CN116911107A - Cable temperature prediction method, device and terminal equipment - Google Patents
Cable temperature prediction method, device and terminal equipment Download PDFInfo
- Publication number
- CN116911107A CN116911107A CN202310757054.1A CN202310757054A CN116911107A CN 116911107 A CN116911107 A CN 116911107A CN 202310757054 A CN202310757054 A CN 202310757054A CN 116911107 A CN116911107 A CN 116911107A
- Authority
- CN
- China
- Prior art keywords
- model
- cable
- temperature
- cable core
- electromagnetic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Laying Of Electric Cables Or Lines Outside (AREA)
Abstract
本申请适用于隧道电缆技术领域，提供了电缆温度预测方法、装置及终端设备，该方法包括：建立电磁场计算模型、温度场计算模型、流体场计算模型以及隧道和电缆的三维几何模型；建立电缆集群的电磁‑热‑流多物理场有限元仿真三维模型，并添加电磁热耦合和非等温流耦合；设置该仿真模型下的环境温度、风速和边界条件，对该仿真模型施加负荷电流，以及对几何模型设置网格剖分参数进行网格剖分；对仿真模型进行有限元暂态计算，获取电缆缆芯温度数据；基于电缆缆芯温度数据对电缆缆芯温度预测模型进行训练，基于训练后的电缆缆芯温度预测模型对电缆温度进行预测。本申请预测结果更贴合实际。
This application is applicable to the technical field of tunnel cables and provides cable temperature prediction methods, devices and terminal equipment. The method includes: establishing an electromagnetic field calculation model, a temperature field calculation model, a fluid field calculation model and a three-dimensional geometric model of the tunnel and cable; establishing a cable Clustered electromagnetic-thermal-flow multiphysics finite element simulation three-dimensional model, and add electromagnetic thermal coupling and non-isothermal flow coupling; set the ambient temperature, wind speed and boundary conditions under the simulation model, apply load current to the simulation model, and Set the meshing parameters of the geometric model for meshing; perform finite element transient calculations on the simulation model to obtain cable core temperature data; train the cable core temperature prediction model based on the cable core temperature data. Based on the training The latter cable core temperature prediction model predicts the cable temperature. The prediction results of this application are more realistic.
Description
Technical Field
The application belongs to the technical field of tunnel cables, and particularly relates to a cable temperature prediction method, a device and terminal equipment.
Background
With the rapid development of the power network, in order to solve the conflict between urban land shortage and urban overhead cables, the laying mode of tunnel cable clusters is more common, so that the phenomena of cable life reduction and cable resource waste caused by the problem of load distribution of the power cables are generated. If the temperature of the cable core of the power cable can be predicted, reasonable cable load planning can be performed according to the cable core temperature, so that the overall current carrying capacity of the tunnel cable cluster is further improved, and therefore, the temperature is an important parameter for reflecting whether the power cable normally operates or not and is also used as an important basis for reasonably distributing loads.
At present, many researches on cable core temperature prediction are sequentially carried out, but the temperature of the cable core is imperfect and has a certain limitation, because the temperature of the cable core is difficult to detect in the operation process of the cable, and the problems of large error, high cost and the like still exist although the temperature is measured by adding optical fibers into the cable. The inventors found in the study that: the two-dimensional model is used for carrying out simulation on the cable running state, and compared with the actual cable running, the problems of neglecting the influences of more complex electromagnetic correlation, heat transfer correlation, non-isothermal flow and the like exist, so that the temperature of the cable core of the cable is difficult to accurately predict.
Disclosure of Invention
In order to overcome the problems in the related art, the embodiment of the application provides a cable temperature prediction method, a device and terminal equipment.
The application is realized by the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for predicting a cable temperature, including:
establishing an electromagnetic field calculation model, a temperature field calculation model, a fluid field calculation model and a three-dimensional geometric model of a tunnel and a cable, wherein the geometric model comprises structural parameters and material parameters of each layer of structure of the cable;
establishing an electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model of the cable cluster under the material parameters according to the electromagnetic field calculation model, the temperature field calculation model, the fluid field calculation model and the three-dimensional geometric model of the tunnel and the cable, and adding electromagnetic thermal coupling and non-isothermal flow coupling;
setting the environment temperature, wind speed and boundary conditions under the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, applying load current to the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, and setting mesh subdivision parameters for the geometric model to perform mesh subdivision;
performing finite element transient calculation on the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model to obtain cable core temperature data;
And training the cable core temperature prediction model based on the cable core temperature data, and predicting the cable temperature based on the trained cable core temperature prediction model.
In the embodiment of the application, the three-dimensional transient model of the electromagnetic-thermal-flow multi-physical field coupling of the tunnel cable cluster is constructed, and compared with the two-dimensional model, the model can simulate and analyze the real running condition of the tunnel cable cluster; the operation condition of the cable is simulated more closely through electromagnetic thermal coupling and non-isothermal flow coupling, so that the prediction result is more fit and practical. Compared with detection and monitoring of optical fiber cables, the embodiment of the application has low cost and wide application range.
With reference to the first aspect, in some embodiments, the expression of the electromagnetic field calculation model is:
wherein J is e And J s Is the source variable, which is the vortex density and the current density, respectively, and the unit is A/m 2 The method comprises the steps of carrying out a first treatment on the surface of the H is the magnetic field intensity, unit A/m; b is magnetic induction intensity, and the unit is T; d is an electric displacement vector;
the temperature field calculation model expression is as follows:
wherein phi is in Indicating the amount of heat flowing into a particular micro-element; phi out Indicating the amount of heat flowing out of a particular micro-element; q represents the internal heat of the micro-element body; c represents the constant pressure heat capacity of the gas, and the unit is J/(kg.K); ρ is the density of air in kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the λ represents the thermal conductivity of the gas in W/(mK);
the fluid field calculation model expression is:ρ is the density of air in kg/m 3 ，c P Representing the constant pressure heat capacity of gas, wherein the unit is J/(kg.K); λ represents the thermal conductivity of the gas in W/(mK); u is a velocity component in the x-axis direction in m/s; v is the velocity component in the y-axis direction in m/s; w is a velocity component in the z-axis direction in m/s;
the geometric model of the cable is a three-dimensional geometric model constructed according to a cable core, an insulating layer of the cable, a buffer layer of the cable, a metal sheath layer of the cable and an outer sheath layer of the cable, the structural parameters comprise thickness and outer diameter, and the material parameters comprise heat conductivity coefficient, constant pressure heat capacity, density, relative dielectric parameters, relative magnetic conductivity and electric conductivity.
With reference to the first aspect, in some embodiments, the electromagnetic thermal coupling is a coupling between an electromagnetic field and a thermal field, and the non-isothermal flow coupling is a coupling between a thermal field and a fluid field;
the electromagnetic thermal coupling is as follows:
the non-isothermal flow coupling is:
wherein J is vortex density, and the unit is A/m 2 The method comprises the steps of carrying out a first treatment on the surface of the Sigma is conductivity, sigma 0 The initial conductivity is S/m; alpha is a parameter of the unit and is, Is a set of temperature parameters in degrees celsius. J (J) e Is a vortex density parameter set, and has the unit of A/m 2 ；q v Is a charge, in units of C; ρ is the fluid density in Kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the p is the fluid pressure in N/m 2 The method comprises the steps of carrying out a first treatment on the surface of the u is the fluid velocity in m 3 S; mu is dynamic viscosity, and the unit is Pa.s;The gradient is F, the external force acting on the fluid, and the unit is N.
With reference to the first aspect, in some embodiments, the setting the environmental temperature, the wind speed, and the boundary conditions under the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, applying a load current to the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model includes:
applying a periodically varying load current to the cable core;
applying a zero potential to the copper shield;
for the upper boundary of the physical model, heat is transferred in a convection heat transfer mode, and the air convection heat transfer coefficient is set to be 10W/(m) for the third type boundary condition of the temperature field 2 K); for the left and right boundaries of the physical model, as the outer boundary is far away from the cable, the insulation position is used as a second class boundary condition, and the heat flux density is 0; for the lower boundary of the physical model,setting a preset constant temperature as a first type of boundary condition;
Setting the ambient temperature to a temperature curve which changes periodically;
the wind speed is set to be a step function, and the step function is expressed as a wind speed change and a stable transient model.
With reference to the first aspect, in some embodiments, the performing mesh subdivision on the geometric model setting mesh subdivision parameters includes:
the model area is divided into two parts of a cable and an external environment for grid subdivision, a denser triangle unit is adopted for the cable part for division, and a sparser triangle and quadrilateral grid is adopted for the external environment for subdivision.
With reference to the first aspect, in some embodiments, the training the cable core temperature prediction model based on the cable core temperature data includes:
deleting incomplete data sets in the cable core temperature data, and dividing the remaining complete data sets into a training set and a verification set;
normalizing the training set and the verification set;
and training the cable core temperature prediction model by adopting a training set after normalization processing, and verifying the performance of the trained cable core temperature prediction model by adopting a verification set after normalization processing.
With reference to the first aspect, in some embodiments, the cable core temperature prediction model is a CNN-LSTM-Attention model.
In a second aspect, an embodiment of the present application provides a cable temperature prediction apparatus, including:
the first model building module is used for building an electromagnetic field calculation model, a temperature field calculation model, a fluid field calculation model and a three-dimensional geometric model of the tunnel and the cable, wherein the three-dimensional geometric model comprises structural parameters and material parameters of each layer of structure of the cable;
the second model building module is used for building an electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model of the cable cluster under the material parameters according to the electromagnetic field calculation model, the temperature field calculation model, the fluid field calculation model and the three-dimensional geometric model of the tunnel and the cable, and adding electromagnetic thermal coupling and non-isothermal flow coupling;
the device comprises a setting dividing module, a geometric model setting module and a mesh subdivision module, wherein the setting dividing module is used for setting the environmental temperature, wind speed and boundary conditions of the electromagnetic-thermal-flow multi-physical-field finite element simulation three-dimensional model, applying load current to the electromagnetic-thermal-flow multi-physical-field finite element simulation three-dimensional model, and setting mesh subdivision parameters for the geometric model to perform mesh subdivision;
the data acquisition module is used for carrying out finite element transient calculation on the electromagnetic-thermal-flow multi-physical field finite element three-dimensional simulation model to acquire cable core temperature data;
The training prediction module is used for training the cable core temperature prediction model based on the cable core temperature data and predicting the cable temperature based on the trained cable core temperature prediction model.
In a third aspect, an embodiment of the present application provides a terminal device, including a memory and a processor, where the memory stores a computer program executable on the processor, and where the processor implements the cable temperature prediction method according to any one of the first aspects when executing the computer program.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the cable temperature prediction method according to any one of the first aspects.
In a fifth aspect, an embodiment of the present application provides a computer program product for, when run on a terminal device, causing the terminal device to perform the cable temperature prediction method according to any one of the first aspects above.
It will be appreciated that the advantages of the second to fifth aspects may be found in the relevant description of the first aspect, and are not described here again.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a cable temperature prediction method according to an embodiment of the present application;
FIG. 2 is a cross-sectional symmetry view of a 110kV cable in accordance with an embodiment of the application;
FIG. 3 is a three-dimensional model diagram of a tunnel cable cluster according to an embodiment of the present application;
FIG. 4 is a graph of periodic tunnel ambient temperature provided by an embodiment of the present application;
FIG. 5 is a graph of periodic load current provided by an embodiment of the present application;
FIG. 6 is a grid section view of a tunnel cable cluster according to an embodiment of the present application;
FIG. 7 is a grid quality assessment graph of a tunnel cable cluster provided by an embodiment of the present application;
FIG. 8 is a graph showing a temperature profile of a tunnel cable cluster according to an embodiment of the present application;
FIG. 9 is a graph of operating temperature of a three-phase cable of a loop in a tunnel cable cluster according to an embodiment of the present application;
FIG. 10 is a diagram illustrating the input and output structure of a cable core temperature prediction model according to an embodiment of the present application;
FIG. 11 is a graph of a prediction error of a cable core of a CNN-LSTM cable core prediction model A-phase cable, according to an embodiment of the present application;
FIG. 12 is a graph of a prediction result of a CNN-LSTM cable core prediction model A-phase cable core according to an embodiment of the present application;
FIG. 13 is a graph of the prediction error of a B-phase cable core of a CNN-LSTM cable core prediction model according to an embodiment of the present application;
FIG. 14 is a graph of a predicted result of a B-phase cable core of a CNN-LSTM cable core prediction model according to an embodiment of the present application;
FIG. 15 is a graph of the prediction error of a C-phase cable core of a CNN-LSTM cable core prediction model according to an embodiment of the present application;
FIG. 16 is a graph of a predicted result of a C-phase cable core of a CNN-LSTM cable core prediction model according to an embodiment of the present application;
FIG. 17 is a block diagram of a cable core temperature prediction CNN-LSTM-Attention model according to an embodiment of the present application;
FIG. 18 is a graph showing a comparison of the prediction results of a phase A cable core of a CNN-LSTM-Attention cable core prediction model according to an embodiment of the present application;
FIG. 19 is a graph showing the comparison of the prediction results of a C-phase cable core of a CNN-LSTM-Attention cable core prediction model according to an embodiment of the present application;
FIG. 20 is a graph showing the comparison of the predicted results of a B-phase cable core of a CNN-LSTM-Attention cable core prediction model according to an embodiment of the present application;
FIG. 21 is a graph showing the root mean square error of the algorithm of the CNN-LSTM model and the CNN-LSTM-Attention model according to an embodiment of the present application;
fig. 22 is a schematic structural diagram of a cable temperature prediction device according to an embodiment of the present application;
fig. 23 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Fig. 1 is a schematic flowchart of a cable temperature prediction method according to an embodiment of the present application, and referring to fig. 1, the cable temperature prediction method is described in detail as follows:
step 101, an electromagnetic field calculation model, a temperature field calculation model, a fluid field calculation model and a three-dimensional geometric model of a tunnel and a cable are established, wherein the three-dimensional geometric model comprises structural parameters and material parameters of each layer of structure of the cable.
In the embodiment of the application, when a single-core high-voltage power cable flows a load alternating current in an electromagnetic field, the material of the metal part of the cable generates eddy current loss, which is caused by the fact that the cable core and the metal sheath layer are in an alternating magnetic field. Macroscopic electromagnetic phenomena can be equated to maxwell's equations. The basic variables include: magnetic field strength H, unit A/m. The electric field strength E is in V/m. Magnetic induction B, unit is T. And an electric displacement vector D, the source variables of which include: current density J, unit A/m 2 . And a charge density p in C/m 3 . The expression based on which the electromagnetic field calculation model is derived may be:
wherein J is e And J s Is the source variable, which is the vortex density and the current density, respectively, and the unit is A/m 2 The method comprises the steps of carrying out a first treatment on the surface of the H is the magnetic field intensity, unit A/m; b is magnetic induction intensity, and the unit is T; d is an electric displacement vector; to characterize macroscopic electromagnetic properties, the relationship between the parameters of maxwell's equations and the relevant field quantities can be expressed as:
D＝εE
B＝μH
J＝σE
wherein epsilon is dielectric constant, mu is magnetic permeability and the unit is H/m; sigma is conductivity in S/m.
In the embodiment of the application, the temperature field is similar to the gravity field in space, the field with the temperature is called as the temperature field, and the heat transfer phenomenon exists in the temperature field of heat transfer science, and the heat transfer modes can be respectively heat conduction, heat convection and heat radiation. The surrounding environment of the tunnel cable cluster is air, belongs to natural convection, and adopts a third type of boundary condition to solve a numerical calculation model. A third type of boundary conditions, in which the convective heat transfer coefficient of the model boundary with the outside air is defined, defines the heat exchange between the inside and outside of the model, and the temperature field calculation model expression is:
wherein phi is in Indicating the amount of heat flowing into a particular micro-element; phi out Indicating the amount of heat flowing out of a particular micro-element; q represents the internal heat of the micro-element body; c represents the constant pressure heat capacity of the gas, and the unit is J/(kg.K); ρ is the density of air in kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the Lambda represents the thermal conductivity of the gas in W/(mK).
In the embodiment of the application, a proper fluid field is needed to be selected, and the air flow in the fluid field is generally divided into natural convection and forced convection, wherein the natural convection depends on the temperature distribution condition in the air. When the temperature is unevenly distributed, the cold flow is reduced, the heat flow is increased, and natural convection is formed in the tunnel. Ventilation devices are usually arranged in the tunnel to realize forced convection to dissipate heat of the cable. The forced convection is to distinguish laminar flow and turbulent flow, and the laminar flow smoothly and slowly flows in a straight line in a tunnel; the turbulence is that the motion track of the fluid is changed in different magnitudes along with the change of the flow velocity, the faster the flow velocity is, the larger the swing amplitude is, and the flow is irregular, so that the Reynolds number is judged, and the fluid in the tunnel is determined to be laminar or turbulent before the fluid field is analyzed.
Determining whether the fluid in the tunnel is laminar or turbulent according to the following formula:
wherein U is air flow velocity, L is tunnel diameter, ρ is air density, and the unit is kg/m 3 Eta is the kinetic viscosity in Pas. When the Reynolds number is less than 2300, the fluid in the tunnel is generally considered to be laminar, and when the Reynolds number is more than 4000, the fluid in the tunnel is generally considered to be mainly turbulent. For example, the tunnel cross-section is 2.9m long and 2.8m wide, and the average flow rate in the tunnel is 1m/s. When ρ=1.29, η=17.9×10 -6 Taking this standard value, its Reynolds number>>4000, the tunnel is thus determined to be turbulent. Based on this, the fluid field calculation model expression is:ρ is the density of air in kg/m 3 ，c P Representing the constant pressure heat capacity of gas, wherein the unit is J/(kg.K); λ represents the thermal conductivity of the gas in W/(mK); u is a velocity component in the x-axis direction in m/s; v is the velocity component in the y-axis direction in m/s; w is the velocity component in the z-axis direction in m/s.
The geometric model of the cable is a three-dimensional geometric model constructed according to a cable core, an insulating layer of the cable, a buffer layer of the cable, a metal sheath layer of the cable and an outer sheath layer of the cable, the structural parameters comprise thickness and outer diameter, and the material parameters comprise heat conductivity coefficient, constant pressure heat capacity, density, relative dielectric parameters, relative magnetic conductivity and electric conductivity.
Specifically, a 110kV tunnel XLPE cable cluster model can be selectively established, and the cables can adopt YJLW03-64/110-1 multiplied by 1200mm 2 For faster calculation in the process of establishing a geometric model of the cable, simplifying the structure of the cable, combining a conductor shielding layer with an insulating layer in a shielding way, combining an inner sheath layer with an outer sheath layer, and mainly comprising a cable core, an insulating layer, a buffer layer, a metal sheath layer and the outer sheath layer, wherein the three-dimensional structure is formed by the 5 parts The geometrical model, the symmetry diagram of the 110kV cable section is shown in figure 2. Exemplary, the structural parameters of the materials of each layer of the three-dimensional geometric model of the cable are shown in table 1.
TABLE 1 structural parameters of materials of layers of three-dimensional geometric model of Cable
In the model, a cable laying mode is selected to be tunnel laying, an 8-loop 110kV high-voltage single-core cable is laid horizontally, wherein the distance between the upper layer and the lower layer of the cable is 0.04m, and the width of a passage in the middle of the cable tunnel is 1.3m. A three-dimensional model diagram of a tunnel cable cluster is shown in fig. 3. The structural parameters of the three-dimensional geometric model of the tunnel may include cross-section length, cross-section width, concrete thickness, and ground-to-surface distance, as specifically shown in table 2.
TABLE 2 structural parameters of three-dimensional geometric tunnel model
| Parameters (parameters) | Long cross section | Cross-sectional width | Concrete thickness | Distance to the ground |
| Length (m) | 2.9 | 2.8 | 2.5 | 15 |
In this embodiment, the materials of each layer of the three-dimensional geometric model of the cable can be shown in table 3.
TABLE 3 three-dimensional geometric Cable model Material
Step 102, establishing an electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model of the cable cluster under the material parameters according to the electromagnetic field calculation model, the temperature field calculation model, the fluid field calculation model and the three-dimensional geometric model of the tunnel and the cable, and adding electromagnetic thermal coupling and non-isothermal flow coupling.
In order to realize the coupling effect of the electromagnetic-thermal-flow multi-physical field in the embodiment, electromagnetic thermal coupling between an electromagnetic field and a thermal field and non-isothermal flow coupling between the thermal field and a fluid field are arranged in an electromagnetic-thermal-flow multi-physical field finite element three-dimensional simulation model. When the cable core is charged with load current, the cable core conductor generates joule heat under the action of an alternating magnetic field of the cable core conductor, and meanwhile, the metal sheath also generates electromagnetic loss and eddy current loss, so that the temperature of the cable is increased along with the increase of the load current of the cable core. The temperature of the cable is higher and higher, so that the electromagnetic effect is more obvious, the loss of the cable core and the metal sheath is increased, and the temperature field and the electromagnetic field are mutually coupled. And the inlet is set with a corresponding wind speed value in the turbulence model setting, and the outlet is set to inhibit backflow so as to be equivalent to forced convection in the tunnel.
Illustratively, electromagnetic thermal coupling is a coupling between an electromagnetic field and a thermal field, and non-isothermal flow coupling is a coupling between a thermal field and a fluid field. Specifically, the electromagnetic thermal coupling is:
the non-isothermal flow coupling is:
wherein J is vortex density, and the unit is A/m 2 The method comprises the steps of carrying out a first treatment on the surface of the Sigma is conductivity, sigma 0 The initial conductivity is S/m; alpha is a parameter of the unit and is, Is a set of temperature parameters in degrees celsius. J (J) e Is a vortex density parameter set, and has the unit of A/m 2 ；q v Is a charge, in units of C; ρ is the fluid density in Kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the p is the fluid pressure in N/m 2 The method comprises the steps of carrying out a first treatment on the surface of the u is the fluid velocity in m 3 S; mu is dynamic viscosity, and the unit is Pa.s;The gradient is F, the external force acting on the fluid, and the unit is N.
And 103, setting the environment temperature, wind speed and boundary conditions under the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, applying load current to the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, and setting mesh subdivision parameters for the geometric model to perform mesh subdivision.
Illustratively, "setting the environmental temperature, wind speed, and boundary conditions under the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, and applying the load current to the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model" described in step 103 may include:
applying a periodically varying load current to the cable core; applying a zero potential to the copper shield;
for the upper boundary of the physical model, heat is transferred in a convection heat transfer mode, and the air convection heat transfer coefficient is set to be 10W/(m) for the third type boundary condition of the temperature field 2 K); for the left and right boundaries of the physical model, as the outer boundary is far away from the cable, the insulation position is used as a second class boundary condition, and the heat flux density is 0; setting a preset constant temperature as a first type boundary condition for the lower boundary of the physical model;
setting the ambient temperature to a temperature curve which changes periodically; the wind speed is set to be a step function, and the step function is expressed as a wind speed change and a stable transient model.
Illustratively, "mesh-mesh parameters are set for the geometric model" described in step 103 may include: the model area is divided into two parts of a cable and an external environment for grid subdivision, a denser triangle unit is adopted for the cable part for division, and a sparser triangle and quadrilateral grid is adopted for the external environment for subdivision.
Specifically, the following three boundary conditions can exist in the heat transfer process under the temperature field: (1) The upper boundary of the physical model carries out heat transfer in a convection heat transfer mode, which is a third type of boundary condition, and h=8w/mK; (2) The left and right boundaries of the physical model are far from the cable, so that the insulation treatment can be used as a second type boundary condition, namely wq=0; (3) The lower boundary of the physical model is connected to the soil, and thus a constant value of 20 ℃ is set for the lower boundary as a first type of boundary condition.
Specifically, the electromagnetic field may have the following two boundary conditions in the process of calculating the electromagnetic loss of the power cable: (1) first class boundary conditions: the physical condition on the boundary specifies a value on the boundary of the physical quantity and is equal to the infinity vector magnetic bit 0; (2) a second class of boundary conditions: the physical condition on the boundary specifies that the value of the normal derivative of the physical quantity on the boundary is
In particular, the fluid field has a boundary condition in the operation of the tunnel cable cluster that is, a boundary coupling is a third type of boundary condition
Specifically, the tunnel environment temperature of the finite element simulation model is set, and as shown in fig. 4, the environment temperature can be in [21.5 ℃ -25.8 ℃ ] circulation periodically.
Specifically, an operation load current of a simulation model is set, and the load current changes periodically, and the x-axis is shown in FIG. 5For time, the y-axis is the load, the current coefficient is a, and thus the load current is aI 0 。
In this embodiment, meshing of finite element calculations is indispensable. The quality of mesh dissection greatly influences the accuracy of simulation calculation and the solving time, and the part incapable of mesh dissection in the geometric model can be simplified by removing details, virtual operation or CAD features in the setting process. The free grids are mainly adopted to conduct model grid division, the model area is classified into two types of cables and external environments, the temperature change is relatively rapid for the cable portion, the temperature change is due to the change of physical properties of materials, meanwhile, the calculation of cable loss, circulation and the like is high in precision requirements, therefore, denser triangle unit division is adopted, the external environments comprise air, the cable tunnels are divided by adopting sparse triangles and quadrilateral grids, the calculation efficiency of the whole model is guaranteed, and the model division effect is shown in fig. 6.
In this embodiment, for all grid quality evaluations, 1 represents good quality, 0 represents degraded cell, and quality is poor. As shown in fig. 7, the minimum unit mass and the average unit mass in the model approach to 1, so that the mesh subdivision quality of the model is good, and the calculation accuracy and calculation speed of the model are further ensured.
And 104, performing finite element transient calculation on the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model to obtain cable core temperature data.
The method comprises the steps of carrying out finite element transient calculation on an electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model through a solver, and obtaining a cable core temperature distribution diagram and a cable core temperature curve change diagram of the cable.
In this embodiment, according to the setting of the boundary condition in step 103, the wind speed is subjected to step function processing to ensure the convergence of the model, an electromagnetic-thermal-flow multi-physical field is established, an appropriate solver FGMRES is selected, and transient research is performed to finally obtain a simulation calculation result as shown in fig. 8. One of the loop cables is selected, and the cable core is subjected to temperature curve drawing as shown in fig. 9. In fig. 9, the curve of the band x represents the left-side core temperature, the curve of the band o represents the intermediate core temperature, and the curve of the band delta represents the right-side core temperature.
And 105, training a cable core temperature prediction model based on the cable core temperature data, and predicting the cable temperature based on the trained cable core temperature prediction model.
Exemplary, the "training the cable core temperature prediction model based on the cable core temperature data" described in step 105 may specifically be: deleting incomplete data sets in the cable core temperature data, and dividing the remaining complete data sets into a training set and a verification set; normalizing the training set and the verification set; and training the cable core temperature prediction model by adopting a training set after normalization processing, and verifying the performance of the trained cable core temperature prediction model by adopting a verification set after normalization processing.
For example, according to the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, the cable core temperature condition of the cable running for 5 days is obtained, and the cable core temperature condition is divided into 2800 groups of data. Taking the first 70% of data in the data set, namely 2000 groups of data, as a training set of a cable core temperature prediction model; the last 30% of data, namely 800 sets of data, are used as a verification set of the cable core temperature prediction model. Because the input data quantity of the convolutional neural network can obviously influence the prediction effect of the cable core temperature prediction model, the input data quantity of the convolutional neural network can be selectively increased so as to improve the prediction effect of the cable core temperature of the convolutional neural network. The input/output data of the prediction model is exemplified by an a-phase cable among the three-phase cables, as shown in table 4. A total of 2800 sets of sample data. The input and output structure of the cable core temperature prediction model is shown in fig. 10, k=6 in the cable core temperature prediction model structure, x1 is a time sequence, x2 is an ambient temperature ℃, x3 is a wind speed m/s, x4 is a load current a, x5 is an outer sheath temperature, and x6 is a cable magnetic flux. As an input variable, m=1, represents the core temperature of the predicted cable for the fifth day. The model was trained from the first 70% of sample data and the last 30% of sample data to verify the correctness of the model.
Table 4A phase cable input/output data
Because some data may be unreliable due to problems of boundary condition setting, grid segmentation and the like in the data acquired through the model, and the data is deleted to cause data deletion, a deletion method can be selected for compensating the deleted data.
Most of characteristic dimensions and numerical values in the data set are different, the model can be greatly influenced, even training cannot be completed, therefore, data standardization pretreatment is needed to be carried out on the original data set before the original data set is input into the model, the model training effect can be perfected, and therefore, min-max standardization treatment can be selected.
The cable core temperature prediction model can be a CNN-LSTM model or a CNN-LSTM-Attention model.
The CNN-LSTM model is a model obtained by combining a long-term memory network LSTM with a convolutional neural network CNN. The CNN-LSTM combined model half is a CNN network in which convolutional layers are used to extract features, and the latter half is LSTM predictions used to extract temporal features of the cable data. And finally, combining the LSTM and the convolution layer through a full connection layer, improving the capacity of the LSTM network memory module, avoiding the problem of prediction hysteresis caused by huge data quantity, and finally generating final prediction output through an output layer.
Specifically, the CNN-LSTM cable core temperature prediction result and error based on the three-dimensional finite element method are analyzed as follows:
(1) Prediction error of cable core of A-phase cable and prediction result of cable core of A-phase cable
For a-phase power cables, the performance of the CNN-LSTM model on a-phase cable temperature test set was first evaluated with Root Mean Square Error (RMSE) as an indicator, as shown in fig. 11. The real value and the predicted value are presented in a dot diagram form, the number of error points in the predicted result can be rapidly analyzed, and the temperature prediction Root Mean Square Error (RMSE) of the A-phase power cable is only 0.14 and is close to 0, so that the model has good fitting degree and small error after being verified by a test set. According to the CNN-LSTM prediction model, the obtained A-phase cable temperature prediction result is visually analyzed in the form of a line graph, wherein the broken line represents a true value, and the solid line represents a predicted value, as shown in FIG. 12. The fitting degree of the predicted value and the true value of the A-phase cable core temperature is good, certain deviation exists, the predicted value and the true value show hysteresis in a certain time, and the predicted value curve shows more abrupt in certain turning positions compared with the true value curve on a fitting image. This is because time-series data corresponds to historical data to make future predictions, and hysteresis of the prediction results is unavoidable.
(2) Prediction error of B-phase cable core and prediction result of B-phase cable core
For phase B power cables, the performance of the CNN-LSTM model on the phase a cable temperature test set was also evaluated using Root Mean Square Error (RMSE) as an indicator, as shown in fig. 13. The true value and the predicted value errors are presented in a dot diagram form, and the Root Mean Square Error (RMSE) of the temperature prediction of the B-phase power cable is only 0.168, which shows that the model has good fitting degree through the verification of a test set, and the error is larger than that of the A-phase, but accords with the error standard. According to the CNN-LSTM prediction model, the obtained B-phase cable temperature prediction result is visually analyzed in the form of a line graph, wherein the broken line represents a true value, and the solid line represents a predicted value, as shown in FIG. 14. The predicted value of the B-phase cable core in fig. 14 lags behind the true value and the maximum error is only 1.2 ℃.
(3) C-phase cable core prediction error and C-phase cable core prediction result
For the C-phase power cable, the performance of the CNN-LSTM model on the C-phase cable temperature test set was evaluated using Root Mean Square Error (RMSE) as an indicator, as shown in FIG. 15. And the Root Mean Square Error (RMSE) of the C-phase power cable temperature prediction was 0.139. Compared with phase A, phase C has better fitting degree and smaller error. According to the CNN-LSTM prediction model, the obtained C-phase cable temperature prediction result is visually analyzed in the form of a line graph, wherein the broken line represents a true value, and the solid line represents a predicted value, as shown in FIG. 16. The C-phase cable core in the graph 16 is low in temperature and small in error as the C-phase cable in the input data is positioned at the inner side of the tunnel and is influenced by wind speed and the like, the data characteristic value is more obvious, and therefore the C-phase cable core prediction effect is better.
For the CNN-LSTM cable core temperature prediction model based on the three-dimensional finite element method, the model performance evaluation index can indicate the fitting effect of the model through the determination coefficient (R2) and the Mean Absolute Error (MAE) besides the Root Mean Square Error (RMSE), as shown in table 5. As can be seen from Table 5, the performance evaluation indexes MAE of the three-phase cable prediction model all tend to be 0, and the determination coefficients (R2) all tend to be 1, so that the error of the cable core prediction model of the CNN-LSTM cable is relatively small, and the fitting degree is good.
TABLE 5CNN-LSTM model fitting Effect
| Cable/evaluation index | MAE | R2 |
| A-phase cable | 0.14 | 0.9843 |
| B-phase cable | 0.21 | 0.7714 |
| C-phase cable | 0.13 | 0.9620 |
According to analysis of a CNN-LSTM temperature prediction result of a three-dimensional finite element method, the prediction error of the A phase temperature and the C phase temperature is smaller, but the prediction error of the B phase cable temperature is deficient relative to the other two phases, and the influence of important time steps in the LSTM is smaller, so that the error of the cable core temperature at an inflection point of temperature discount is larger. CNN-LSTM temperature prediction based on three-dimensional finite element method, if the time sequence span is larger and the network is deeper, the problems of large calculated amount, more time consumption and larger error can occur.
In the embodiment, the structure of a CNN-LSTM-Attention cable core temperature prediction model based on a three-dimensional finite element method is shown in fig. 17, CNN extraction characteristics are combined with the capability of LSTM to process long sequences, an Attention mechanism is used for optimization, and the proportion of useful information is increased in a probability distribution weight mode, so that the loss of the useful information is avoided, the dependence of the sequences is discovered, the influence of important time steps in the LSTM is improved, and the cable core temperature prediction error of the cable is further reduced.
The model is divided into 5 layers: an input layer, a CNN layer, an LSTM layer, an attention layer and an output layer.
(1) The first layer is an input layer, and three-phase cable core temperature is used as input data to prescribe a format of the three-phase cable core temperature, such as time steps, characteristic dimensions and the like.
(2) The second layer is a CNN layer, firstly, the data are tiled into one-dimensional data, and on the premise that the characteristics of the data are ensured to have time sequence through CNN, the spatial connection between different characteristic values in the data is extracted.
(3) The third layer is an LSTM layer, the defect that the data space component cannot be acquired by the LSTM layer is overcome through CNN, the LSTM layer has memory, and time sequence change information of nonlinear data of cable core temperature change can be extracted.
(4) The fourth layer is an Attention layer, an Attention mechanism can improve the distribution weight of important time steps in LSTM, and further optimize the cable core temperature prediction result, the essence of the Attention mechanism is that the weighted average sum of LSTM output vectors in the hidden layer is used as the input of the Attention layer, the training is carried out through a fully connected layer, the output of the fully connected layer is normalized by using a softmax function, the distribution weight of each hidden layer vector is obtained, and the weight size represents the importance degree of the hidden state of each time step to the prediction result.
(5) The fifth layer is an output layer and outputs the final cable core temperature prediction result.
Specifically, the CNN-LSTM-Attention cable core temperature prediction result and error analysis based on the three-dimensional finite element method are as follows:
(1) A, C phase cable core prediction result comparison analysis
In the analysis of a loop three-phase cable core prediction model of the CNN-LSTM cable core based on a three-dimensional finite element method, relatively small errors exist in the A phase cable core and the C phase cable core, but a certain error between a true value and a predicted value can be obviously found on a B phase cable core prediction line diagram. The prediction results in the use of the CNN-LSTM-Attention model are thus shown in FIGS. 18, 19 and 20.
As can be seen from fig. 18 and 19, the cable core temperature predicted by CNN-LSTM-attribute is more consistent with the true value than the cable core temperature predicted by CNN-LSTM at the highest point and the lowest point of the cable core predicted by a-phase cable and C-phase cable. The attribute mechanism can improve the distribution weight of important time steps in LSTM, properly make up the error of important nodes and key time steps, and reduce certain hysteresis of the prediction result.
(2) B-phase cable core prediction result comparison analysis
According to the CNN-LSTM-Attention prediction model shown in FIG. 20, the obtained B-phase cable temperature prediction result is visually analyzed in the form of a line graph, and three line graphs, namely a cable core temperature true value, a CNN-LSTM prediction value and a CNN-LSTM-Attention prediction value, can be clearly found in a comparison graph from top to bottom. Therefore, compared with a true value, a predicted value by adopting a CNN-LSTM method has relatively larger error, the predicted temperature of the folding point is improved in a key way through the optimization of an attention mechanism, and meanwhile, the predicted error of the temperature of the whole B-phase cable core is reduced to a certain degree.
Error pairs for the three-dimensional finite element method based CNN-LSTM-Attention cable core temperature prediction and the three-dimensional finite element method based CNN-LSTM cable core temperature prediction are shown in FIG. 21. As can be seen from FIG. 21, the method of optimizing the attention mechanism is adopted, wherein the A phase RMSE is 0.132, the B phase RMSE is 0.145, and the C phase RMSE is 0.128, compared with the CNN-LSTM model, the performance evaluation index is obviously reduced, and the more the performance evaluation index tends to be 0, the smaller the error is, so that the time prediction hysteresis and the weight distribution to the heavy point time steps can be well improved by optimizing the attention mechanism, and the temperature prediction error of the cable core is reduced.
The model performance evaluation index can also indicate the fitting effect of the model by its determination coefficient (R2) and Mean Absolute Error (MAE) in addition to Root Mean Square Error (RMSE), as shown in table 6.
TABLE 6CNN-LSTM-Attention model fitting Effect
| Cable/evaluation index | MAE | R2 |
| A-phase cable | 0.12 | 0.9896 |
| B-phase cable | 0.15 | 0.9642 |
| C-phase cable | 0.11 | 0.9803 |
As can be seen from the performance evaluation index (MAE) and the decision coefficient (R2) of the three-phase cable prediction model in Table 6, the error requirement is met, and the error of the CNN-LSTM-Attention cable core prediction model based on the three-dimensional finite element method is smaller. Compared with the table 5, the addition of the Attention mechanism optimizes the overall error of the cable core ABC three-phase cable, and especially improves the accuracy of the B-phase cable core to the maximum, so that the Attention mechanism better improves the CNN-LSTM cable core prediction model.
According to the cable temperature prediction method, the three-dimensional transient model of electromagnetic-thermal-flow multi-physical field coupling of the tunnel cable cluster is constructed, and compared with a two-dimensional model, the model can simulate and analyze the actual running condition of the tunnel cable cluster; the operation condition of the cable is simulated more closely through electromagnetic thermal coupling and non-isothermal flow coupling, so that the prediction result is more fit and practical. The three-dimensional transient model is combined with the CNN-LSTM-Attention algorithm, and a new effective thought is provided for predicting the temperature of the cable core. Compared with detection and monitoring of optical fiber cables, the method is low in cost and wide in application range.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
Corresponding to the cable temperature prediction method described in the above embodiments, fig. 22 shows a block diagram of a cable temperature prediction apparatus according to an embodiment of the present application, and for convenience of explanation, only the portions related to the embodiment of the present application are shown.
Referring to fig. 22, the cable temperature prediction apparatus in an embodiment of the present application may include a first model building module 201, a second model building module 202, a setting dividing module 203, a data acquisition module 204, and a training prediction module 205.
The first model building module 201 is configured to build an electromagnetic field calculation model, a temperature field calculation model, a fluid field calculation model, and a three-dimensional geometric model of a tunnel and a cable, where the three-dimensional geometric model includes structural parameters and material parameters of each layer of the cable.
The second model building module 202 is configured to build an electromagnetic-thermal-flow multi-physical-field finite element simulation three-dimensional model of the cable cluster under the material parameters according to the electromagnetic field calculation model, the temperature field calculation model, the fluid field calculation model and the three-dimensional geometric model of the tunnel and the cable, and add electromagnetic thermal coupling and non-isothermal flow coupling.
The setting and dividing module 203 is configured to set an environmental temperature, a wind speed and a boundary condition under the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, apply a load current to the electromagnetic-thermal-flow multi-physical field finite element simulation three-dimensional model, and set mesh parameters to the geometric model for mesh division.
The data acquisition module 204 is configured to perform finite element transient calculation on the electromagnetic-thermal-flow multi-physical field finite element simulation model, and acquire cable core temperature data.
The training prediction module 205 is configured to train a cable core temperature prediction model based on the cable core temperature data, and predict a cable temperature based on the trained cable core temperature prediction model.
Optionally, the expression of the electromagnetic field calculation model is:
wherein J is e And J s Is the source variable, which is the vortex density and the current density, respectively, and the unit is A/m 2 The method comprises the steps of carrying out a first treatment on the surface of the H is the magnetic field intensity, unit A/m; b is magnetic induction intensity, and the unit is T; d is an electric displacement vector;
the temperature field calculation model expression is as follows:
wherein phi is in Indicating the amount of heat flowing into a particular micro-element; phi out Indicating the amount of heat flowing out of a particular micro-element; q represents the internal heat of the micro-element body; c represents the constant pressure heat capacity of the gas, and the unit is J/(kg.K); ρ is the density of air in kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the λ represents the thermal conductivity of the gas in W/(mK);
the fluid field calculation model expression is:ρ is the density of air in kg/m 3 ，c P Representing the constant pressure heat capacity of gas, wherein the unit is J/(kg.K); λ represents the thermal conductivity of the gas in W/(mK); u is a velocity component in the x-axis direction in m/s; v is the velocity component in the y-axis direction in m/s; w is a velocity component in the z-axis direction in m/s;
the geometric model of the cable is a three-dimensional geometric model constructed according to a cable core, an insulating layer of the cable, a buffer layer of the cable, a metal sheath layer of the cable and an outer sheath layer of the cable, the structural parameters comprise thickness and outer diameter, and the material parameters comprise heat conductivity coefficient, constant pressure heat capacity, density, relative dielectric parameters, relative magnetic conductivity and electric conductivity.
Optionally, the electromagnetic thermal coupling is a coupling between an electromagnetic field and a thermal field, and the non-isothermal fluid coupling is a coupling between a thermal field and a fluid field;
the electromagnetic thermal coupling is as follows:
the non-isothermal flow coupling is:
wherein J is vortex density, and the unit is A/m 2 The method comprises the steps of carrying out a first treatment on the surface of the Sigma is conductivity, sigma 0 The initial conductivity is S/m; alpha is a parameter of the unit and is,is a set of temperature parameters in degrees celsius. J (J) e Vortex density parameter set, unit is A/m 2 ；q v Is a charge, in units of C; ρ is the fluid density in Kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the p is the fluid pressure in N/m 2 The method comprises the steps of carrying out a first treatment on the surface of the u is the fluid velocity in m 3 S; mu is dynamic viscosity, and the unit is Pa.s;The gradient is F, the external force acting on the fluid, and the unit is N.
Optionally, the setting dividing module 203 may specifically be configured to:
applying a periodically varying load current to the cable core;
applying a zero potential to the copper shield;
for the upper boundary of the physical model, heat is transferred in a convection heat transfer mode, and the air convection heat transfer coefficient is set to be 10W/(m) for the third type boundary condition of the temperature field 2 K); for the left and right boundaries of the physical model, as the outer boundary is far away from the cable, the insulation position is used as a second class boundary condition, and the heat flux density is 0; setting a preset constant temperature as a first type boundary condition for the lower boundary of the physical model;
setting the ambient temperature to a temperature curve which changes periodically;
the wind speed is set to be a step function, and the step function is expressed as a wind speed change and a stable transient model.
Optionally, the setting dividing module 203 may specifically be configured to:
the model area is divided into two parts of a cable and an external environment for grid subdivision, a denser triangle unit is adopted for the cable part for division, and a sparser triangle and quadrilateral grid is adopted for the external environment for subdivision.
Alternatively, the training prediction module 205 may specifically be configured to:
deleting incomplete data sets in the cable core temperature data, and dividing the remaining complete data sets into a training set and a verification set;
normalizing the training set and the verification set;
and training the cable core temperature prediction model by adopting a training set after normalization processing, and verifying the performance of the trained cable core temperature prediction model by adopting a verification set after normalization processing.
The cable core temperature prediction model is a CNN-LSTM-Attention model.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The embodiment of the present application further provides a terminal device, referring to fig. 23, the terminal device 300 may include: at least one processor 310 and a memory 320, said memory 320 having stored therein a computer program executable on said at least one processor 310, said processor 310 implementing steps in any of the various method embodiments described above, such as steps 101 to 105 in the embodiment shown in fig. 1, when said computer program is executed. Alternatively, the processor 310 may implement the functions of the modules/units in the above-described embodiments of the apparatus, such as the functions of the modules 201 to 205 shown in fig. 22, when executing the computer program.
By way of example, a computer program may be partitioned into one or more modules/units that are stored in memory 320 and executed by processor 310 to perform the present application. The one or more modules/units may be a series of computer program segments capable of performing specific functions for describing the execution of the computer program in the terminal device 300.
It will be appreciated by those skilled in the art that fig. 23 is merely an example of a terminal device and is not limiting of the terminal device, and may include more or fewer components than shown, or may combine certain components, or different components, such as input-output devices, network access devices, buses, etc.
The processor 310 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 320 may be an internal storage unit of the terminal device, or may be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), or the like. The memory 320 is used for storing the computer program and other programs and data required by the terminal device. The memory 320 may also be used to temporarily store data that has been output or is to be output.
The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or to one type of bus.
Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements steps for implementing the embodiments of the cable temperature prediction method described above.
Embodiments of the present application provide a computer program product which, when run on a mobile terminal, causes the mobile terminal to perform steps that enable the various embodiments of the cable temperature prediction method described above to be implemented.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310757054.1A CN116911107A (en) | 2023-06-26 | 2023-06-26 | Cable temperature prediction method, device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310757054.1A CN116911107A (en) | 2023-06-26 | 2023-06-26 | Cable temperature prediction method, device and terminal equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911107A true CN116911107A (en) | 2023-10-20 |
Family
ID=88350245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310757054.1A Pending CN116911107A (en) | 2023-06-26 | 2023-06-26 | Cable temperature prediction method, device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911107A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118408646A (en) * | 2024-07-02 | 2024-07-30 | 国网山东省电力公司邹城市供电公司 | A method and system for early warning of abnormal temperature of power cable joints |
| CN118586250A (en) * | 2024-08-06 | 2024-09-03 | 河北科技大学 | Direct buried cable core temperature prediction method, device, terminal and storage medium |
| CN119090136A (en) * | 2024-08-19 | 2024-12-06 | 北京天泰志远科技股份有限公司 | A data-driven equipment technical status evaluation method and system |
| CN119378306A (en) * | 2024-10-11 | 2025-01-28 | 国网四川省电力公司电力科学研究院 | High voltage cable defect identification method and system based on cross-connected ground loop current |
| CN119720688A (en) * | 2025-02-26 | 2025-03-28 | 河北科技大学 | Cable bridge laying cable temperature prediction method, device, terminal and storage medium |
| CN120610103A (en) * | 2025-06-09 | 2025-09-09 | 南方电网能源发展研究院有限责任公司 | Dynamic intelligent monitoring system of cable group current carrying capacity based on multi-dimensional information |
-
2023
- 2023-06-26 CN CN202310757054.1A patent/CN116911107A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118408646A (en) * | 2024-07-02 | 2024-07-30 | 国网山东省电力公司邹城市供电公司 | A method and system for early warning of abnormal temperature of power cable joints |
| CN118586250A (en) * | 2024-08-06 | 2024-09-03 | 河北科技大学 | Direct buried cable core temperature prediction method, device, terminal and storage medium |
| CN118586250B (en) * | 2024-08-06 | 2024-12-06 | 河北科技大学 | Method, device, terminal and storage medium for predicting temperature of cable core of buried cable |
| CN119090136A (en) * | 2024-08-19 | 2024-12-06 | 北京天泰志远科技股份有限公司 | A data-driven equipment technical status evaluation method and system |
| CN119378306A (en) * | 2024-10-11 | 2025-01-28 | 国网四川省电力公司电力科学研究院 | High voltage cable defect identification method and system based on cross-connected ground loop current |
| CN119378306B (en) * | 2024-10-11 | 2025-06-24 | 国网四川省电力公司电力科学研究院 | High-voltage cable defect identification method and system based on cross-connection grounding circulation |
| CN119720688A (en) * | 2025-02-26 | 2025-03-28 | 河北科技大学 | Cable bridge laying cable temperature prediction method, device, terminal and storage medium |
| CN120610103A (en) * | 2025-06-09 | 2025-09-09 | 南方电网能源发展研究院有限责任公司 | Dynamic intelligent monitoring system of cable group current carrying capacity based on multi-dimensional information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116911107A (en) | Cable temperature prediction method, device and terminal equipment | |
| CN110083908B (en) | Prediction method of cable core temperature based on finite element analysis | |
| CN118586250B (en) | Method, device, terminal and storage medium for predicting temperature of cable core of buried cable | |
| Pareek et al. | A framework for analytical power flow solution using gaussian process learning | |
| Xiao et al. | Non‐contact voltage measurement of three‐phase overhead transmission line based on electric field inverse calculation | |
| CN116359653A (en) | Method, device, computer equipment and storage medium for determining cable ampacity | |
| Han et al. | Multi‐objective robust dynamic VAR planning in power transmission girds for improving short‐term voltage stability under uncertainties | |
| CN118260990A (en) | Cable core temperature prediction method and system based on finite element method | |
| CN119494177A (en) | Modeling and analysis method and device for thermal circuit fault in intermediate connection of high voltage power cable | |
| CN118504388A (en) | Transformer time-harmonic magnetic field determining method, device, electronic equipment and storage medium | |
| CN106934096B (en) | A method for calculating the temperature of the steel core based on the surface temperature of the overhead conductor | |
| CN115659818A (en) | Power cable conductor temperature prediction method and device | |
| CN119720688A (en) | Cable bridge laying cable temperature prediction method, device, terminal and storage medium | |
| CN119129201A (en) | A switch cabinet partial discharge simulation method and system | |
| CN118643697A (en) | Method and device for electromagnetic thermal coupling analysis of key components in converter station valve hall | |
| CN113868916B (en) | LFVPSO-BPNN-based multi-loop groove cabling temperature rise prediction method | |
| Huang et al. | Modular digital twin modelling method for 10 kV cable lines based on real‐time temperature field inversion | |
| Ding et al. | Research on digital twin diagnosis model for the thermal-electric field of high-voltage switchgears | |
| Asadpourahmadchali et al. | Hybrid continuous circuit‐trapezoidal integration method analysis of multi‐cross structure of grounding system | |
| Zeng et al. | Load component decomposition and online modelling based on small disturbance response characteristic matching | |
| Freschi et al. | Mixed-dimensional elements in transient thermal analysis of gradient coils | |
| Yuan et al. | Research on Hot Spot Temperature Inversion Method of Cable Intermediate Joints Based on Finite Element and Optimized BP Neural Network Method | |
| CN120278044B (en) | Quick calculation method and related device for heat flow coupling field of power equipment | |
| Bao et al. | Prediction of bundle-conductor ampacity based on transformer-LSTM | |
| CN119989578B (en) | Compressor blade shape generation method, device, equipment, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |