CN112557808A - Single-phase earth fault positioning method for power distribution network - Google Patents
Single-phase earth fault positioning method for power distribution network Download PDFInfo
- Publication number
- CN112557808A CN112557808A CN202011221476.XA CN202011221476A CN112557808A CN 112557808 A CN112557808 A CN 112557808A CN 202011221476 A CN202011221476 A CN 202011221476A CN 112557808 A CN112557808 A CN 112557808A
- Authority
- CN
- China
- Prior art keywords
- fault
- neural network
- particle
- power distribution
- wavelet neural
- 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.)
- Withdrawn
Links
Images
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
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- 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
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Locating Faults (AREA)
Abstract
The invention relates to a single-phase earth fault positioning method for a power distribution network, which comprises the steps of analyzing the transient characteristics of a single-phase fault of a low-current earth system, establishing a single-phase earth fault positioning model of the power distribution network based on a wavelet neural network, and initializing the weight and the threshold of the wavelet neural network model; performing particle type fitness calculation on the weight and the threshold of the initialized wavelet neural network model by using an improved particle swarm algorithm, solving the individual optimum of each particle, solving the global optimum value of the whole population, optimizing the particle speed and position to obtain the optimal weight and threshold, and sending the optimal weight and threshold into the wavelet neural network model for updating; and based on the optimal weight and threshold, positioning the single-phase earth fault point of the power distribution network through a wavelet neural network model. The invention combines the improved particle swarm algorithm with good global optimization capability and the wavelet neural network algorithm, establishes the mapping between the fault characteristics and the fault point position, and improves the fault positioning precision and accuracy.
Description
Technical Field
The invention belongs to the technical field of single-phase earth fault positioning of a power distribution network, and particularly relates to a single-phase earth fault positioning method of the power distribution network based on an improved particle swarm algorithm and a wavelet neural network.
Background
In a medium and low voltage power grid, the grounding mode mainly adopts 3 modes of low current grounding, neutral point ungrounded, arc suppression coil grounding and high impedance grounding, and the 10kV power system in China mostly adopts the running mode of neutral point ungrounded or arc suppression coil grounding.
The fault which is more frequently occurred in the small current grounding system is a single-phase grounding short-circuit fault, when the system has the single-phase grounding fault, the phase voltage of the non-fault two phases can be raised, but the line voltage is still symmetrical, and at the moment, the system can still continuously run for one to two hours. However, if the device is operated for a long time, insulation weak links can be broken down, so that interphase short circuit faults are caused, and heavy loss is caused to a power system. Therefore, the deep research on the fault location of the single-phase grounding short circuit of the small-current grounding system is necessary for quickly and accurately eliminating the fault.
Disclosure of Invention
The invention aims to solve the technical problem of providing a power distribution network single-phase earth fault positioning method based on an improved particle swarm algorithm and a wavelet neural network, and quickly and accurately realizing the accurate positioning of a power distribution network single-phase earth fault point. The technical scheme adopted by the invention for solving the technical problems is as follows:
a single-phase earth fault positioning method for a power distribution network analyzes the transient characteristics of single-phase faults of a low-current earth system, establishes a single-phase earth fault positioning model of the power distribution network based on a wavelet neural network, and initializes the weight and the threshold of the wavelet neural network model;
the particle swarm optimization has the advantage of global optimization capability, particle type fitness calculation is carried out on the weight and the threshold of the initialized wavelet neural network model by utilizing the particle swarm optimization, the individual optimum of each particle is solved, then the global optimum value of the whole group is solved, then the particle speed and the position are optimized, the optimum weight and the optimum threshold are finally obtained, and the optimum weight and the optimum threshold are sent to the wavelet neural network model for updating;
and based on the optimal weight and threshold, positioning the single-phase earth fault point of the power distribution network through a wavelet neural network model.
The method for extracting the transient characteristics of the single-phase fault and the method for positioning the single-phase earth fault point of the power distribution network based on the wavelet neural network model are the prior art and are not described herein again.
The invention has the beneficial effects that:
the invention provides a power distribution network single-phase earth fault positioning method based on an improved particle swarm algorithm and a wavelet neural network on the basis of the existing single-phase earth fault positioning method. The invention combines the improved particle swarm algorithm with good global optimization capability and the wavelet neural network algorithm, establishes the mapping between the fault characteristics and the fault point position, and improves the fault positioning precision and accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are specific embodiments of the invention, and that other drawings within the scope of the present application can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a schematic diagram of zero sequence current distribution when a small current grounding system is grounded in a single phase according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the training process of the wavelet neural network according to the embodiment of the present invention;
fig. 3 is a schematic diagram of a fault location method based on an improved particle swarm algorithm and a wavelet neural network according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the drawings and examples, including but not limited to the following examples.
A power distribution network single-phase earth fault positioning method based on an improved particle swarm algorithm and a wavelet neural network comprises the following steps:
When a certain outlet of the small-current grounding system is in single-phase grounding short circuit, the voltage to ground of a non-fault phase is increased, and large transient zero-sequence fault current is generated, but the line voltage still keeps symmetry, so that continuous power supply of a user is not influenced, and the system can continue to operate for a period of time. However, if the fault is not eliminated for a long time, the fault is amplified to be an interphase short-circuit fault, normal power supply is influenced, even equipment is damaged, and the safe operation of the system is damaged.
Fig. 1 is a schematic diagram of zero-sequence current distribution when a small-current grounding system according to an embodiment of the present invention is grounded in a single phase, where the diagram includes L1、L2、L3There are three lines in total. Denoted by L in FIG. 13The transient zero sequence current distribution situation of the line A phase grounding fault is drawn as an example when the small current grounding system is grounded in a single phase. When a single-phase earth fault occurs, the voltage to earth of the fault phase becomes zero, and the capacitance current also becomes zero; not the faulty line L1、L2Occurring zero sequence current i01、i02Is the sum of the capacitance currents of the non-fault phases of the line, i.e. i01＝iB1+iC1，i02＝iB2+iC2The direction is that the bus points to the line and leads the zero-sequence voltage by 90 degrees; faulty line L3Is equal to the sum of all capacitance currents of the system non-fault line in value, namely 3iC＝-(3i01+3i02). Faulty line L3The zero sequence current value of the non-fault line is far larger than that of the non-fault line, and the direction of the zero sequence current in the non-fault line is the same as that of the zero sequence current in the non-fault lineThe opposite direction, i.e. pointing from the line to the bus, lags the zero sequence voltage by 90 °.
In the non-grounding mode of the neutral point, the current of the fault point is the sum of non-fault relative-to-ground capacitance currents of all lines in the whole system, i.e. iC＝iB1+iC1+iB2+iC2+iB3+iC3(ii) a In the mode that the neutral point is grounded through the arc suppression coil, the inductive current i generated by the arc suppression coil is generated under the action of zero sequence voltageLThe current of the fault point is the sum i of the capacitance-to-ground currents of the non-fault phases of all lines in the whole systemCAnd the inductor current iLA vector sum of iK＝iC+iL。
And 2, researching a wavelet neural network based fault positioning method.
Wavelet transform is widely applied to analyzing non-stationary signals, and joint local analysis in time domain and frequency domain can be realized. One of the advantages of wavelet transform is the diversity of wavelet function, which shows great advantage in extracting information in signals, and the analysis of time domain signals and frequency domain signals is completed by scaling operation and translation operation.
The wavelet neural network is formed by adding a wavelet transformation theory to the feedforward neural network, the algorithm combines the advantages of the wavelet transformation theory and the feedforward neural network, the good localization property is shown, the excellent capability is realized when the parallel processing is carried out on large-scale data, and meanwhile, the self-learning capability, the good convergence speed and the approaching capability are realized.
The wavelet neural network structure model is divided into 3 layers including an input layer, a hidden layer and an output layer. The input layer is a modulus maximum value of the wavelet transformation of the fault signal, the output layer comprises a single neuron, and the value of the neuron reflects the position of a fault point and is represented by a normalized value of the distance between the fault point and a bus.
The wavelet neural network training algorithm is as follows:
the method comprises the following steps that a gradient method, namely a fastest descent method is adopted in the training process of the wavelet neural network to solve the problem, forward propagation is adopted firstly, calculation is carried out layer by layer from an input layer of the network, the output of each layer is obtained by calculating an input sample, and finally the output of an output layer of the network is obtained; and then, calculating layer by layer from the output layer of the network by adopting a back propagation process, and correcting the weight. The two propagation processes are repeatedly alternated until convergence. And continuously correcting the weight of each layer to obtain the minimum value of the target error.
Fig. 2 is a schematic diagram illustrating a training process of the wavelet neural network according to the embodiment of the present invention. The number of nodes in the input layer is m (k is 1, 2.. times, m), the number of wavelet elements in the hidden layer is N (j is 1, 2.. times, N), the number of nodes in the output layer is N (i is 1, 2.. times, N), and x iskFor input samples in the input layer, yiRepresenting the actual output value in the output layer,
is the desired output value, ω, of the output layerkjRepresenting the connection weight, omega, of the input layer node corresponding to the hidden layer nodejiAnd representing the connection weight value corresponding to the hidden layer node and the output layer node. In the hidden layer node, ajAs a translation factor, bjIs the contraction factor. Wavelet neurons in the hidden layer select Mexican hat wavelet functions, and output layer nodes adopt Sigmoid functions.
The input of the jth wavelet element in the hidden layer is:
the output is:
the output of the ith node of the neural network output layer is as follows:
the output error energy function is:
the wavelet transformation is a modern signal processing mode, is very suitable for analyzing the transient process of a power system, and can realize accurate positioning of faults by combining with good nonlinear mapping capability of input/output of a neural network. However, the problems of low convergence rate and local minimum value exist in the traditional neural network algorithm, the Particle Swarm Optimization (PSO) is combined, and the particle swarm optimization is organically combined with the wavelet neural network according to the characteristic that the particle swarm optimization has global optimization capability, so that the purpose of improving the fault positioning accuracy and precision is achieved.
And 3, researching the wavelet neural network based on the optimization of the improved particle swarm optimization.
The PSO algorithm is a group intelligent evolution calculation theory provided according to the research on the predation behavior of the bird group, and the key point of the idea is to randomly initialize a group of particles, comprehensively analyze the flight experience of individuals and groups of the group of particles, dynamically adjust the speed and the position of a particle swarm, finally search in a solution space and find an optimal solution through iteration.
Xi＝(xi1+xi2+···+xid+···+xiD)
In the formula: xiAnd searching the position of the ith particle in a population consisting of m particles in the D-dimensional space.
Vi＝(vi1+vi2+···+vid+···+viD)
In the formula: vi—XiThe speed of (2).
In the iterative process, updating the particles in the population according to two extreme values of speed and position, searching the optimal solution of the individual particles and the optimal solution of the population according to the particle fitness value, and respectively marking the optimal solutions as individual extreme values PbestiAnd global extreme value Gbesti。
The updated formula of particle velocity and position can be expressed as:
Vid(t+1)＝ωVid(t)+c1r1(pid-xid)+c2r2(pgd-xid)
Xid(t+1)＝Xid(t)+Vid(t+1)
in the formula: t is the number of iterations; i-particle number; d-the dimension of space D; xid(t) -the updated position of the particle i after the t-th iteration in the d-dimension of the space; vid(t) -speed; p is a radical ofid-an individual extremum; p is a radical ofgd-a global extremum; c. C1、c2The random acceleration weights updated for the individual extrema and the global extrema respectively are usually taken as c1＝c 22; omega-inertia weight coefficient, the calculation formula is omegamax-t*(ωmax-ωmin)/tmaxWherein ω ismin＝0.4，ωmax＝0.9。
Fig. 3 is a schematic diagram of a fault location method based on an improved particle swarm algorithm and a wavelet neural network according to an embodiment of the present invention. The steps of obtaining the optimal weight and threshold of the wavelet neural network model by utilizing the particle swarm algorithm are as follows:
s1, initializing a population;
s2, carrying out real number coding on the initial weight value and the threshold value of the neuron;
inputting data and preprocessing the data;
s3, calculating the particle fitness;
s4, finding out the individual optimum of each particle;
s5, solving the global optimal quality value of the whole population;
s6, optimizing the speed and the position of the particles;
s7, judging whether the end condition is met, if not, turning to the step S3; if yes, obtaining the optimal weight value and the threshold value.
Finally, it is to be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the technical solutions of the present invention, and the scope of the present invention is not limited thereto. Those skilled in the art will understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.
Claims (6)
1. A single-phase earth fault positioning method of a power distribution network is characterized in that single-phase fault transient characteristics of a low-current earth system are analyzed, a single-phase earth fault positioning model of the power distribution network based on a wavelet neural network is established, and weight and threshold values of the wavelet neural network model are initialized;
performing particle type fitness calculation on the weight and the threshold of the initialized wavelet neural network model by using an improved particle swarm algorithm, solving the individual optimum of each particle, solving the global optimum value of the whole population, optimizing the particle speed and position to obtain the optimal weight and threshold, and sending the optimal weight and threshold into the wavelet neural network model for updating;
and based on the optimal weight and threshold, positioning the single-phase earth fault point of the power distribution network through a wavelet neural network model.
2. The method for positioning the single-phase earth fault of the power distribution network according to claim 1, wherein the step of obtaining the optimal weight and threshold of the wavelet neural network model by using the particle swarm algorithm comprises the following steps:
s1, initializing a population;
s2, carrying out real number coding on the initial weight value and the threshold value of the neuron;
inputting data and preprocessing the data;
s3, calculating the particle fitness;
s4, finding out the individual optimum of each particle;
s5, solving the global optimal quality value of the whole population;
s6, optimizing the speed and the position of the particles;
s7, judging whether the end condition is met, if not, turning to the step S3; if yes, obtaining the optimal weight value and the threshold value.
3. The method for locating the single-phase earth fault of the power distribution network according to claim 2, wherein after the single-phase earth fault occurs, the voltage to earth of the fault phase becomes zero, and the capacitance current also becomes zero; the magnitude of zero-sequence current appearing in a non-fault circuit is the sum of capacitance currents of non-fault phases of the circuit, and the direction is that a bus points to the circuit and leads the zero-sequence voltage by 90 degrees; the zero sequence current of the faulted line is numerically equal to the sum of all the capacitive currents of the system non-faulted line and is in the opposite direction to the zero sequence current in the non-faulted line, i.e. directed from the line to the bus and lags the zero sequence voltage by 90 °.
4. The single-phase earth fault location method for the power distribution network according to claim 2, wherein in the non-earth mode of the neutral point, the current of the fault point is the sum of the non-fault relative earth capacitance current of each line in the whole system; in the mode of grounding the neutral point through the arc suppression coil, the current of the fault point is the vector sum of the sum of capacitance current to ground and inductance current of each non-fault phase of each line in the whole system.
5. The single-phase earth fault location method of the power distribution network according to claim 2, wherein the wavelet neural network training algorithm is as follows:
the training process of the wavelet neural network adopts a gradient method, firstly adopts forward propagation, and calculates from the input layer of the network layer to layer, the output of each layer is calculated by an input sample, and finally the output of the output layer of the network is obtained; then, calculating layer by layer from the output layer of the network by adopting a back propagation process, and correcting the weight; the two propagation processes are repeatedly alternated until convergence; and continuously correcting the weight of each layer to obtain the minimum value of the target error.
6. The single-phase earth fault location method for the power distribution network according to claim 2, wherein a calculation formula of the improved particle swarm optimization is as follows:
Xi＝(xi1+xi2+…+xid+…+xiD)；
in the formula: xi-searching in the D-dimensional space for the location of the ith particle in a population of m particles;
Vi＝(vi1+vi2+…+vid+…+viD)；
in the formula: vi—XiThe speed of (d);
in the iterative process, updating the particles in the population according to two extreme values of speed and position, searching the optimal solution of the individual particles and the optimal solution of the population according to the particle fitness value, and respectively marking the optimal solutions as individual extreme values PbestiAnd global extreme value Gbesti；
The updated formula of particle velocity and position can be expressed as:
Vid(t+1)＝ωVid(t)+c1r1(pid-xid)+c2r2(pgd-xid)；
Xid(t+1)＝Xid(t)+Vid(t+1)；
in the formula: t is the number of iterations; i-particle number; d-the dimension of space D; xid(t) -the updated position of the particle i after the t-th iteration in the d-dimension of the space; vid(t) -speed; p is a radical ofid-an individual extremum; p is a radical ofgd-a global extremum; c. C1、c2Respectively updating random acceleration weights for the individual extremum and the global extremum, and taking c1＝c22; omega-inertia weight coefficient, the calculation formula is omegamax-t*(ωmax-ωmin)/tmaxWherein ω ismin＝0.4，ωmax＝0.9。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011221476.XA CN112557808A (en) | 2020-11-05 | 2020-11-05 | Single-phase earth fault positioning method for power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011221476.XA CN112557808A (en) | 2020-11-05 | 2020-11-05 | Single-phase earth fault positioning method for power distribution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112557808A true CN112557808A (en) | 2021-03-26 |
Family
ID=75041441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011221476.XA Withdrawn CN112557808A (en) | 2020-11-05 | 2020-11-05 | Single-phase earth fault positioning method for power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112557808A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113933650A (en) * | 2021-10-13 | 2022-01-14 | 国网江苏省电力有限公司镇江供电分公司 | Low-current ground fault line selection method |
| CN117892117A (en) * | 2024-03-13 | 2024-04-16 | 国网山东省电力公司邹城市供电公司 | Fault positioning method and system for power transmission line of power distribution network |
| CN117892117B (en) * | 2024-03-13 | 2024-05-31 | 国网山东省电力公司邹城市供电公司 | Fault positioning method and system for power transmission line of power distribution network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103884966A (en) * | 2014-04-15 | 2014-06-25 | 河海大学常州校区 | Power distribution network low-current single-phase earth fault positioning method based on neural network |
| CN107589342A (en) * | 2017-09-04 | 2018-01-16 | 云南电网有限责任公司电力科学研究院 | A kind of one-phase earthing failure in electric distribution network localization method and system |
| CN111178430A (en) * | 2019-12-28 | 2020-05-19 | 上海电机学院 | Particle swarm optimization-based rectifier circuit fault diagnosis method for neural network |
-
2020
- 2020-11-05 CN CN202011221476.XA patent/CN112557808A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103884966A (en) * | 2014-04-15 | 2014-06-25 | 河海大学常州校区 | Power distribution network low-current single-phase earth fault positioning method based on neural network |
| CN107589342A (en) * | 2017-09-04 | 2018-01-16 | 云南电网有限责任公司电力科学研究院 | A kind of one-phase earthing failure in electric distribution network localization method and system |
| CN111178430A (en) * | 2019-12-28 | 2020-05-19 | 上海电机学院 | Particle swarm optimization-based rectifier circuit fault diagnosis method for neural network |
Non-Patent Citations (2)
| Title |
|---|
| 张士庭等: "《县级无人值班变电站运行与管理》", 31 January 2015 * |
| 林正馨: "《电力系统继电保护》", 31 May 1986 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113933650A (en) * | 2021-10-13 | 2022-01-14 | 国网江苏省电力有限公司镇江供电分公司 | Low-current ground fault line selection method |
| CN117892117A (en) * | 2024-03-13 | 2024-04-16 | 国网山东省电力公司邹城市供电公司 | Fault positioning method and system for power transmission line of power distribution network |
| CN117892117B (en) * | 2024-03-13 | 2024-05-31 | 国网山东省电力公司邹城市供电公司 | Fault positioning method and system for power transmission line of power distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cho et al. | Feature selection and parameters optimization of SVM using particle swarm optimization for fault classification in power distribution systems | |
| CN110082640B (en) | Distribution network single-phase earth fault identification method based on long-time memory network | |
| Sadeh et al. | A new and accurate fault location algorithm for combined transmission lines using adaptive network-based fuzzy inference system | |
| CN103728535B (en) | A kind of extra-high-voltage direct-current transmission line fault location based on wavelet transformation transient state energy spectrum | |
| CN102129013B (en) | Distribution network fault location method utilizing natural frequency and artificial neural network | |
| Ayyagari | Artificial neural network based fault location for transmission lines | |
| Saravanan et al. | A comparitive study on ANN based fault location and classification technique for double circuit transmission line | |
| CN110687395A (en) | Fault line selection method for power distribution network with distributed power supply based on deep belief network | |
| Ray et al. | Application of extreme learning machine for underground cable fault location | |
| CN107589342A (en) | A kind of one-phase earthing failure in electric distribution network localization method and system | |
| CN112180210A (en) | Power distribution network single-phase earth fault line selection method and system | |
| Mishra et al. | A universal high impedance fault detection technique for distribution system using S-transform and pattern recognition | |
| Fan et al. | Transmission line fault location using deep learning techniques | |
| CN112557808A (en) | Single-phase earth fault positioning method for power distribution network | |
| Zhang et al. | Detection of single-phase-to-ground faults in distribution networks based on Gramian Angular Field and Improved Convolutional Neural Networks | |
| CN117630569A (en) | Low-current single-phase earth fault multi-criterion fusion line selection method based on GRU neural network | |
| Kou et al. | Transmission line fault identification based on BP neural network | |
| Sahel et al. | Wavelet energy moment and neural networks based particle swarm optimisation for transmission line protection | |
| CN116482571A (en) | CNN-based low-current single-phase earth fault multi-criterion fusion line selection method | |
| Tong et al. | A fault location method for active distribution network with renewable sources based on bp neural network | |
| Shaaban et al. | Wavelet signal energy with RBFNN and GRNN for fault classification in transmission line with series compensator | |
| Jain et al. | Classification and location of single line to ground faults in double circuit transmission lines using artificial neural networks | |
| Martin et al. | Classification of faults in double circuit lines using wavelet transforms | |
| Kezunovic et al. | Advanced approaches for detecting and diagnosing transients and faults | |
| Eldin et al. | High impedance fault detection in EHV series compensated lines using the wavelet transform |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210326 |
|
| WW01 | Invention patent application withdrawn after publication |