CN116466189A - Power distribution network fault line selection method based on particle swarm optimization support vector machine - Google Patents
Power distribution network fault line selection method based on particle swarm optimization support vector machine Download PDFInfo
- Publication number
- CN116466189A CN116466189A CN202310512915.XA CN202310512915A CN116466189A CN 116466189 A CN116466189 A CN 116466189A CN 202310512915 A CN202310512915 A CN 202310512915A CN 116466189 A CN116466189 A CN 116466189A
- Authority
- CN
- China
- Prior art keywords
- particle swarm
- support vector
- vector machine
- fault line
- particle
- 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
- 239000002245 particle Substances 0.000 title claims abstract description 129
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 64
- 238000005457 optimization Methods 0.000 title claims abstract description 54
- 238000009826 distribution Methods 0.000 title claims abstract description 44
- 238000010187 selection method Methods 0.000 title claims abstract description 25
- 230000001052 transient effect Effects 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000007704 transition Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 16
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution network fault line selection method based on a particle swarm optimization support vector machine, which comprises the following steps: 1. acquiring transient zero sequence currents of all lines in a power distribution network; 2. performing Fourier transform on the transient zero-sequence current signals of each line to obtain transient zero-sequence current frequency domain signals; 3. inputting the frequency domain signals into a pre-trained particle swarm optimization support vector machine model, and outputting a fault line selection result of the power distribution network; 4. judging whether the envelope slope of the transient zero-sequence current of the fault line selected in the step three is positive and negative opposite to the envelope slope of the transient zero-sequence current of the non-fault line, and determining the fault line selected in the step three as the fault line when the envelope slope of the transient zero-sequence current of the non-fault line is positive and negative opposite to the envelope slope of the transient zero-sequence current of the non-fault line; otherwise, returning to the first step. The invention can accurately select the fault line under various single-phase grounding fault conditions, has good sensitivity, reliability and rapidity, and is convenient for popularization and application.
Description
Technical Field
The invention belongs to the technical field of power grid fault line selection, and particularly relates to a power distribution network fault line selection method based on a particle swarm optimization support vector machine.
Background
The current domestic distribution lines are wide in distribution, long in line and multiple in branches, the operation environment is complex, single-phase ground faults account for more than 70% of the total faults of the distribution network, power failure accidents are continuous due to single-phase ground faults, and the faults are operated for a long time, so that the accidents are expanded, and the safety of system equipment, personnel, livestock, property and the like is seriously threatened. Therefore, diagnosis and analysis are urgently needed to be carried out on the running state of the power distribution network line, and accurate line selection is realized when single-phase earth faults occur, so that the fault removal time is shortened, and the risks of large-area power failure, equipment, personal and property safety and the like are reduced.
Aiming at a distribution network small-current grounding system, when a single-phase grounding fault occurs in the system, the existing small-current grounding line selection device has the problems that line selection is inaccurate, the adaptability of a line selection algorithm is low, the running state of the line selection device, equipment parameters, wave recording data and other information are lack of unified management, and operation and maintenance personnel cannot master fault information in the first time.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the power distribution network fault line selection method based on the particle swarm optimization support vector machine, which can accurately select a fault line under various single-phase ground fault conditions, has good sensitivity, reliability and rapidity, and is convenient to popularize and apply.
In order to solve the technical problems, the invention adopts the following technical scheme: a power distribution network fault line selection method based on a particle swarm optimization support vector machine comprises the following steps:
step one, acquiring transient zero sequence currents of all lines in a power distribution network;
performing Fourier transform on the transient zero-sequence current signals of each line to obtain transient zero-sequence current frequency domain signals of each line;
inputting transient zero sequence current frequency domain signals of all lines into a pre-trained particle swarm optimization support vector machine model, and outputting a fault line selection result of the power distribution network based on the particle swarm optimization support vector machine model; in the particle swarm optimization support vector machine model, penalty parameters and nuclear parameters in the support vector machine model are optimized through the particle swarm algorithm;
judging whether the envelope slope of the transient zero-sequence current of the fault line selected in the step three is positive and negative opposite to the envelope slope of the transient zero-sequence current of the non-fault line, and determining the fault line selected in the step three as the fault line when the envelope slope of the fault line selected in the step three is positive and negative opposite to the envelope slope of the non-fault line, and ending the fault line selection; otherwise, returning to the first step.
According to the power distribution network fault line selection method based on the particle swarm optimization support vector machine, the transient zero sequence current I of each line is the average value of three-phase current instantaneous values of each line, and is expressed as I= (I) by a formula a +I b +I c ) 3, wherein I a Is the instantaneous value of phase A current of the line, I b Is the B-phase current instantaneous value of the line, I c Is the instantaneous value of the phase C current of the line.
In the above power distribution network fault line selection method based on the particle swarm optimization support vector machine, in the third step, the training process of the particle swarm optimization support vector machine model is as follows:
step S1, establishing a fault simulation working condition of a power distribution network, setting a power grid voltage, a node load, a line fault position, a transition resistance and a fault phase angle value range, generating a fault scene set covering the parameter range, collecting transient zero sequence currents of each line in all scenes, and forming a training data set of a particle swarm optimization support vector machine model;
s2, performing Fourier transform on transient zero-sequence current signals of each line in the training data set to obtain transient zero-sequence current frequency domain signals of each line;
s3, initializing the position and the speed of a particle swarm, and representing the position of each particle in the particle swarm as a punishment parameter and a kernel parameter set in a support vector machine model;
s4, initializing a position matrix X of the particle swarm;
s5, updating a position matrix X of the particle swarm;
s6, calculating the fitness value of each particle by adopting a fitness function;
step S7, for each particle, comparing the fitness value of the particle with the fitness value of the current optimal position of the particle, and updating when the fitness value is better;
step S8, for each particle, comparing the fitness value of the particle with the fitness value of the global optimal position of the particle swarm, and updating when the fitness value is better;
step S9, finishing iteration when the maximum iteration times are reached, otherwise, returning to step S3 to continue iteration execution, and determining a solution of the global optimal position of the particle swarm after finishing iteration as a penalty parameter and a kernel parameter in the support vector machine model;
and S10, training a particle swarm optimization support vector machine model by using a training data set to obtain a trained particle swarm optimization support vector machine model.
In the above power distribution network fault line selection method based on the particle swarm optimization support vector machine, the formula adopted when updating the position matrix X of the particle swarm in step S5 is as follows:
x ij (n+1)＝x ij (n)+λF i (n)(P g (n)-x ij (n))+(1-λ)F i (n)(P i (n)-x ij (n))+F i (n)(x ij (n)-x i+1,j (n))
wherein x is ij (n) is the particle at the ith row and jth column position in the particle group at the iteration number of n, x ij (n+1) is a particle at the j-th column position of the i-th row in the particle swarm when the iteration number is n+1, λ is an inertia coefficient and λ=λ min +n×(λ max -λ min )n max N is the iteration number and takes the value of 1 to n max Natural number lambda of (a) min Lambda is the minimum coefficient of inertia max For maximum inertia coefficient, n max Is the total iteration number; f (F) i (n) is a scaling factor; p (P) i (n) is the current optimal position of the particle when the iteration number is n, P g (n) is the global optimal position of the particle swarm when the iteration number is n; x is x i+1,j (n) is the number of iterations n time-lapse dividing the particles at the position of the (i+1) th row and the (j) th column in the particle swarm.
The power distribution network fault line selection method based on the particle swarm optimization support vector machine is used for scaling the coefficient F i The calculation formula of (n) is:
wherein F is min For minimum scaling factor, F max Is the maximum scaling factor.
According to the power distribution network fault line selection method based on the particle swarm optimization support vector machine, in the step S6, the fitness function adopted when the fitness value of each particle is calculated is a Rastrigin function or a Griewank function.
In the above power distribution network fault line selection method based on the particle swarm optimization support vector machine, the kernel function of the particle swarm optimization support vector machine model in step S10 adopts a gaussian kernel function.
In the above method for selecting a power distribution network fault line based on the particle swarm optimization support vector machine, in the fourth step, the method for determining whether the slope of the envelope curve of the transient zero-sequence current of the fault line selected in the third step is positive and negative opposite to the slope of the envelope curve of the transient zero-sequence current of the non-fault line is as follows:
a1, selecting the maximum/minimum value of the transient zero sequence current of the line;
step A2, performing interpolation operation on a sequence formed by maximum/minimum values to obtain an upper envelope line and a lower envelope line of a signal;
and A3, obtaining the average value of the upper envelope curve and the lower envelope curve to obtain the envelope curve of the signal.
According to the power distribution network fault line selection method based on the particle swarm optimization support vector machine, when interpolation operation is carried out on the sequence formed by the maximum/minimum values in the step A2, a Newton interpolation method is adopted.
In the above power distribution network fault line selection method based on the particle swarm optimization support vector machine, the geometric mean value is adopted when the mean value of the upper envelope line and the lower envelope line is calculated in the step A3.
Compared with the prior art, the invention has the following advantages: the invention combines the principle that the slope of the envelope of the transient zero sequence current of the fault line and the slope of the envelope of the transient zero sequence current of the non-fault line are positive and negative, based on the particle swarm optimization support vector machine model, performs fault line selection, improves the particle swarm algorithm when the penalty parameter and the nuclear parameter of the support vector machine model are optimized by adopting the particle swarm algorithm, provides a new method for updating the position matrix of the particle swarm, can accurately select the fault line under various single-phase grounding fault conditions, has good sensitivity, reliability and rapidity, and is convenient to popularize and apply.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a block flow diagram of the method of the present invention.
Detailed Description
As shown in fig. 1, the power distribution network fault line selection method based on the particle swarm optimization support vector machine of the invention comprises the following steps:
step one, acquiring transient zero sequence currents of all lines in a power distribution network;
in this embodiment, the transient zero-sequence current I of each line is an average value of three-phase current transients of each line, and is expressed as i= (I by a formula a +I b +I c ) 3, wherein I a Is the instantaneous value of phase A current of the line, I b Is the B-phase current instantaneous value of the line, I c Is the instantaneous value of the phase C current of the line.
Performing Fourier transform on the transient zero-sequence current signals of each line to obtain transient zero-sequence current frequency domain signals of each line;
inputting transient zero sequence current frequency domain signals of all lines into a pre-trained particle swarm optimization support vector machine model, and outputting a fault line selection result of the power distribution network based on the particle swarm optimization support vector machine model; in the particle swarm optimization support vector machine model, penalty parameters and nuclear parameters in the support vector machine model are optimized through the particle swarm algorithm;
in the third embodiment, in the step three, the training process of the particle swarm optimization support vector machine model is as follows:
step S1, establishing a fault simulation working condition of a power distribution network, setting a power grid voltage, a node load, a line fault position, a transition resistance and a fault phase angle value range, generating a fault scene set covering the parameter range, collecting transient zero sequence currents of each line in all scenes, and forming a training data set of a particle swarm optimization support vector machine model;
in the specific implementation, the fault scene set is to take values of power grid voltage, node load, line fault position, transition resistance and fault phase angle in a certain range according to the actual running condition of the power distribution network, and a parameter traversal table is formed. And forming a large number of simulation scenes, namely fault scene sets, by arranging and combining the parameter values in the parameter traversal table.
The training data set of the particle swarm optimization support vector machine model is used for running single-phase fault simulation working conditions of the power distribution network under all fault scenes contained in the fault scene set, collecting zero sequence currents of all lines and recording corresponding fault lines; and taking the transient zero sequence current as a data main body, taking the corresponding fault line as a data tag, and forming a training data set of the particle swarm optimization support vector machine model together.
S2, performing Fourier transform on transient zero-sequence current signals of each line in the training data set to obtain transient zero-sequence current frequency domain signals of each line;
s3, initializing the position and the speed of a particle swarm, and representing the position of each particle in the particle swarm as a punishment parameter and a kernel parameter set in a support vector machine model;
s4, initializing a position matrix X of the particle swarm;
s5, updating a position matrix X of the particle swarm;
in this embodiment, the formula adopted when updating the position matrix X of the particle swarm in step S5 is:
x ij (n+1)＝x ij (n)+λF i (n)(P g (n)-x ij (n))+(1-λ)F i (n)(P i (n)-x ij (n))+F i (n)(x ij (n)-x i+1,j (n))
wherein x is ij (n) is the particle at the ith row and jth column position in the particle group at the iteration number of n, x ij (n+1) is a particle at the j-th column position of the i-th row in the particle swarm when the iteration number is n+1, λ is an inertia coefficient and λ=λ min +n×(λ max -λ min )n max N is the iteration number and takes the value of 1 to n max Natural number lambda of (a) min Lambda is the minimum coefficient of inertia max For maximum inertia coefficient, n max Is the total iteration number; f (F) i (n) is a scaling factor; p (P) i (n) is the current optimal position of the particle when the iteration number is n, P g (n) is the global optimal position of the particle swarm when the iteration number is n; x is x i+1,j (n) is the number of iterations n time-lapse dividing the particles at the position of the (i+1) th row and the (j) th column in the particle swarm.
In the present embodiment, the scaling factor F i The calculation formula of (n) is:
wherein F is min For minimum scaling factor, F max Is the maximum scaling factor.
S6, calculating the fitness value of each particle by adopting a fitness function;
in this embodiment, the fitness function used in calculating the fitness value of each particle in step S6 is a ratio function or a Griewank function.
Step S7, for each particle, comparing the fitness value of the particle with the fitness value of the current optimal position of the particle, and updating when the fitness value is better;
step S8, for each particle, comparing the fitness value of the particle with the fitness value of the global optimal position of the particle swarm, and updating when the fitness value is better;
step S9, finishing iteration when the maximum iteration times are reached, otherwise, returning to step S3 to continue iteration execution, and determining a solution of the global optimal position of the particle swarm after finishing iteration as a penalty parameter and a kernel parameter in the support vector machine model;
and S10, training a particle swarm optimization support vector machine model by using a training data set to obtain a trained particle swarm optimization support vector machine model.
In this embodiment, the kernel function of the particle swarm optimization support vector machine model in step S10 adopts a gaussian kernel function. Judging whether the envelope slope of the transient zero-sequence current of the fault line selected in the step three is positive and negative opposite to the envelope slope of the transient zero-sequence current of the non-fault line, and determining the fault line selected in the step three as the fault line when the envelope slope of the fault line selected in the step three is positive and negative opposite to the envelope slope of the non-fault line, and ending the fault line selection; otherwise, returning to the first step.
In this embodiment, in the fourth step, the method for determining whether the slope of the envelope of the transient zero-sequence current of the fault line selected in the third step is positive or negative, when the slope of the envelope of the transient zero-sequence current of the non-fault line is positive or negative, includes:
a1, selecting the maximum/minimum value of the transient zero sequence current of the line;
step A2, performing interpolation operation on a sequence formed by maximum/minimum values to obtain an upper envelope line and a lower envelope line of a signal;
in this embodiment, newton interpolation is used when the interpolation is performed on the sequence of maximum/minimum values in step A2.
And A3, obtaining the average value of the upper envelope curve and the lower envelope curve to obtain the envelope curve of the signal.
In this embodiment, in the step A3, a geometric average is used when the upper envelope and the lower envelope are averaged.
It will be appreciated by those skilled in the art that 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 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
The foregoing descriptions of specific exemplary embodiments of the present invention are presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application to thereby enable one skilled in the art to make and utilize the invention in various exemplary embodiments and with various modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (10)
1. A power distribution network fault line selection method based on a particle swarm optimization support vector machine is characterized by comprising the following steps:
step one, acquiring transient zero sequence currents of all lines in a power distribution network;
performing Fourier transform on the transient zero-sequence current signals of each line to obtain transient zero-sequence current frequency domain signals of each line;
inputting transient zero sequence current frequency domain signals of all lines into a pre-trained particle swarm optimization support vector machine model, and outputting a fault line selection result of the power distribution network based on the particle swarm optimization support vector machine model; in the particle swarm optimization support vector machine model, penalty parameters and nuclear parameters in the support vector machine model are optimized through the particle swarm algorithm;
judging whether the envelope slope of the transient zero-sequence current of the fault line selected in the step three is positive and negative opposite to the envelope slope of the transient zero-sequence current of the non-fault line, and determining the fault line selected in the step three as the fault line when the envelope slope of the fault line selected in the step three is positive and negative opposite to the envelope slope of the non-fault line, and ending the fault line selection; otherwise, returning to the first step.
2. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 1, wherein the method is characterized by comprising the following steps of: the transient zero-sequence current I of each line is the average value of three-phase current instantaneous values of each line, and is expressed as I= (I by a formula a +I b +I c ) 3, wherein I a Is the instantaneous value of phase A current of the line, I b Is the B-phase current instantaneous value of the line, I c Is the instantaneous value of the phase C current of the line.
3. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 1, wherein the method is characterized by comprising the following steps of: in the third step, the training process of the particle swarm optimization support vector machine model is as follows:
step S1, establishing a fault simulation working condition of a power distribution network, setting a power grid voltage, a node load, a line fault position, a transition resistance and a fault phase angle value range, generating a fault scene set covering the parameter range, collecting transient zero sequence currents of each line in all scenes, and forming a training data set of a particle swarm optimization support vector machine model;
s2, performing Fourier transform on transient zero-sequence current signals of each line in the training data set to obtain transient zero-sequence current frequency domain signals of each line;
s3, initializing the position and the speed of a particle swarm, and representing the position of each particle in the particle swarm as a punishment parameter and a kernel parameter set in a support vector machine model;
s4, initializing a position matrix X of the particle swarm;
s5, updating a position matrix X of the particle swarm;
s6, calculating the fitness value of each particle by adopting a fitness function;
step S7, for each particle, comparing the fitness value of the particle with the fitness value of the current optimal position of the particle, and updating when the fitness value is better;
step S8, for each particle, comparing the fitness value of the particle with the fitness value of the global optimal position of the particle swarm, and updating when the fitness value is better;
step S9, finishing iteration when the maximum iteration times are reached, otherwise, returning to step S3 to continue iteration execution, and determining a solution of the global optimal position of the particle swarm after finishing iteration as a penalty parameter and a kernel parameter in the support vector machine model;
and S10, training a particle swarm optimization support vector machine model by using a training data set to obtain a trained particle swarm optimization support vector machine model.
4. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 3, wherein the method is characterized by comprising the following steps of: in step S5, the formula adopted when updating the position matrix X of the particle swarm is:
x ij (n+1)＝x ij (n)+λF i (n)(P g (n)-x ij (n))+(1-λ)F i (n)(P i (n)-x ij (n))+F i (n)(x ij (n)-x i+1,j (n))
wherein x is ij (n) is the particle at the ith row and jth column position in the particle group at the iteration number of n, x ij (n+1) is a particle at the j-th column position of the i-th row in the particle swarm when the iteration number is n+1, λ is an inertia coefficient and λ=λ min +n×(λ max -λ min )n max N is the iteration number and takes the value of 1 to n max Natural number lambda of (a) min Lambda is the minimum coefficient of inertia max For maximum inertia coefficient, n max Is the total iteration number; f (F) i (n) is a scaling factor; p (P) i (n) is the current optimal position of the particle when the iteration number is n, P g (n) is the global optimal position of the particle swarm when the iteration number is n; x is x i+1,j (n) is the number of iterations n time-lapse dividing the particles at the position of the (i+1) th row and the (j) th column in the particle swarm.
5. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 4, wherein the method is characterized by comprising the following steps of: scaling factor F i Calculation formula of (n)The method comprises the following steps:
wherein F is min For minimum scaling factor, F max Is the maximum scaling factor.
6. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 3, wherein the method is characterized by comprising the following steps of: the fitness function used in calculating the fitness value of each particle in step S6 is a rastigin function or a Griewank function.
7. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 3, wherein the method is characterized by comprising the following steps of: in step S10, the kernel function of the particle swarm optimization support vector machine model adopts a gaussian kernel function.
8. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 1, wherein the method is characterized by comprising the following steps of: in the fourth step, the method for determining whether the envelope slope of the transient zero-sequence current of the fault line selected in the third step is positive and negative, and when the envelope slope of the transient zero-sequence current of the non-fault line is positive and negative, the method for determining the envelope of the transient zero-sequence current of any line is as follows:
a1, selecting the maximum/minimum value of the transient zero sequence current of the line;
step A2, performing interpolation operation on a sequence formed by maximum/minimum values to obtain an upper envelope line and a lower envelope line of a signal;
and A3, obtaining the average value of the upper envelope curve and the lower envelope curve to obtain the envelope curve of the signal.
9. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 8, wherein the method is characterized by comprising the following steps of: and A2, performing interpolation operation on the sequence formed by the maximum value and the minimum value, wherein Newton interpolation is adopted.
10. The power distribution network fault line selection method based on the particle swarm optimization support vector machine according to claim 8, wherein the method is characterized by comprising the following steps of: and (3) when the average value of the upper envelope curve and the lower envelope curve is calculated in the step A3, adopting a geometric average value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310512915.XA CN116466189A (en) | 2023-05-09 | 2023-05-09 | Power distribution network fault line selection method based on particle swarm optimization support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310512915.XA CN116466189A (en) | 2023-05-09 | 2023-05-09 | Power distribution network fault line selection method based on particle swarm optimization support vector machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116466189A true CN116466189A (en) | 2023-07-21 |
Family
ID=87177088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310512915.XA Pending CN116466189A (en) | 2023-05-09 | 2023-05-09 | Power distribution network fault line selection method based on particle swarm optimization support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116466189A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203456A (en) * | 2016-07-20 | 2016-12-07 | 西安科技大学 | Coal dust Algorithm for Overlapping Granule separation method based on improved differential evolution particle cluster algorithm |
| CN109344918A (en) * | 2018-12-05 | 2019-02-15 | 国网陕西省电力公司宝鸡供电公司 | Based on the big data distribution network fault line selection analysis method for improving particle swarm algorithm |
| CN113820566A (en) * | 2021-10-10 | 2021-12-21 | 西安科技大学 | Coal mine power grid leakage selecting method |
-
2023
- 2023-05-09 CN CN202310512915.XA patent/CN116466189A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203456A (en) * | 2016-07-20 | 2016-12-07 | 西安科技大学 | Coal dust Algorithm for Overlapping Granule separation method based on improved differential evolution particle cluster algorithm |
| CN109344918A (en) * | 2018-12-05 | 2019-02-15 | 国网陕西省电力公司宝鸡供电公司 | Based on the big data distribution network fault line selection analysis method for improving particle swarm algorithm |
| CN113820566A (en) * | 2021-10-10 | 2021-12-21 | 西安科技大学 | Coal mine power grid leakage selecting method |
Non-Patent Citations (2)
| Title |
|---|
| 谢建宏;: "智能结构损伤自诊断的PSO-LSWSVM方法", 计算机应用研究, vol. 34, no. 12, pages 3660 - 3662 * |
| 邹心遥;陈敬伟;姚若河;: "采用粒子群优化的SVM算法在数据分类中的应用", 华侨大学学报(自然科学版), no. 02, pages 171 - 174 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110082640B (en) | Distribution network single-phase earth fault identification method based on long-time memory network | |
| Brandwajn et al. | Severity indices for contingency screening in dynamic security assessment | |
| CN108667005B (en) | Power grid static and dynamic combination vulnerability assessment method considering new energy influence | |
| CN112748359A (en) | Power distribution network ground fault identification method and system based on random forest | |
| CN112017070A (en) | Method and system for evaluating transient stability of power system based on data enhancement | |
| Rueda et al. | Heuristic optimization based approach for identification of power system dynamic equivalents | |
| CN110907754A (en) | Fault line severity evaluation method based on PSD-BPA | |
| CN115688574A (en) | Transient stability online evaluation method and system for power system | |
| CN112072651B (en) | Transient voltage instability and power angle instability identification method based on transient energy function | |
| CN103825270B (en) | A kind of power distribution network three-phase state estimates the processing method of Jacobian matrix constant | |
| Gupta et al. | Power system network equivalents: Key issues and challenges | |
| CN116466189A (en) | Power distribution network fault line selection method based on particle swarm optimization support vector machine | |
| CN111722053A (en) | Multi-energy complementary micro-grid fault rapid identification method and system | |
| CN109861293B (en) | Method for evaluating influence of photovoltaic uncertainty on small signal stability of power system | |
| CN112285482A (en) | Active power distribution network fault determination method and system | |
| CN115954956A (en) | Method and system for evaluating access capacity of distributed power supply of power distribution network | |
| Heidari et al. | Electromagnetic transients simulation-based surrogate models for tolerance analysis of FACTS apparatus | |
| CN110988590B (en) | PCA-SVM model-based distribution network line selection method and system | |
| Ramirez-Gonzalez et al. | Evaluation of Static Network Equivalent Models for N-1 Line Contingency Analysis | |
| Wang et al. | An identification method for power grid error parameters based on sensitivity analysis and deep residual network. | |
| CN117368648B (en) | Power distribution network single-phase earth fault detection method, system, equipment and storage medium | |
| CN111293701B (en) | Method and device for estimating sunken area of power distribution network containing distributed photovoltaic | |
| CN118523316B (en) | Dominant instability mode discrimination method based on transient response and line state information | |
| Bais et al. | Fault Classification Using Hybrid FCN-BiLSTM Model in Grid Integrated with Distributed Generators | |
| CN114510837A (en) | Power transmission line operation scene generation method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230721 |