeable flow layer is used to characterize the leakage state value; The optimized one-dimensional pipeline laminar flow model and the three-dimensional laminar flow model are coupled, boundary conditions at the coupling point are set, and a reduced-order computational fluid dynamics model is constructed, wherein the reduced-order computational fluid dynamics model is used to simulate the insulating oil flow at the cable end of the historical submarine oil-filled cable under a preset cable end pressure value; A data loading module, used for loading different cable operating condition data into the reduced-order computational fluid dynamics model and performing simulation calculations to obtain the insulating oil flow rate at the cable end of the historical submarine oil-filled cable under each of the cable operating condition data, wherein the cable operating condition data includes a cable end pressure value, a leakage point location, and a leakage state value; A data set construction module, used to construct a data set according to the cable working condition data and the insulating oil flow rate at the cable end; A model training module is used to train a deep neural network using the data set. During the training process, the cable end pressure value and the cable end insulating oil flow rate are used as inputs, and the leakage point position and the leakage state value are used as outputs for training to obtain a submarine oil-filled cable leakage recognition model. A data response module is used to respond to a leakage detection request for a submarine oil-filled cable and obtain a cable end pressure value and a cable end insulating oil flow rate of the submarine oil-filled cable to be detected; The leakage identification module is used to input the cable end pressure value and the cable end insulating oil flow rate of the submarine oil-filled cable to be detected into the submarine oil-filled cable leakage identification model for identification, and output the leakage point position and leakage status value of the submarine oil-filled cable to be detected.

8. An electronic device, characterized in that: The electronic device comprises a memory and a processor; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images