CN113935238A - Insulation aging degree evaluation method based on cable joint surface temperature - Google Patents
Insulation aging degree evaluation method based on cable joint surface temperature Download PDFInfo
- Publication number
- CN113935238A CN113935238A CN202111192644.1A CN202111192644A CN113935238A CN 113935238 A CN113935238 A CN 113935238A CN 202111192644 A CN202111192644 A CN 202111192644A CN 113935238 A CN113935238 A CN 113935238A
- Authority
- CN
- China
- Prior art keywords
- cable joint
- model
- temperature
- surface temperature
- insulation
- 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
- 238000009413 insulation Methods 0.000 title claims abstract description 39
- 230000032683 aging Effects 0.000 title claims abstract description 22
- 238000011156 evaluation Methods 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 230000008878 coupling Effects 0.000 claims abstract description 11
- 238000010168 coupling process Methods 0.000 claims abstract description 11
- 238000005859 coupling reaction Methods 0.000 claims abstract description 11
- 238000004088 simulation Methods 0.000 claims abstract description 11
- 230000007613 environmental effect Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 18
- 238000012546 transfer Methods 0.000 claims description 16
- 230000015556 catabolic process Effects 0.000 claims description 14
- 238000006731 degradation reaction Methods 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 9
- 239000012530 fluid Substances 0.000 claims description 8
- 230000005855 radiation Effects 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims description 8
- 238000005094 computer simulation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000005672 electromagnetic field Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000008689 nuclear function Effects 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000035699 permeability Effects 0.000 claims description 3
- 229920002379 silicone rubber Polymers 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000006866 deterioration Effects 0.000 claims 4
- 150000001875 compounds Chemical class 0.000 claims 1
- 238000012795 verification Methods 0.000 abstract description 3
- 239000004020 conductor Substances 0.000 description 16
- 238000004458 analytical method Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000002500 effect on skin Effects 0.000 description 1
- 238000010291 electrical method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000004945 silicone rubber Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention discloses an insulation aging degree evaluation method based on the surface temperature of a cable joint. And then, acquiring the surface temperature distribution simulation data of the cable joint under different operating conditions by using a coupling calculation model. And finally, constructing a training set, a verification set and a test set by using the simulation data, and constructing a state prediction model by adopting a kernel-based extreme machine (KELM) algorithm. The prediction model can rapidly and accurately judge the insulation aging degree of the cable joint according to the data of the operating current, the environmental temperature and the surface temperature.
Description
Technical Field
The invention belongs to the field of power systems, and particularly relates to an insulation aging degree evaluation method based on the surface temperature of a cable joint.
Background
The cable joint is an important device for connecting power cables, and the failure probability of the cable joint is high in a cable system, so that the power supply reliability is seriously deteriorated. The problem of insulation failure of cable joints is particularly prominent, and the insulation state is closely related to the service life. In order to maintain the stable operation of the power grid, it is significant to accurately evaluate the degradation degree of the insulation performance of the cable joint and take corresponding measures.
At present, most of insulation performance monitoring methods of cable joints are electrical measurement methods. The methods identify the type and degree of the insulation defect by identifying state information such as partial discharge signals, dielectric loss factors and the like. In addition to electrical measurement methods, temperature monitoring can also be used to reflect the insulation state. The temperature method has the advantage of easy measurement, and can be used for identifying air gap defects, conductor eccentricity, contact resistance of connecting tubes and other problems. However, the temperature method is susceptible to interference from external factors, such as ambient temperature and humidity, solar radiation, etc., resulting in limited accuracy of analysis. Meanwhile, a method for diagnosing the insulation degradation degree of a cable joint based on a temperature mode is not yet mature and needs to be further researched. Therefore, the analysis of the temperature representation of the degradation degree of the insulation performance of the cable joint under the complex operation condition has a significant meaning when a corresponding evaluation method is provided.
Disclosure of Invention
The invention aims to provide an insulation aging degree evaluation method based on the surface temperature of a cable joint. Firstly, an electromagnetic-thermal coupling calculation model of the cable joint is constructed, wherein the electromagnetic-thermal coupling calculation model is characterized by operating current, ambient temperature and aging degree. And then, acquiring the surface temperature distribution simulation data of the cable joint under different operating conditions by using a coupling calculation model. And finally, constructing a training set, a verification set and a test set by using the simulation data, and constructing a state prediction model by adopting a kernel-based extreme machine (KELM) algorithm. The prediction model can rapidly and accurately judge the insulation aging degree of the cable joint according to the data of the operating current, the environmental temperature and the surface temperature.
Therefore, the technical scheme adopted by the invention is that the method for evaluating the insulation aging degree based on the surface temperature of the cable joint comprises the following steps:
(1) constructing an electro-thermal coupling calculation model taking account of insulation aging
The electromagnetic field control equation is:
where μ is magnetic permeability, J is current density, and σ is electric conductivity ρeIs a bulk charge density, and ε is a mediumAn electrical constant,. is a differential operator.
The temperature and heat control equation is expressed as:
wherein ρ represents a density of a substance, cpRepresents the constant pressure heat capacity of the substance, and lambda represents the heat conductivity coefficient of the substance; q (T) represents the heat per unit volume generated by the heat source, and T represents the temperature.
(2) Setting boundary conditions of a computational model
Setting the magnetic vector potential and the electric potential at the electromagnetic boundary to be 0;
the thermal boundary conditions of the computational model are determined by thermal conductivity boundary conditions and satisfy the following formula:
n·(-λ▽T)=(hrad+hcon)(T-Te)
in the formula, TeTo actually measure the ambient temperature, hconIs a natural convection heat transfer coefficient, hradFor the heat radiation convection heat transfer coefficient, n represents the boundary normal vector.
(3) Obtaining the simulation data of the surface temperature distribution of the cable joint under different operating conditions
And according to the actual operation condition of the cable joint, performing three-dimensional parametric scanning on the operation current, the environment temperature and the dielectric loss angle by using a coupling calculation model to obtain surface temperature distribution so as to establish a database sample.
(4) And constructing an insulation degradation degree prediction model, and predicting the insulation degradation degree by using a nuclear-limit-machine-based method.
Further, the heat radiation convection heat transfer coefficient hradIs composed of
hrad=εδ(T2+Te 2)(T+Te)
Wherein, delta is Stefan-Boltzmann constant, epsilon is surface emissivity, TeThe measured ambient temperature is used as the measured ambient temperature;
natural convection heat transfer coefficient hconAnd analyzing by adopting a natural convection heat transfer coefficient experiment correlation formula:
Nu=C(Gr·Pr)n
where Nu is the Nu is the Nu is the characteristic length of the fluid outer boundary, Gr is the Gr-Davenov number, Pr is the Prnst number, the coefficient C and the index n are empirical constants, avThe volume expansion coefficient of the fluid, delta T is the temperature difference between the fluid temperature and the environment wall surface, v is kinematic viscosity, and g represents the gravity coefficient.
Further, the tangent value tan delta of the dielectric loss angle in the step (3) has a corresponding relation with the dielectric conductivity RD and the aging degree of the silicon rubber:
RD=tanδ·wCc
in the formula, CcIs the cable joint equivalent capacitance, w is the angular frequency.
Further, the step (4) specifically includes:
firstly, selecting data in a database sample to construct a training set and a testing set, taking the distribution of environmental temperature, operating current and surface temperature as input variables of a model, taking a dielectric loss angle as an output variable of the model, respectively carrying out normalization processing on the training set and the testing set, and then carrying out phase space reconstruction on the data after the normalization processing;
secondly, establishing an extreme learning machine algorithm model of a kernel function; comprises that
The kernel function is the radial basis function:
where η is a parameter of the radial basis function, xiRepresenting sample input, yiRepresenting sample output
The output of the extreme learning machine algorithm model is obtained as follows:
in the formula, Y represents expected output, E is an identity matrix, C represents a normalization coefficient, Y (x) represents test set output, N represents the number of training set samples, and K (x, x)i) Representing the kernel function χelmRepresenting a radial function.
And thirdly, setting parameter ranges of punishment parameters and nuclear parameters, training a model by using an extreme learning machine algorithm, optimizing regularization coefficients and nuclear function parameters by using a particle swarm optimization, determining model parameters of an optimal prediction model, and finally predicting a test set sample by using the model.
By adopting the technical scheme, the invention has the following advantages and beneficial effects:
the invention develops the operation temperature analysis of the cable joint considering the insulation aging degree. And (3) considering the influences of factors such as load current, environment temperature, insulation aging degree and the like, and obtaining the distribution simulation data of the surface temperature by applying a cable joint electromagnetic-thermal coupling analysis model. Meanwhile, a training set, a verification set and a test set are constructed by using simulation data, the insulation degradation degree of the cable joint is predicted by adopting a kernel limit machine (KELM) method, and the internal state of the cable joint can be rapidly identified according to the surface temperature.
Compared with an electrical method, the temperature method has the advantages of simple field data acquisition, low implementation cost and the like; the axial temperature distribution of the cable joint under different aging degrees is obtained by adopting a numerical analysis method based on electro-thermal coupling, and the temperature rise trend caused by the aging degrees is easy to find; the simulation data is used as an analysis training set, so that the method has the advantages of sufficient data volume and more accurate state analysis; the extreme learning machine (KELM) with strong generalization ability is used as a training and predicting model, so that the insulation degradation degree of the cable joint can be effectively predicted through temperature measurement under the conditions of less training sample data and more influence factors. The method is simple and practical, has feasibility, accuracy and applicability, and can be widely applied.
Drawings
FIG. 1 shows a cable joint temperature field distribution at an ambient temperature of 298.15K, an operating current of 900A, and a dielectric loss angle of 0.04;
FIG. 2 shows the temperature field distribution of the cable joint at an ambient temperature of 298.15K, an operating current of 900A and a dielectric loss angle of 0.002;
FIG. 3 shows the temperature distribution curves of the cable joint surface under different dielectric loss angles at an ambient temperature of 288.15K and a load current of 500A;
FIG. 4 shows the temperature distribution curves of the cable joint surface under different dielectric loss angles at an ambient temperature of 288.15K and a load current of 500A;
FIG. 5 shows the temperature distribution curve of the cable joint surface under different dielectric loss angles at an ambient temperature of 298.15K and a load current of 500A;
FIG. 6 is based on a KELM cable joint insulation degradation state prediction model;
FIG. 7 Cable joint insulation degradation diagnostic prediction based on the KELM method.
Detailed Description
The invention provides an insulation aging degree evaluation method based on the surface temperature of a cable joint, which is realized by adopting the following steps:
(1) electro-thermal coupling calculation model for setting and insulation aging
The following basic hypothesis conditions were followed: neglecting structures with little influence on physical field analysis, such as a joint grounding column, a heat shrinkable tube, a sealing ring, a semiconductor shielding layer and the like; except the conductivity of the copper material, all other constituent materials are regarded as isotropic uniform media and physical parameters are constants; the connecting tube and the conductor are combined into one element and the resistance thereof is regarded as a uniform resistance. And the coupling effect of the physical field is fully considered, the interference of a boundary layer on the calculation of the physical field is avoided, and a space of 0.5m by 7.0m is selected as a solution domain by taking the connecting pipe of the intermediate joint as the center.
High-voltage cable joint conductor flow crossCurrent flow, skin effect is present. The insulating medium presents an electric field distribution due to the conductor voltage. Introducing magnetic vector potential A and electric potential according to Maxwell equation setObtaining an electromagnetic field control equation:
wherein, mu is magnetic permeability H/m; j is the current density, A/m2(ii) a Sigma is the conductivity, S/m; rhoeIs the bulk charge density, C/m3(ii) a ε represents a dielectric constant, F/m. ^ is a differential operator.
Cable joints typically operate in a cross-connect, mid-point ground, or the like. The heat loss of the cable joint and the sheath of the cable body is very small. The heat source of the cable joint mainly comprises conductor loss and dielectric loss. Wherein, the conductor loss is generated by alternating current flowing through the conductor; dielectric losses are due to hysteresis effects of the dielectric conductance and polarization of the medium under the influence of the electric field.
Q(T)=|J|2/σ(T)
Wherein Q is the heat per unit volume generated by the heat source, W/m3。
Since the electrical conductivity of the cable joint conductor is a temperature-dependent function, a change in the temperature field will result in a change in the electrical conductivity and thus in a change in the conductor loss. Therefore, the conductivity of the conductor is calculated as follows
In the formula, σ293.15A conductor conductivity of 5.45e7S/m at 293.15K; alpha is the temperature coefficient of the conductor 0.00395; t is the temperature, K.
The cable joint laid in the underground working well has the advantages that the heat inside the cable joint flows in a heat conduction mode, and the cable joint and the surrounding environment exchange heat mainly in a natural convection mode and a heat radiation mode. According to the law of conservation of energy, the governing equation can be expressed as:
in the formula, rho represents the density of the material, kg/m3;cpRepresents the constant pressure heat capacity of the substance, J/kg.K; and lambda represents the thermal conductivity of the substance, W/(m.K).
(2) Setting boundary conditions of a computational model
The conductor is loaded with a load current and an operating voltage. The magnetic vector is highest in amplitude at the metal conductor, and rapidly decays towards 0 in the external space. The potential has the highest amplitude at the metal conductor and is attenuated to 0 at the shielding layer and the aluminum sheath. The magnetic vector potential and the electric potential at the electromagnetic boundary are set to 0.
The thermal boundary conditions of the computational model are determined by the thermal conductivity boundary conditions and satisfy the following equation.
n·(-λ▽T)=(hrad+hcon)(T-Te)
In the formula, TeMeasured ambient temperature, K; h isconIs the natural convection heat transfer coefficient, W/(m)2·K);hradIs the heat radiation convection heat transfer coefficient, W/(m)2K). n denotes a boundary normal vector.
Heat radiation convection heat transfer coefficient hradIs arranged as
hrad=εδ(T2+Te 2)(T+Te)
Wherein δ is Stefan-Boltzmann constant, and is 5.67 × 10-8W/(m2·K4) (ii) a ε is the surface emissivity and is taken to be 0.9.
Natural convection heat transfer coefficient hconThe analysis can be carried out by adopting a natural convection heat transfer coefficient experiment correlation.
Nu=C(Gr·Pr)n
Wherein Nu is Nu; l is the characteristic length of the fluid outer boundary; gr is Gr Grax Xiaofu number; pr is the Plantt number; the coefficient C and the index n are empirical constants; a isvIs the coefficient of volume expansion, K, of the fluid-1(ii) a l is the characteristic length, m; delta T is the temperature difference between the fluid temperature and the environmental wall surface, K; v is kinematic viscosity, m2/s。
(3) Obtaining the simulation data of the surface temperature distribution of the cable joint under different operating conditions
On the basis of the calculation models in the steps 1 and 2, the calculation model aims at 110kV and 630mm2And constructing a physical field simulation model by the cable and the joint thereof. The geometry, thermal conductivity and electrical conductivity parameters of the cable and its joint are shown in table 1. Wherein the conductor conductivity gives a calculated function with respect to temperature; the electrical conductivity RD of the silicone rubber medium has a corresponding relation with the dielectric loss tangent value tan delta and the aging degree. The calculated heat transfer coefficient of the surface of the cable joint is 6.0W/(m)2·K)。
RD=tanδ·wCc
In the formula, CcEquivalent capacitance of cable joint, 1.06 uF; w is the angular frequency, rad/s.
TABLE 1 intermediate joint material parameter table (293.15K)
And (3) carrying out three-dimensional parametric scanning on the load current, the ambient temperature and the dielectric loss angle by using Commol Multiphysics to obtain surface temperature distribution so as to establish a database sample. The operation load current is set between 500 and 1100A, and parametric scanning is carried out at intervals of 50A. The ambient temperature was set between 278.15-308.15K and the parametric scan was performed at 2.5K intervals. The dielectric loss angle settings were parameterised scanned at 0,0.001,0.002, 0.005,0.01,0.015,0.02,0.025,0.03,0.035,0.04,0.045,0.05,0.055,0.056,0.06, 0.065,0.07,0.075,0.08, respectively. Data relating to cable joints and operating current, ambient temperature, surface temperature, and insulation degradation were obtained in 3211 sets. Wherein, the surface temperature takes the surface temperature corresponding to the position of the cable joint connecting pipe as a reference. Wherein, the environmental temperature is 298.15K, the operating current is 900A, the temperature field distribution of the cable joint under different dielectric loss angles is shown in fig. 1 and fig. 2, and the surface temperature distribution curve of the cable joint under different dielectric loss angles is shown in fig. 3-5.
(4) Insulation degradation degree prediction model construction
In the first step, 3111 groups are randomly selected as a training set, the other 100 groups are used as a test set, the distribution of the environment temperature, the running current and the surface temperature is used as input variables of a model, the degradation degree (dielectric loss angle) of the cable joint insulation is used as an output variable of the model, and after the training set and the test set are respectively subjected to normalization processing, phase space reconstruction is performed on sample data.
And secondly, establishing an extreme learning machine algorithm model of the kernel function. Given a training sample (x)i,yi) Where 1 ≦ i ≦ 3211, sample input xi=[xi1,xi1,···,xin]Sample output yi=[yi1,yi1,···,yim]. Setting the kernel function to a Radial Basis Function (RBF):
where η is a parameter of the radial basis function, h (x)i),h(xj),K(xi,xj) Is a kernel function.
The output of the KELM is obtained as:
in the formula, Y represents a desired output, E is an identity matrix, and C represents a normalization coefficient. Y (x) represents the output of the test set, and N represents the number of samples in the training set.
And thirdly, setting parameter ranges of punishment parameters and nuclear parameters, optimizing normalization coefficients and nuclear function parameters by using an algorithm training model and adopting a particle swarm algorithm, determining model parameters of an optimal prediction model, and finally predicting a test set sample by using the model. As shown in fig. 6.
(5) Predictive effect validation
Comparing the test sample with the prediction result, calculating three performance indexes of Mean Square Error (MSE), Mean Absolute Error (MAE) and fitting coefficient R2 of the prediction result and the actual result, and evaluating the prediction effect, wherein the MSE and the MAE reflect the prediction accuracy from respective angles, and the smaller the value is, the higher the accuracy is; r2 represents the fitness of the algorithmic model to the actual value, with higher values indicating higher fitness. The effectiveness of the insulation aging degree evaluation method based on the surface temperature of the cable joint was evaluated according to the above indexes.
Calculation of prediction result index: MSE 9.04 × 10-6,MAE=0.0025,R20.9833, the model has good prediction precision and can meet engineering application. As shown in fig. 7.
Claims (5)
1. An insulation aging degree evaluation method based on cable joint surface temperature is characterized in that: the method comprises the following steps:
(1) constructing an electro-thermal coupling calculation model taking account of insulation aging
The electromagnetic field control equation is:
where μ is magnetic permeability, J is current density, and σ is electric conductivity ρeIs the bulk charge density, ε is the dielectric constant,is a differential operator;
the temperature and heat control equation is expressed as:
wherein ρ represents a density of a substance, cpRepresents the constant pressure heat capacity of the substance, and lambda represents the heat conductivity coefficient of the substance; q (T) represents the heat per unit volume generated by the heat source, and T represents the temperature;
(2) setting boundary conditions of a computational model
Setting the magnetic vector potential and the electric potential at the electromagnetic boundary to be 0;
the thermal boundary conditions of the computational model are determined by thermal conductivity boundary conditions and satisfy the following formula:
in the formula, TeTo actually measure the ambient temperature, hconIs a natural convection heat transfer coefficient, hradThe heat radiation convection heat transfer coefficient is shown, and n represents a boundary normal vector;
(3) obtaining the simulation data of the surface temperature distribution of the cable joint under different operating conditions
According to the actual operation condition of the cable joint, a coupling calculation model is applied to carry out three-dimensional parametric scanning on the operation current, the environment temperature and the dielectric loss angle to obtain surface temperature distribution so as to establish a database sample;
(4) and constructing an insulation degradation degree prediction model, and predicting the insulation degradation degree by using a nuclear-limit-machine-based method.
2. The method for evaluating the degree of insulation deterioration based on the surface temperature of a cable joint according to claim 1, wherein: heat radiation convection heat transfer coefficient hradIs composed of
Wherein, delta is Stefan-Boltzmann constant, epsilon is surface emissivity, TeThe measured ambient temperature is used as the measured ambient temperature;
natural convection heat transfer coefficient hconAnd analyzing by adopting a natural convection heat transfer coefficient experiment correlation formula:
Nu=C(Gr·Pr)n
in the formula (I), the compound is shown in the specification,nu is Nu, l is the characteristic length of the fluid outer boundary, Gr is Gr-dawn, Pr is Prandtl, the coefficient C and the index n are empirical constants, avThe volume expansion coefficient of the fluid, delta T is the temperature difference between the fluid temperature and the environment wall surface, v is kinematic viscosity, and g represents the gravity coefficient.
3. The method for evaluating the degree of insulation deterioration based on the surface temperature of a cable joint according to claim 1, wherein: the tangent value tan delta of the dielectric loss angle has a corresponding relation with the dielectric conductivity RD and the aging degree of the silicon rubber:
RD=tanδ·wCc
in the formula, CcIs the cable joint equivalent capacitance, w is the angular frequency.
4. The method for evaluating the degree of insulation deterioration based on the surface temperature of a cable joint according to claim 1, wherein: the step (4) specifically comprises:
firstly, selecting data in a database sample to construct a training set and a testing set, taking the distribution of environmental temperature, operating current and surface temperature as input variables of a model, taking a dielectric loss angle as an output variable of the model, respectively carrying out normalization processing on the training set and the testing set, and then carrying out phase space reconstruction on the data after the normalization processing;
secondly, establishing an extreme learning machine algorithm model of a kernel function;
and thirdly, setting parameter ranges of punishment parameters and nuclear parameters, training a model by using an extreme learning machine algorithm, optimizing regularization coefficients and nuclear function parameters by using a particle swarm optimization, determining model parameters of an optimal prediction model, and finally predicting a test set sample by using the model.
5. The method for evaluating the degree of insulation deterioration based on the surface temperature of a cable joint according to claim 4, wherein: the extreme learning machine algorithm model for establishing the kernel function comprises
The kernel function is the radial basis function:
where η is a parameter of the radial basis function, xiRepresenting sample input, yiRepresenting sample output
The output of the extreme learning machine algorithm model is obtained as follows:
in the formula, Y represents expected output, E is an identity matrix, C represents a normalization coefficient, Y (x) represents test set output, N represents the number of training set samples, and K (x, x)i) Representing a kernel function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111192644.1A CN113935238A (en) | 2021-10-13 | 2021-10-13 | Insulation aging degree evaluation method based on cable joint surface temperature |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111192644.1A CN113935238A (en) | 2021-10-13 | 2021-10-13 | Insulation aging degree evaluation method based on cable joint surface temperature |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113935238A true CN113935238A (en) | 2022-01-14 |
Family
ID=79278812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111192644.1A Pending CN113935238A (en) | 2021-10-13 | 2021-10-13 | Insulation aging degree evaluation method based on cable joint surface temperature |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113935238A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114543896A (en) * | 2022-03-23 | 2022-05-27 | 成都高斯电子技术有限公司 | Capacitive equipment medium water content and aging evaluation method based on temperature drift electrical parameters |
CN116911068A (en) * | 2023-09-06 | 2023-10-20 | 成都汉度科技有限公司 | Method and system for predicting effective life of cable joint |
CN118067201A (en) * | 2024-04-17 | 2024-05-24 | 四川赛康智能科技股份有限公司 | Full life cycle monitoring method and system for explosion-proof box |
-
2021
- 2021-10-13 CN CN202111192644.1A patent/CN113935238A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114543896A (en) * | 2022-03-23 | 2022-05-27 | 成都高斯电子技术有限公司 | Capacitive equipment medium water content and aging evaluation method based on temperature drift electrical parameters |
CN114543896B (en) * | 2022-03-23 | 2024-05-10 | 成都高斯电子技术有限公司 | Capacitive equipment medium water content and aging evaluation method based on temperature drift electrical parameters |
CN116911068A (en) * | 2023-09-06 | 2023-10-20 | 成都汉度科技有限公司 | Method and system for predicting effective life of cable joint |
CN116911068B (en) * | 2023-09-06 | 2023-11-28 | 成都汉度科技有限公司 | Method and system for predicting effective life of cable joint |
CN118067201A (en) * | 2024-04-17 | 2024-05-24 | 四川赛康智能科技股份有限公司 | Full life cycle monitoring method and system for explosion-proof box |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113935238A (en) | Insulation aging degree evaluation method based on cable joint surface temperature | |
CN103901291B (en) | The diagnostic method of a kind of converting equipment built-in electrical insulation defect | |
CN108051364A (en) | A kind of EPR nuclear energy cable residue lifetime estimation method and prediction EPR nuclear energy cable remaining life methods | |
CN113884794A (en) | Method for evaluating main insulation aging state of motor wire bar | |
Qiu et al. | Probability analysis for failure assessment of electric energy metering equipment under multiple extreme stresses | |
CN111307480B (en) | Embedded heat pipe-based heat transfer management system, method and storage medium | |
CN111896849A (en) | Oil paper insulation performance analysis method and device considering non-uniform medium | |
Ma et al. | Temperature compensation method for infrared detection of live equipment under the interferences of wind speed and ambient temperature | |
CN108038268A (en) | GIL running temperature appraisal procedures in a kind of corridor pipe | |
CN113435073B (en) | GIS bus shell temperature measuring point arrangement optimization method | |
Zhao et al. | A dynamic monitoring method of temperature distribution for cable joints based on thermal knowledge and conditional generative adversarial network | |
CN112526305A (en) | Cable joint discharge live detection method based on high-speed light sensation and pressure wave technology | |
Zhao et al. | Real-time reconstruction of temperature field for cable joints based on inverse analysis | |
CN111060565A (en) | High-voltage direct-current cable material resistivity characteristic evaluation method | |
CN112989641B (en) | Method for detecting defects of high-voltage cable intermediate joint | |
Muniz et al. | Prospects of life estimation of low voltage electrical cables insulated by PVC by emissivity measurement | |
Huang et al. | Predicting the temperature of the electrolytic capacitor based on neural network algorithm | |
CN113779822A (en) | Motor insulation life prediction method based on multi-field coupling calculation | |
CN111880057A (en) | Cable insulation detection method for dielectric constant distribution display of insulating layer | |
Hua et al. | Lifetime Prediction of Aviation Cables Based on an Improved Electromagnetic-Thermal Coupling Model | |
He et al. | Simulation of Ultrasonic Propagation in Transformers within Thermal Fields and Intelligent Methodology for Hot-spot Temperature Recognition | |
Cui | Characterization of outdoor dielectrics for power system applications | |
CN113945299B (en) | Transformer winding temperature distribution and residual life prediction method | |
He et al. | Location prediction model of zero value insulator based on PNN | |
Zhan et al. | 110kV cable joint temperature computation based on radial basis function neural networks |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220819 Address after: No.170 Renmin Road, Anqing City, Anhui Province 246000 Applicant after: STATE GRID ANHUI ELECTRIC POWER CO., LTD. ANQING POWER SUPPLY Co. Applicant after: STATE GRID CORPORATION OF CHINA Address before: No.170 Renmin Road, Anqing City, Anhui Province 246000 Applicant before: STATE GRID ANHUI ELECTRIC POWER CO., LTD. ANQING POWER SUPPLY Co. |