CN112214851B - Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm - Google Patents
Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm Download PDFInfo
- Publication number
- CN112214851B CN112214851B CN202011057905.4A CN202011057905A CN112214851B CN 112214851 B CN112214851 B CN 112214851B CN 202011057905 A CN202011057905 A CN 202011057905A CN 112214851 B CN112214851 B CN 112214851B
- Authority
- CN
- China
- Prior art keywords
- electric field
- switch cabinet
- support vector
- vector machine
- genetic algorithm
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/245—Classification techniques relating to the decision surface
- G06F18/2451—Classification techniques relating to the decision surface linear, e.g. hyperplane
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention relates to a prediction and optimization method of a switch cabinet electric field based on a support vector machine and a genetic algorithm, which comprises the following steps: 1. selecting main factors and levels influencing the distribution of an electric field in the switch cabinet, establishing an orthogonal test table, calculating the electric field in the switch cabinet to obtain the maximum electric field intensity on the surface of the contact box, and constructing a training sample; 2. a prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet is established by adopting a regression model of a support vector machine; 3. selecting influence factors and horizontal combinations to carry out finite element electric field calculation to obtain the maximum electric field intensity of the surface of the contact box, constructing a verification sample, and optimizing penalty factors and kernel function parameters of a prediction model to obtain an optimized prediction model; 4. and optimally designing the switch cabinet structure by using a genetic algorithm, wherein the value of the influence factor corresponding to the minimum value of the maximum electric field intensity on the surface of the contact box is the optimized structural parameter. The method can simply, efficiently and accurately predict and optimize the structure of the electric field of the switch cabinet.
Description
Technical Field
The invention belongs to the technical field of power switch cabinets, and particularly relates to a switch cabinet electric field prediction and optimization method based on a support vector machine and a genetic algorithm.
Background
The high-voltage switch cabinet is used as important electric equipment for receiving and distributing electric energy, is widely applied to each link of a power transmission network and a power distribution network, has direct relation to the safety of the whole power grid and the power supply quality of a power system to users, and is one of the most important electric equipment in the power system. With the development of the high-voltage switch cabinet towards miniaturization and compactness, the space size and the occupied area of the switch cabinet are greatly saved, and simultaneously, more severe requirements are provided for the insulation and structural design of the switch cabinet. Due to unreasonable structural design and insulation arrangement, not only is the expected insulation effect difficult to achieve, but also insulation defects can be caused, and further operation faults and even accidents of the switch cabinet can be caused. The electric field distribution is the most important factor influencing the insulation performance inside the switch cabinet. Therefore, the prediction and optimization of the electric field in the switch cabinet are carried out, and the method has important significance for improving the insulation performance and the operation reliability of the switch cabinet.
At present, the high-voltage switch cabinet is mainly used for optimizing and analyzing an electric field by means of finite element analysis software, however, most of parameters adopted in the optimization process are existing empirical parameters, and the optimization process usually includes parameter change and repeated tests for many times, so that great blindness is achieved. Particularly for the optimization design under multiple influence factors, if the primary and secondary conditions of the factors are unclear, not only the workload of the optimization design is large, but also the optimal optimization result may not be obtained.
Disclosure of Invention
The invention aims to provide a prediction and optimization method of a switch cabinet electric field based on a support vector machine and a genetic algorithm, which can simply, efficiently and accurately predict and structurally optimize the switch cabinet electric field.
In order to achieve the purpose, the invention adopts the technical scheme that: a prediction and optimization method for an electric field of a switch cabinet based on a support vector machine and a genetic algorithm comprises the following steps:
step 1: selecting main factors and levels influencing the distribution of an electric field in the switch cabinet, establishing an orthogonal test table for calculating the electric field in the switch cabinet, calculating the electric field in the switch cabinet in each combination mode in the orthogonal test table by using finite element analysis software to obtain the maximum electric field intensity on the surface of the contact box, and performing normalization processing to obtain a training sample;
step 2: based on a training sample set, a support vector machine regression model is adopted to establish a prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet, the prediction model takes each influence factor set X as an input characteristic quantity and the maximum electric field intensity E on the surface of the contact box as an output quantity, and the relationship between the two is established: e ═ f (x);
and step 3: carrying out finite element electric field calculation on the influence factors except the orthogonal test and the horizontal combination in the complete test to obtain the maximum electric field intensity on the surface of the contact box, carrying out normalization processing to obtain a verification sample, and optimizing a penalty factor C and a kernel function gamma parameter of a prediction model to obtain the optimized prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet;
and 4, step 4: the maximum electric field intensity on the surface of the contact box is taken as an optimization control target, the switch cabinet structure is optimally designed by utilizing a genetic algorithm, and the value of the influence factor corresponding to the minimum value of the maximum electric field intensity on the surface of the contact box is the optimized structure parameter.
Further, in the step 1, the main factors influencing the distribution of the electric field inside the switch cabinet include a phase distance, a bus bar cross section area and a chamfer diameter.
Further, in the step 1, the orthogonal test table is a three-factor three-level orthogonal table L9(33)。
Further, in step 1, the finite element analysis software is ANSYS software, COMSOL software or FLUX software.
Further, in step 1, the normalization processing is to pre-process training sample data to accelerate the training speed and the convergence speed of the model and improve the prediction accuracy, and the normalization processing method includes:
wherein the content of the first and second substances,
for the normalized variable values, xiIs a variable value before normalization, xmaxAnd xminUpper and lower limits of the variables, respectively.
Further, in step 2, the basic idea of the regression model of the support vector machine is to find a hyperplane which satisfies a condition and can divide the sample set into two types, and the expression is as follows:
wherein L is the classification interval of the distance between the sample and the hyperplane; w is the weight of sample classification; n is the number of samples; λ > 0 is a penalty factor used for adjusting the loss caused by outliers and balancing the algorithm complexity and the sample error rate; relaxation variable xiiAnd > 0, ensuring the classification precision under the condition that the samples cannot be linearly separated.
Further, in the step 2, the support vector machine regression model adopts an RBF kernel function:
K(xi,xj)＝exp(-γ||xi-xj||2),
wherein, gamma is a width parameter in the RBF kernel function and is used for controlling the action range of the kernel function; x is a radical of a fluorine atomi、xjIs a feature vector of the classified sample.
Further, in the step 3, the penalty factor C and the kernel function γ parameter are optimized by improving a grid search method, a genetic algorithm or a particle swarm algorithm.
Further, in the step 4, a genetic algorithm is utilized to encode the parameters to be optimized to generate chromosomes, and the existing population is replaced by the new population through selection, crossing and variation methods; better offspring are obtained by exchanging between the parent chromosomes, and optimized structural parameters are obtained.
Compared with the prior art, the invention has the following beneficial effects: the invention adopts orthogonal design, can determine the primary and secondary sequence of the influence of each factor on the design index under the condition of less test times, and can quickly obtain the optimal factor level combination so as to obtain the optimal design target. The method is realized based on a support vector machine and a genetic algorithm, the support vector machine is a statistical theory method based on a structural risk minimization principle, the problems of small samples, nonlinearity and overfitting can be effectively solved, the generalization capability is good, the genetic algorithm has excellent global optimal searching capability, and the optimal feature subset and the optimal parameters of a classifier are simultaneously searched by combining an encapsulation type feature extraction method, so that the optimal structural parameters can be effectively improved and obtained. The prediction and optimization results obtained by the method can provide reference for the structural design and optimization of the high-voltage switch cabinet.
Drawings
FIG. 1 is a flow chart of a method implementation of an embodiment of the present invention.
FIG. 2 is a diagram illustrating a calculation result according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and the embodiments.
Referring to fig. 1, the invention provides a method for predicting and optimizing an electric field of a switch cabinet based on a support vector machine and a genetic algorithm, which comprises the following steps:
step 1: selecting main factors and levels influencing the distribution of an electric field in the switch cabinet, establishing an orthogonal test table for calculating the electric field of the switch cabinet, calculating the electric field in the switch cabinet in each combination mode in the orthogonal test table by using finite element analysis software to obtain the maximum electric field intensity on the surface of the contact box, and performing normalization processing to obtain a training sample.
The main factors influencing the distribution of the electric field in the switch cabinet comprise a phase distance D, a bus bar sectional area S and a chamfer diameter D, each influencing factor has 3 levels, and the design of a gauge head is shown in a table 1, so that a three-factor three-level orthogonal table L is established9(33) See table 2.
TABLE 1 header design
Table 2 orthogonal test table L9(33)
And (3) calculating the internal electric field of the switch cabinet in different combination modes in the table 2 by using finite element calculation software ANSYS, COMSOL or FLUX to obtain the maximum electric field intensity of the surface of the contact box, wherein the maximum electric field intensity is used as the 4 th column of the table 2. In the embodiment, COMSOL software is adopted to calculate the electric field in the switch cabinet.
In order to accelerate the sample training speed and the convergence speed of the model and improve the prediction precision, the training sample data shown in the table 2 is preprocessed by adopting a normalization method, wherein the normalization method comprises the following steps:
wherein the content of the first and second substances,
for the normalized variable values, xiIs a variable value before normalization, xmaxAnd xminUpper and lower limits for the variables, respectively.
Step 2: based on a training sample set, a support vector machine regression model is adopted to establish a prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet, the prediction model takes each influence factor set X as an input characteristic quantity and the maximum electric field intensity E on the surface of the contact box as an output quantity, and the relationship between the two is established: e ═ f (x).
The basic idea of the regression model of the support vector machine is to find a hyperplane which satisfies the conditions and can divide a sample set into two types, wherein the expression is as follows:
wherein L is the classification interval of the distance between the sample and the hyperplane; w is the weight of sample classification; n is the number of samples; λ > 0 is a penalty factor used for adjusting the loss caused by outliers and balancing the algorithm complexity and the sample error rate; relaxation variable xiiAnd > 0, ensuring the classification precision under the condition that the samples cannot be linearly separated.
The regression model of the support vector machine adopts a Radial Basis Function (RBF) kernel function, and has the advantages of strong learning capacity and mapping to infinite dimension:
K(xi,xj)＝exp(-γ||xi-xj||2),
wherein, gamma is a width parameter in the RBF kernel function and is used for controlling the action range of the kernel function; x is the number ofi、xjIs a feature vector of the classified sample.
And step 3: and (3) performing finite element electric field calculation on the influence factors and horizontal combinations except the orthogonal test in the complete test to obtain the maximum electric field intensity on the surface of the contact box, performing normalization processing to obtain a verification sample, and optimizing the penalty factor C and the kernel function gamma parameter of the prediction model to obtain the optimized prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet.
The penalty factor C and the kernel function gamma parameter of the support vector machine prediction model are optimized, and an improved grid search method, a genetic algorithm or a particle swarm algorithm can be adopted. In the embodiment, a particle swarm algorithm is adopted, and a learning factor c is set1＝1.5，c21.7, the population number is 30, the maximum evolution generation number is 200, the coefficient k is 0.6, the elastic coefficient epsilon is 1, and the value ranges of C and gamma are respectively set as [2 ]3，29]And [2 ]-8，2-2]。
And 4, step 4: the maximum electric field intensity on the surface of the contact box is taken as an optimization control target, the switch cabinet structure is optimally designed by utilizing a genetic algorithm, and the value of the influence factor corresponding to the minimum value of the maximum electric field intensity on the surface of the contact box is the optimized structure parameter.
The genetic algorithm encodes the parameters to be optimized to generate chromosomes, replaces the existing population with the new population by selection, crossing and variation methods, and obtains better offspring by exchanging parent chromosomes to obtain optimized structural parameters. In this example, the probability of generating a new chromosome was set to 0.8, and the probability of mutation was set to 0.05.
The beneficial effects of the invention are further explained below by taking a certain type of 10kV switch cabinet as an example.
1) The phase distance D, the bus bar sectional area S and the chamfer diameter D are analyzed and selected as main factors influencing the distribution of the electric field in the switch cabinet, and the levels of all the factors are shown in Table 3. An orthogonal test table of the 10kV switch cabinet electric field calculation is established, and is shown in table 4. The electric field inside the switch cabinet under each combination mode in the orthogonal table is calculated by using finite element analysis software COMSOL, the maximum electric field strength of the surface of the contact box is obtained, the result is listed in the 4 th column of the table 3, and the typical calculation result is shown in figure 2. The data in table 4 were normalized to serve as training samples.
Electric field influence factor and level of 310 kV switch cabinet
Table 410 orthogonal test table L9(33)
2) Based on a training sample set, a support vector machine regression model is adopted to establish a prediction model of the maximum electric field strength on the surface of the contact box of the switch cabinet, the model takes the phase distance D, the bus bar sectional area S and the chamfer diameter D as input characteristic quantities, and the maximum electric field strength E on the surface of the contact box as output quantities, and the relationship between the two is established.
3) And (3) performing electric field calculation on 18 groups of influence factors and horizontal combinations except the orthogonal test (9) in the complete test (27 groups) by using finite element analysis software COMSOL to obtain the maximum field intensity of the surface of the contact box, wherein the maximum field intensity is used as a verification sample. And optimizing a penalty factor C and a kernel function gamma parameter of the support vector machine prediction model by adopting a particle swarm optimization, wherein the optimized parameters are as follows: c204.8 and y 0.1566.
4) The maximum electric field intensity E on the surface of the contact box is taken as an optimization control target, the switch cabinet structure is optimally designed by utilizing a genetic algorithm, the minimum value of the maximum electric field intensity on the surface of the contact box is 21.3kV/cm, and the corresponding optimal structure parameters are as follows: the distance d is 151.2mm, and the bus bar section area S is 12.38cm2And the chamfer diameter D is 3.6 mm.
The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.
Claims (9)
1. A prediction and optimization method for an electric field of a switch cabinet based on a support vector machine and a genetic algorithm is characterized by comprising the following steps:
step 1: selecting main factors and levels influencing the distribution of an electric field in the switch cabinet, establishing an orthogonal test table for calculating the electric field in the switch cabinet, calculating the electric field in the switch cabinet in each combination mode in the orthogonal test table by using finite element analysis software to obtain the maximum electric field intensity on the surface of the contact box, and performing normalization processing to obtain a training sample;
step 2: based on a training sample set, a support vector machine regression model is adopted to establish a prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet, the prediction model takes each influence factor set X as an input characteristic quantity and the maximum electric field intensity E on the surface of the contact box as an output quantity, and the relationship between the two is established: e ═ f (x);
and step 3: carrying out finite element electric field calculation on the influence factors except the orthogonal test and the horizontal combination in the complete test to obtain the maximum electric field intensity on the surface of the contact box, carrying out normalization processing to obtain a verification sample, and optimizing a penalty factor C and a kernel function gamma parameter of a prediction model to obtain the optimized prediction model of the maximum electric field intensity on the surface of the contact box of the switch cabinet;
and 4, step 4: the maximum electric field intensity on the surface of the contact box is taken as an optimization control target, the switch cabinet structure is optimally designed by utilizing a genetic algorithm, and the value of the influence factor corresponding to the minimum value of the maximum electric field intensity on the surface of the contact box is the optimized structural parameter.
2. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm as claimed in claim 1, wherein in the step 1, the main factors influencing the distribution of the electric field inside the switch cabinet comprise a phase distance, a bus bar cross section and a chamfer diameter.
3. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm as claimed in claim 1, wherein in the step 1, the orthogonal test table is a three-factor three-level orthogonal table L9(33)。
4. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm as claimed in claim 1, wherein in the step 1, the finite element analysis software is ANSYS software, COMSOL software or FLUX software.
5. The method according to claim 1, wherein in the step 1, the normalization processing is to pre-process training sample data to accelerate the training speed and the convergence speed of the model and improve the prediction accuracy, and the normalization processing method is:
wherein, the first and the second end of the pipe are connected with each other,
for the normalized variable values, xiIs a variable value before normalization, xmaxAnd xminUpper and lower limits for the variables, respectively.
6. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm as claimed in claim 1, wherein in the step 2, the basic idea of the regression model of the support vector machine is to find a hyperplane which can divide the sample set into two types and satisfies the condition, and the expression is as follows:
wherein L is the classification interval of the distance between the sample and the hyperplane; w is the weight of sample classification; n is the number of samples; λ > 0 is a penalty factor used for adjusting the loss caused by outliers and balancing the algorithm complexity and the sample error rate; relaxation variable xiiAnd > 0, ensuring the classification precision under the condition that the samples cannot be linearly separated.
7. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm, according to claim 1, wherein in the step 2, the support vector machine regression model adopts an RBF kernel function:
K(xi,xj)＝exp(-γ||xi-xj||2),
wherein, gamma is a width parameter in the RBF kernel function and is used for controlling the action range of the kernel function; x is the number ofi、xjIs a feature vector of the classified sample.
8. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm as claimed in claim 1, wherein in the step 3, the penalty factor C and the kernel function gamma parameter are optimized by improving a grid search method, a genetic algorithm or a particle swarm algorithm.
9. The method for predicting and optimizing the electric field of the switch cabinet based on the support vector machine and the genetic algorithm is characterized in that in the step 4, the genetic algorithm is used for coding the parameters to be optimized to generate chromosomes, and the new population is used for replacing the existing population through selection, crossing and variation methods; better offspring are obtained by exchanging between the parent chromosomes, and optimized structural parameters are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011057905.4A CN112214851B (en) | 2020-09-29 | 2020-09-29 | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011057905.4A CN112214851B (en) | 2020-09-29 | 2020-09-29 | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112214851A CN112214851A (en) | 2021-01-12 |
| CN112214851B true CN112214851B (en) | 2022-06-07 |
Family
ID=74051035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011057905.4A Active CN112214851B (en) | 2020-09-29 | 2020-09-29 | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112214851B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768701A (en) * | 2012-07-02 | 2012-11-07 | 河海大学常州校区 | High-voltage switch cabinet insulator electric field optimization method based on quantum genetic algorithm |
| CN103440370A (en) * | 2013-08-21 | 2013-12-11 | 国家电网公司 | Transmission and transformation project construction cost assessment method and device |
| CN104849633A (en) * | 2015-05-15 | 2015-08-19 | 国家电网公司 | Switchgear partial discharge mode recognition method |
| CN110703057A (en) * | 2019-11-04 | 2020-01-17 | 国网山东省电力公司电力科学研究院 | Power equipment partial discharge diagnosis method based on data enhancement and neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11486925B2 (en) * | 2020-05-09 | 2022-11-01 | Hefei University Of Technology | Method for diagnosing analog circuit fault based on vector-valued regularized kernel function approximation |
-
2020
- 2020-09-29 CN CN202011057905.4A patent/CN112214851B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768701A (en) * | 2012-07-02 | 2012-11-07 | 河海大学常州校区 | High-voltage switch cabinet insulator electric field optimization method based on quantum genetic algorithm |
| CN103440370A (en) * | 2013-08-21 | 2013-12-11 | 国家电网公司 | Transmission and transformation project construction cost assessment method and device |
| CN104849633A (en) * | 2015-05-15 | 2015-08-19 | 国家电网公司 | Switchgear partial discharge mode recognition method |
| CN110703057A (en) * | 2019-11-04 | 2020-01-17 | 国网山东省电力公司电力科学研究院 | Power equipment partial discharge diagnosis method based on data enhancement and neural network |
Non-Patent Citations (1)
| Title |
|---|
| 高低压开关柜体新产品开发集成平台研究;李建华;《中国优秀硕士学位论文》;20190515;第C042-535页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112214851A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102074955B (en) | Method based on knowledge discovery technology for stability assessment and control of electric system | |
| Guo et al. | Improved support vector machine oil price forecast model based on genetic algorithm optimization parameters | |
| CN106779277B (en) | Classified evaluation method and device for network loss of power distribution network | |
| CN107516171B (en) | Prediction analysis system and analysis method for key operation indexes of power grid enterprise | |
| CN116031888B (en) | Dynamic load prediction-based power flow optimization method, system and storage medium | |
| CN109034676B (en) | Power distribution network fault recovery scheme interval evaluation method under incomplete index weight information | |
| CN110705859A (en) | PCA-self-organizing neural network-based method for evaluating running state of medium and low voltage distribution network | |
| CN114302418A (en) | Method and device for detecting network element equipment performance and computer readable medium | |
| CN115831263A (en) | Method and system for optimizing qualification rate of electrolytic refining high-purity indium product | |
| CN112214851B (en) | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm | |
| CN116701919B (en) | Optimization monitoring method and system for gyro-type hydrogen fuel generator | |
| Rezaeian‐Marjani et al. | Probabilistic assessment of D‐STATCOM operation considering correlated uncertain variables | |
| CN112348236A (en) | Abnormal daily load demand prediction system and method for intelligent power consumption monitoring terminal | |
| Zhu et al. | A novel fast estimation and regroup method of retired lithium‐ion battery cells | |
| CN111239516A (en) | Method and device for predicting service life of mutual inductor | |
| CN112488443B (en) | Method and system for evaluating utilization rate of power distribution equipment based on data driving | |
| CN108123436B (en) | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm | |
| CN113283702B (en) | Power flow state evaluation method and device integrating safety and stability characteristics of power system | |
| Yin et al. | Big data cleaning model of smart grid based on Tensor Tucker decomposition | |
| CN116542000B (en) | Power grid refinement management system based on source network data analysis | |
| CN115292938B (en) | Rapid multi-machine equivalent modeling method and device for large photovoltaic power station based on improved bi-kmeans | |
| Xi et al. | Analysis of phase-shift full bridge zvzcs converter | |
| Al-Abdulwahab | Probabilistic electrical power generation modeling using genetic algorithm | |
| Wei et al. | A two-stage diversity enhancement differential evolution algorithm for multi-objective optimization problem | |
| CN111106607B (en) | Method and device for judging stability of static voltage |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |