CN112149869A - Method and system for predicting air gap discharge voltage of direct current transmission line - Google Patents

Method and system for predicting air gap discharge voltage of direct current transmission line Download PDF

Info

Publication number
CN112149869A
CN112149869A CN202010844276.3A CN202010844276A CN112149869A CN 112149869 A CN112149869 A CN 112149869A CN 202010844276 A CN202010844276 A CN 202010844276A CN 112149869 A CN112149869 A CN 112149869A
Authority
CN
China
Prior art keywords
data
transmission line
parameters
training
current transmission
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
Application number
CN202010844276.3A
Other languages
Chinese (zh)
Inventor
李鹏
丁玉剑
姚修远
周军
时卫东
雷挺
苏宇
姜德喜
刘玉胜
孙东旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
State Grid Anhui Electric Power Co Ltd
State Grid Xinjiang Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
State Grid Anhui Electric Power Co Ltd
State Grid Xinjiang Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI, State Grid Anhui Electric Power Co Ltd, State Grid Xinjiang Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202010844276.3A priority Critical patent/CN112149869A/en
Publication of CN112149869A publication Critical patent/CN112149869A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
    • G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
    • G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
    • G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention discloses a method and a system for predicting air gap discharge voltage of a direct-current transmission line, and belongs to the technical field of high voltage and insulation. The method comprises the following steps: acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model; acquiring basic information data of the direct current transmission line to be detected, inputting the basic information data into a training model, and acquiring output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line. Compared with the traditional tower head gap discharge voltage calculation mode, the tower head gap discharge voltage calculation method has higher prediction precision, does not need complicated calculation programs, and can realize the prediction of the breakdown voltage only by inputting the size of the grading ring, meteorological parameters, the width of the tower body and the gap distance.

Description

Method and system for predicting air gap discharge voltage of direct current transmission line
Technical Field
The invention relates to the technical field of high voltage and insulation, in particular to a method and a system for predicting air gap discharge voltage of a direct current transmission line.
Background
The current situation that the energy distribution and economic development of China are extremely unbalanced leads to the need of developing ultra-high voltage transmission projects in China and transmits the power resources stored in the west to the east of developed economy. The ultra-high voltage transmission project has the characteristics of large transmission capacity, long transmission line, high voltage grade and the like, and great challenges are brought to the insulation configuration of the ultra-high voltage transmission project. The air gap is the main external insulation form of the ultra-high voltage transmission line, the discharge characteristic of the air gap at the tower head of the transmission line tower is the important basis of the external insulation design of the ultra-high voltage transmission line, and the rationality of the external insulation design directly influences the economy and the safety of the power transmission and transformation engineering design.
The super-high voltage overhead line has long trans-regional interconnection transmission distance, the climate change of a transmission project along a road is complex, and factors such as the size of a grading ring, the width of a tower body, the climate of a region where the tower is located, the altitude and the like all affect the discharge of a tower head gap. Scientifically selecting the insulation level, and reasonably determining the gap distance is a key problem for optimizing the external insulation design. At present, the breakdown voltage of the tower head air gap of the tower at home and abroad is mainly obtained through a test method, the test cost is high, the period is long, and partial scholars provide methods such as empirical formula fitting and physical model calculation based on a certain amount of discharge tests to calculate the breakdown voltage of the tower head air gap of the tower, but the methods have certain limitations at present.
The existing air gap discharge voltage of the transmission line tower is generally obtained through tests, for example, an operation impact discharge test of a true-size tower head with an altitude of 55m is carried out for a +/-800 kV transmission line, discharge characteristic curves of different gap distances are obtained, and the discharge voltage under different gaps can be obtained through calculation of the curves.
The discharge voltage under other meteorological conditions can be calculated by corresponding formulas through meteorological or altitude correction methods in the standard GB/T16927.1 or IEC60071-2 standard.
The prior art mainly has the following defects:
(1) the applicability is poor, the obtained voltage strictly depends on parameters such as the size of the grading ring, the structure of the tower and meteorological conditions, and the voltage change is large after the relevant parameters are changed.
(2) The former meteorological parameter correction method is a simple mathematical formula, and the calculation precision is poor.
(3) The traditional calculation method is poor in altitude applicability and only suitable for low-altitude areas.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for predicting an air gap discharge voltage of a dc transmission line, comprising:
acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model;
acquiring basic information data of the direct current transmission line to be detected, inputting the basic information data into a training model, and acquiring output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line.
Optionally, during the discharge test, different voltage levels and different meteorological conditions are selected for carrying out.
Optionally, obtaining the training model specifically includes:
taking basic information data as training data and characteristic data as output data, and carrying out normalization processing on the training data to obtain normalized data;
inputting the normalized data into the SVR model, performing optimization processing to obtain optimal parameters, and determining the optimal SVR model according to the optimal parameters
And performing integrated algorithm learning on the training data, the output data and the optimal SVR model to obtain a training model.
Optionally, the training data includes: gap structure parameters and meteorological parameters;
the gap structure parameters include: the ring diameter and pipe diameter data, the gap distance and the tower body width of the high-pressure side grading ring;
the meteorological parameters include: air pressure, air temperature, and relative humidity of the air.
Optionally, the optimizing process uses a gray wolf algorithm for optimizing, and the specific process includes:
initializing a parameter position, a convergence factor, a random vector and a self-adaptive vector, and using the parameter position to represent a solution;
selecting three groups of parameters with the minimum objective function value, and sequentially storing the parameters as alpha, beta and beta;
carrying out surrounding, hunting and attacking treatment aiming at the three groups of parameters, and updating the gray wolf population position, the convergence factor, the random vector and the adaptive vector after the treatment is finished;
and updating the positions of the three parameters of alpha, beta and gamma, and obtaining the alpha position through iteration, wherein the alpha position is the optimal solution.
The invention also provides a system for predicting the air gap discharge voltage of the direct-current transmission line, which comprises the following steps:
the training module is used for acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model;
and the prediction module is used for acquiring basic information data of the direct current transmission line to be detected, inputting the basic information data into the training model and acquiring output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line.
Optionally, during the discharge test, different voltage levels and different meteorological conditions are selected for carrying out.
Optionally, obtaining the training model specifically includes:
taking basic information data as training data and characteristic data as output data, and carrying out normalization processing on the training data to obtain normalized data;
inputting the normalized data into the SVR model, performing optimization processing to obtain optimal parameters, and determining the optimal SVR model according to the optimal parameters
And performing integrated algorithm learning on the training data, the output data and the optimal SVR model to obtain a training model.
Optionally, the training data includes: gap structure parameters and meteorological parameters;
the gap structure parameters include: the ring diameter and pipe diameter data, the gap distance and the tower body width of the high-pressure side grading ring;
the meteorological parameters include: air pressure, air temperature, and relative humidity of the air.
Optionally, the optimizing process uses a gray wolf algorithm for optimizing, and the specific process includes:
initializing a parameter position, a convergence factor, a random vector and a self-adaptive vector, and using the parameter position to represent a solution;
selecting three groups of parameters with the minimum objective function value, and sequentially storing the parameters as alpha, beta and beta;
carrying out surrounding, hunting and attacking treatment aiming at the three groups of parameters, and updating the gray wolf population position, the convergence factor, the random vector and the adaptive vector after the treatment is finished;
and updating the positions of the three parameters of alpha, beta and gamma, and obtaining the alpha position through iteration, wherein the alpha position is the optimal solution.
Compared with the traditional tower head gap discharge voltage calculation mode, the tower head gap discharge voltage calculation method has higher prediction precision, does not need complicated calculation programs, and can realize the prediction of the breakdown voltage only by inputting the size of the grading ring, meteorological parameters, the width of the tower body and the gap distance.
Drawings
FIG. 1 is a flow chart of a method for predicting air gap discharge voltage of a DC transmission line according to the present invention;
FIG. 2 is a flowchart of an embodiment of a method for predicting air gap discharge voltage of a DC transmission line according to the present invention;
fig. 3 is a structural diagram of a system for predicting air gap discharge voltage of a dc transmission line according to the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
The invention provides a method for predicting air gap discharge voltage of a direct current transmission line, which comprises the following steps of:
acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model;
acquiring basic information data of the direct current transmission line to be detected, inputting the basic information data into a training model, and acquiring output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line.
During the discharge test, different voltage levels and different meteorological conditions are selected for carrying out.
Obtaining a training model, specifically comprising:
taking basic information data as training data and characteristic data as output data, and carrying out normalization processing on the training data to obtain normalized data;
inputting the normalized data into the SVR model, performing optimization processing to obtain optimal parameters, and determining the optimal SVR model according to the optimal parameters
And performing integrated algorithm learning on the training data, the output data and the optimal SVR model to obtain a training model.
Training data, comprising: gap structure parameters and meteorological parameters;
the gap structure parameters include: the ring diameter and pipe diameter data, the gap distance and the tower body width of the high-pressure side grading ring;
the meteorological parameters include: air pressure, air temperature, and relative humidity of the air.
Optimizing processing, namely optimizing by using a wolf algorithm, and the specific process comprises the following steps:
initializing a parameter position, a convergence factor, a random vector and a self-adaptive vector, and using the parameter position to represent a solution;
selecting three groups of parameters with the minimum objective function value, and sequentially storing the parameters as alpha, beta and beta;
carrying out surrounding, hunting and attacking treatment aiming at the three groups of parameters, and updating the gray wolf population position, the convergence factor, the random vector and the adaptive vector after the treatment is finished;
and updating the positions of the three parameters of alpha, beta and gamma, and obtaining the alpha position through iteration, wherein the alpha position is the optimal solution.
The invention is further illustrated by the following examples:
as shown in fig. 2, includes:
selecting tower head gap operation impact breakdown test data of +/-1100 kV, +/-800 kV, +/-660 kV and +/-500 kV direct-current transmission line tower head gaps under different gap distances and different meteorological conditions, and dispersedly selecting training data in the training set selection process to enable the training set to contain all meteorological conditions and tower head air gap structure information as much as possible.
And finally, taking the ring diameter of the grading ring at the high-voltage end of the tower, the pipe diameter of the grading ring at the high-voltage end, the width of the tower body, the gap distance, the air pressure, the temperature and the relative humidity as input characteristic quantities, and taking 50% of discharge voltage of the gap of the tower head of the tower as output characteristic quantities.
Normalizing the input characteristic quantity and the output characteristic quantity, wherein the expression is as follows:
Figure BDA0002642498770000061
in formula (II), x'iIs normalized value, xiIs the value before normalization, xmaxAnd xminRespectively, the maximum and minimum values of the characteristic data.
Step two, establishing an optimization objective function;
the mean square error of the output of the Support Vector Regression (SVR) model is taken as an optimization target, the following expression is established,
Figure BDA0002642498770000062
wherein n is the number of training data, yrFor the output value, y, of the r-th training sampler*For the actual breakdown voltage, f, of the r-th training sampleMSEThe minimum value is optimized for the objective function, min.
The process of optimizing Support Vector Regression (SVR) by the Grey wolf algorithm is to find parameters C and gamma which enable the minimum mean square error value (objective function) output by the SVR, and construct an optimal SVR model.
Setting initial parameters of a gray wolf algorithm;
initializing a population XiN) (N is the number of individuals in the population), wherein X isi＝(xi1，xi2，...，xin) (n is a parameter to be optimized of the SVR model, and the value is 2), initializing a convergence factor a and cooperative coefficient vectors A and C, setting the maximum iteration number to be 50, and setting the initial iteration number t to be 1.
Step four, calculating an initial objective function value;
taking the mean square error output by a Support Vector Regression (SVR) model as an optimization target, calculating an initial objective function value corresponding to the position of each wolf, comparing the size of the initial objective function values, selecting three groups of parameters with the minimum initial objective function values, and sequentially storing the three groups of parameters into alpha, beta and three wolfs, wherein the wolf with the highest grade is alpha, which means that the objective function value obtained by the parameters represented by the position of the wolf is the minimum, and beta is beta, and the second is beta.
Step five, updating the position of the wolf through three steps of surrounding, hunting and attacking;
1) a bounding process;
the gray wolf algorithm optimizing process is to simulate the gray wolf surrounding process to carry out optimizing, and the mathematical principle is shown in formulas (1) and (2):
D＝|C*Xp(t)-X(t)| (1)
X(t+1)＝Xp(t)-A*D (2)
where t is the current iteration number, XpThe position vector of the prey is represented, X (t) represents the position vector of the gray wolf in the process of the t iteration, D represents the distance between the gray wolf individual and the prey, A and C are synergistic coefficient vectors, and the calculation is shown in the formulas (3) and (4):
A＝2a*r1-a (3)
C＝2r2 (4)
in the formula, a is a convergence factor, the value of the convergence factor is linearly decreased from 2 to 0 in the iterative process, and r is1And r2Is [0, 1]]A random vector of (1). When | A | > 1, the population of Grey wolfs expands the search scope, looking for better prey, which corresponds to a global search, and when | A | < 1, the population of Grey wolfs will shrink the bounding circle, which corresponds to a local search.
2) A hunting process;
when the position of the prey is judged in the first step, three gray wolfs alpha, beta and leading wolf group omega surround the prey, and then the position of the searched individual is updated according to the position information of the three gray wolfs alpha, beta and leading wolf group omega, as shown in formulas (5) to (11). Wherein equations (5) - (7) calculate the distance from wolf omega to the optimum three wolfs alpha, beta, equations (8) - (10) update the location of the gray wolf, and equation (11) calculates the location of the game.
Dα＝|C1*Xα-X| (5)
Dβ＝|C2*Xβ-X| (6)
D＝|C3*X-X| (7)
X1＝Xα-A1*Dα (8)
X2＝Xβ-A2*Dβ (9)
X3＝X-A3*D (10)
Figure BDA0002642498770000081
Wherein, Xα、Xβ、XRespectively represent the current positions of alpha, beta and three wolfs, C1、C2、C3Representing a random vector, Dα、Dβ、DRespectively representing the distances between the current candidate gray wolf omega and the optimal three wolfs alpha and beta, X represents the gray wolf position vector1、X2、X3The advancing step length and direction of the omega wolf towards alpha, beta and three grey wolfs respectively, and X (t +1) is the final position of the omega wolf.
3) An attack process;
when the prey stops moving, the wolf ends the hunting by attacking. By lowering the convergence factor a, the value approaches the prey, and the value of a also becomes smaller. A is a random vector over the interval [ -2a, 2a ], where a gradually decreases linearly during the iteration. When the random A is on the [ -1, 1] interval, the position of the individual searched for at the next time can be any position between the current position and the prey, namely when | A | < 1, the prey is attacked by gray wolf.
Step six, judging whether the maximum iteration times is reached;
and judging whether the iteration time t reaches the maximum value, if not, returning to the step five to update the convergence factor a and the cooperative coefficient vectors A and C to continue iterative computation until the maximum iteration time is met or the convergence factor a is reduced to 0. If the maximum iteration number is reached, outputting XαAs the SVR optimal parameters.
Initializing an Adaboost-SVR model;
taking the SVR model with the optimal parameters obtained in the step six as a base learner of the Adaboost algorithm, setting the final number of the base learners as T to be 20, and initializing the weight of each sample as follows:
Figure BDA0002642498770000082
step eight, training an optimal Adaboost-SVR model;
the optimal SVR model is obtained by optimizing the six-gray wolf algorithm in the step and is used as a base learner C in the Adaboost algorithm1And calculating the training error of the training sequence as shown in the formula (12). Calculating a base learner C from the training error values1The calculation formula of (c) is shown in equation (13):
Figure BDA0002642498770000083
Figure BDA0002642498770000084
in the formula (I), the compound is shown in the specification,1to train the error, yjFor the output feature quantities of the jth data set in the training sample,
Figure BDA0002642498770000091
the 1 st round jth group of samples are weighted,
Figure BDA0002642498770000092
learning device C1The obtained j-th data prediction output, alpha1Learning device C1The weight occupied.
Then, the second round of sample weights are updated, and the calculation formula is shown as the formula (14):
Figure BDA0002642498770000093
in the formula Z1For the normalization coefficient, the calculation formula is shown in equation (15):
Figure BDA0002642498770000094
and repeating the steps until T base learners are trained, and performing weighted combination to obtain the final Adaboost-SVR model.
Figure BDA0002642498770000095
Step nine, packaging to obtain a visual window interface;
and finally, the model and the training data are packaged and programmed to realize visual window display, key influence parameters such as the ring diameter of the high-voltage end equalizing ring, the pipe diameter of the high-voltage end equalizing ring, the width of the tower body, the gap distance, the air pressure, the temperature, the relative humidity and the like in the prediction data are input to obtain the corresponding breakdown voltage, the breakdown voltage is compared with a test value under the same condition, the maximum prediction error is only 5 percent and the average relative error is 2.7 percent compared with the test value, and the effectiveness of the calculation method is verified.
The invention further provides a system 200 for predicting the air gap discharge voltage of the direct current transmission line, as shown in fig. 3, including:
the training module 201 is used for acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model;
the prediction module 202 acquires basic information data of the direct current transmission line to be tested, inputs the basic information data into the training model, and acquires output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line.
During the discharge test, different voltage levels and different meteorological conditions are selected for carrying out.
Obtaining a training model, specifically comprising:
taking basic information data as training data and characteristic data as output data, and carrying out normalization processing on the training data to obtain normalized data;
inputting the normalized data into the SVR model, performing optimization processing to obtain optimal parameters, and determining the optimal SVR model according to the optimal parameters
And performing integrated algorithm learning on the training data, the output data and the optimal SVR model to obtain a training model.
Training data, comprising: gap structure parameters and meteorological parameters;
the gap structure parameters include: the ring diameter and pipe diameter data, the gap distance and the tower body width of the high-pressure side grading ring;
the meteorological parameters include: air pressure, air temperature, and relative humidity of the air.
Optimizing processing, namely optimizing by using a wolf algorithm, and the specific process comprises the following steps:
initializing a parameter position, a convergence factor, a random vector and a self-adaptive vector, and using the parameter position to represent a solution;
selecting three groups of parameters with the minimum objective function value, and sequentially storing the parameters as alpha, beta and beta;
carrying out surrounding, hunting and attacking treatment aiming at the three groups of parameters, and updating the gray wolf population position, the convergence factor, the random vector and the adaptive vector after the treatment is finished;
and updating the positions of the three parameters of alpha, beta and gamma, and obtaining the alpha position through iteration, wherein the alpha position is the optimal solution.
Compared with the traditional tower head gap discharge voltage calculation mode, the tower head gap discharge voltage calculation method has higher prediction precision, does not need complicated calculation programs, and can realize the prediction of the breakdown voltage only by inputting the size of the grading ring, meteorological parameters, the width of the tower body and the gap distance.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be implemented by adopting various computer languages, such as object-oriented programming language Java and transliterated scripting language JavaScript.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (10)

1. A method for predicting air gap discharge voltage of a direct current transmission line comprises the following steps:
acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model;
acquiring basic information data of the direct current transmission line to be detected, inputting the basic information data into a training model, and acquiring output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line.
2. The method of claim 1, wherein the discharge test is performed by selecting different voltage levels and different meteorological conditions.
3. The method according to claim 1, wherein the obtaining of the training model specifically comprises:
taking basic information data as training data and characteristic data as output data, and carrying out normalization processing on the training data to obtain normalized data;
inputting the normalized data into the SVR model, performing optimization processing to obtain optimal parameters, and determining the optimal SVR model according to the optimal parameters
And performing integrated algorithm learning on the training data, the output data and the optimal SVR model to obtain a training model.
4. The method of claim 3, the training data, comprising: gap structure parameters and meteorological parameters;
the gap structure parameters include: the ring diameter and pipe diameter data, the gap distance and the tower body width of the high-pressure side grading ring;
the meteorological parameters include: air pressure, air temperature, and relative humidity of the air.
5. The method of claim 3, wherein the optimizing process uses a gray wolf algorithm to optimize, and comprises:
initializing a parameter position, a convergence factor, a random vector and a self-adaptive vector, and using the parameter position to represent a solution;
selecting three groups of parameters with the minimum objective function value, and sequentially storing the parameters as alpha, beta and beta;
carrying out surrounding, hunting and attacking treatment aiming at the three groups of parameters, and updating the gray wolf population position, the convergence factor, the random vector and the adaptive vector after the treatment is finished;
and updating the positions of the three parameters of alpha, beta and gamma, and obtaining the alpha position through iteration, wherein the alpha position is the optimal solution.
6. A system for predicting air gap discharge voltage of a dc transmission line, the system comprising:
the training module is used for acquiring basic information data of the direct-current transmission line aiming at the direct-current transmission line, performing a discharge test on a tower head gap of the direct-current transmission line, acquiring characteristic data of gap discharge, training the basic information data and the characteristic data, and acquiring a training model;
and the prediction module is used for acquiring basic information data of the direct current transmission line to be detected, inputting the basic information data into the training model and acquiring output data, wherein the output data is the discharge voltage of the air gap of the direct current transmission line.
7. The system of claim 6, wherein the discharge test is performed by selecting different voltage levels and different meteorological conditions.
8. The system of claim 6, wherein the obtaining of the training model specifically comprises:
taking basic information data as training data and characteristic data as output data, and carrying out normalization processing on the training data to obtain normalized data;
inputting the normalized data into the SVR model, performing optimization processing to obtain optimal parameters, and determining the optimal SVR model according to the optimal parameters
And performing integrated algorithm learning on the training data, the output data and the optimal SVR model to obtain a training model.
9. The system of claim 8, the training data, comprising: gap structure parameters and meteorological parameters;
the gap structure parameters include: the ring diameter and pipe diameter data, the gap distance and the tower body width of the high-pressure side grading ring;
the meteorological parameters include: air pressure, air temperature, and relative humidity of the air.
10. The system of claim 8, wherein the optimizing process uses a gray wolf algorithm to optimize, and the specific process comprises:
initializing a parameter position, a convergence factor, a random vector and a self-adaptive vector, and using the parameter position to represent a solution;
selecting three groups of parameters with the minimum objective function value, and sequentially storing the parameters as alpha, beta and beta;
carrying out surrounding, hunting and attacking treatment aiming at the three groups of parameters, and updating the gray wolf population position, the convergence factor, the random vector and the adaptive vector after the treatment is finished;
and updating the positions of the three parameters of alpha, beta and gamma, and obtaining the alpha position through iteration, wherein the alpha position is the optimal solution.
CN202010844276.3A 2020-08-20 2020-08-20 Method and system for predicting air gap discharge voltage of direct current transmission line Pending CN112149869A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010844276.3A CN112149869A (en) 2020-08-20 2020-08-20 Method and system for predicting air gap discharge voltage of direct current transmission line

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010844276.3A CN112149869A (en) 2020-08-20 2020-08-20 Method and system for predicting air gap discharge voltage of direct current transmission line

Publications (1)

Publication Number Publication Date
CN112149869A true CN112149869A (en) 2020-12-29

Family

ID=73889068

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010844276.3A Pending CN112149869A (en) 2020-08-20 2020-08-20 Method and system for predicting air gap discharge voltage of direct current transmission line

Country Status (1)

Country Link
CN (1) CN112149869A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113219308A (en) * 2021-02-05 2021-08-06 中国电力科学研究院有限公司 Method and system for determining operation impulse discharge voltage of complex gap structure
CN113805107A (en) * 2021-09-15 2021-12-17 国网新疆电力有限公司电力科学研究院 Overhauling and decommissioning evaluation method for transformer
WO2023174015A1 (en) * 2022-03-16 2023-09-21 广东电网有限责任公司东莞供电局 Air gap withstand voltage measurement and calculation method and apparatus, and computer device and medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113219308A (en) * 2021-02-05 2021-08-06 中国电力科学研究院有限公司 Method and system for determining operation impulse discharge voltage of complex gap structure
CN113219308B (en) * 2021-02-05 2024-01-26 中国电力科学研究院有限公司 Method and system for determining operation impulse discharge voltage of complex gap structure
CN113805107A (en) * 2021-09-15 2021-12-17 国网新疆电力有限公司电力科学研究院 Overhauling and decommissioning evaluation method for transformer
WO2023174015A1 (en) * 2022-03-16 2023-09-21 广东电网有限责任公司东莞供电局 Air gap withstand voltage measurement and calculation method and apparatus, and computer device and medium

Similar Documents

Publication Publication Date Title
CN112149869A (en) Method and system for predicting air gap discharge voltage of direct current transmission line
CN111126564B (en) Neural network structure searching method, device and equipment
CN108287808B (en) Universal dynamic tracking sequence sampling method for structural reliability analysis
CN104636985B (en) A kind of transmission line of electricity radio interference Forecasting Methodology of improved BP
CN107590565A (en) A kind of method and device for building building energy consumption forecast model
CN110826525B (en) Face recognition method and system
CN110533086B (en) Semi-automatic image data labeling method
CN110046379B (en) Structure overall damage identification method based on space-frequency information
CN112817312B (en) Path planning method based on double search optimization algorithm
CN116612120B (en) Two-stage road defect detection method for data unbalance
CN108764526A (en) A kind of Train delay artificial neural network recognition methods based on Analysis of Train Operation Order
CN112686481A (en) Runoff forecasting method and processor
CN109147868A (en) Protein function prediction technique, device, equipment and storage medium
CN110796268A (en) Method and device for determining hyper-parameters of business processing model
US10628541B2 (en) Method and apparatus for selecting integrated circuit device neural network modeling sample
CN109961160A (en) A kind of power grid future operation trend predictor method and system based on trend parameter
CN112348408A (en) Online teachers and materials training and evaluation method
CN112614021A (en) Tunnel surrounding rock geological information prediction method based on built tunnel information intelligent identification
CN110852415A (en) Vegetation index prediction method, system and equipment based on neural network algorithm
CN114880806A (en) New energy automobile sales prediction model parameter optimization method based on particle swarm optimization
CN114372558A (en) Residential electricity load prediction method, medium and equipment based on multi-model fusion
CN114238106A (en) Test time prediction method and device, electronic device and storage medium
CN114493245A (en) Mountain torrent disaster easiness evaluation method based on GIS and integrated learning
CN112348062A (en) Meteorological image prediction method, meteorological image prediction device, computer equipment and storage medium
CN108509684B (en) Steering engine and dynamic load simulator matching design method

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