CN116298670A - Intelligent fault positioning method and system suitable for multi-branch distribution line - Google Patents
Intelligent fault positioning method and system suitable for multi-branch distribution line Download PDFInfo
- Publication number
- CN116298670A CN116298670A CN202310042798.5A CN202310042798A CN116298670A CN 116298670 A CN116298670 A CN 116298670A CN 202310042798 A CN202310042798 A CN 202310042798A CN 116298670 A CN116298670 A CN 116298670A
- Authority
- CN
- China
- Prior art keywords
- fault
- branch
- line
- intelligent
- module
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 30
- 230000015654 memory Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 22
- 238000005259 measurement Methods 0.000 claims description 19
- 238000004088 simulation Methods 0.000 claims description 15
- 210000002569 neuron Anatomy 0.000 claims description 10
- 210000004027 cell Anatomy 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 8
- 230000007787 long-term memory Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000011161 development Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 11
- 230000004807 localization Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G01R31/088—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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- 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)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Locating Faults (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an intelligent fault positioning method and system suitable for a multi-branch distribution line, which belong to the technical field of fault positioning of distribution lines, and are used for acquiring phase voltage and phase current waveform information of the head end of a first-stage branch line and current effective values acquired by intelligent ammeter at the tail end of a second-stage branch line; judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line; processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location; and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line. The invention realizes the accurate positioning of fault points under the condition of multi-branch distribution lines, has stronger universality, combines the training of an actual distribution network topological graph, has extremely high precision and strong reliability of the trained positioning network, and has a certain development prospect.
Description
Technical Field
The invention relates to the technical field of power distribution network line fault positioning, in particular to an intelligent fault positioning method and system suitable for multi-branch power distribution lines.
Background
The reliability of the distribution network is greatly affected by the duration of the fault. Accurate and rapid fault location is critical to achieving faster fault clearance and reduced downtime, helping to improve the reliability of the system. However, the topology structure of the power distribution network is very complex due to the fact that the power distribution network comprises a plurality of branches. The distribution network equipment is distributed more dispersedly, and the installation of a high-precision measuring device at the tail end of each branch is not practical. Therefore, power distribution network fault location is a troublesome problem.
Fault localization techniques can be divided into three categories, impedance-based, traveling wave-based, and Machine Learning (ML) -based algorithms. Impedance-based methods use voltage and current measurements to estimate fault location. These methods are easy to implement but are susceptible to multi-branching, metering errors and system scale. With the increasing requirements on positioning accuracy, traveling wave-based methods are increasingly being used in power transmission systems. However, there have been few studies on the use of traveling wave based methods for fault localization of power distribution networks. The main reason is that the traveling wave is easy to reflect and refract when transmitted in the multi-branch distribution network, and the reflecting and refracting behaviors are complex. Detection and accurate fault location of the traveling wave head is very difficult. Some researchers have utilized microphase measurement devices to improve positioning accuracy, which are less affected by fault type and resistance, but they require high quality sampling rates, which is not common in power distribution networks.
At present, a large number of intelligent electric meters and intelligent electronic devices are arranged in a power distribution network, the function of an intelligent measurement technology is fully exerted, and the safety operation level of the power industry is very necessary. The distribution network accumulates a large amount of sample data under the support of industrial informatization. These conditions provide opportunities for machine learning based methods that arise in the climax of artificial intelligence. In the prior art, the simulation data of various fault scenes are utilized to train a model based on machine learning, so that a better positioning result is obtained. This is because conventional fault locating methods make some systematic assumptions about the distribution network, for example, neglecting to some extent the effects of fault type, resistance and line branches on the locating result. Herein, the system assumes what is referred to as an "uncontrollable factor" of the physical model. The machine learning-based method expresses the 'uncontrollable factors' through the super parameters, so that the fitting result is closer to the actual physical model.
Disclosure of Invention
The invention aims to provide an intelligent fault positioning method and system which fully consider the influences of measurement errors and line parameter errors, are more accurate in fault positioning of a multi-branch distribution line and are suitable for the multi-branch distribution line, and solve at least one technical problem in the background technology.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in one aspect, the present invention provides an intelligent fault location method suitable for a multi-branch distribution line, including:
performing fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location;
judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line;
and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line.
Preferably, based on the current effective value that the smart electric meter of second grade branch circuit terminal gathered, judge the fault line, include: collecting all currents I of a secondary branch terminal intelligent ammeter connected with a feeder line ki (1. Ltoreq.i.ltoreq.n) to form a vector I o The method comprises the steps of carrying out a first treatment on the surface of the Vector I e Representing a collection of branches with only small currents, the value of which is smaller than a threshold gamma; 0<p<n; n, O the nodes on the primary and secondary branches, respectively, if p=q, means that only one secondary branch failsThe line being N kp O kp The method comprises the steps of carrying out a first treatment on the surface of the When p is equal to q, the main branch N is represented k(p-1) N kp The fault can cause the power failure of a plurality of secondary branches, and the line where the fault is located can be judged.
Preferably, the power distribution network fault distance measurement model comprises a self-encoder module and a long-period memory network module which are connected in parallel; the self-encoder module is used for reducing the dimension of the waveform information; the long-term and short-term memory network module is used for multiplying the cells in different time periods by taking the extracted time-related characteristic sequences as input.
Preferably, t AEs are connected in parallel to form a self-encoder module layer; the value of t is determined by the length of the input waveform; in the self-encoder module layer training process, the label output of the t self-encoder has the same dimension as the input vector, and the t self-encoder loss function is as follows:
wherein the method comprises the steps of
Representing a dataset S t Reconstructed samples of the input samples of (a); w (W) ti Representing the weight of the t-th self-encoder; h t Is the number of neurons in the hidden layer; lambda, alpha are regularization parameters for adjusting the penalty term weights; KL (ρ) ti ) For Kullback-Leibler divergence, < >>
ρ ti An average activation function value representing hidden layer neuron i; ρ is a sparsity parameter.
Preferably, the long-period and short-period memory network module multiplies the cells in different time periods, so that the output or error of the previous time step is the same as the output of the next time step; the loss function for training the long-short-term memory network is the mean square error:
wherein the method comprises the steps ofS is the total number of training samples,
the estimation result given for LSTM model, y i Representing the true value of sample i.
Preferably, in training the regression distribution network fault-location model, a loss function is defined to account for the effects of the self-encoder module and the long-term memory network module: l=l PAE +L LSTM ；
And determining the super parameters by adopting a grid searching and cross-validation method, and using a Sigmoid function as an activation function of a full-connection layer in the long-period memory network module.
In a second aspect, the present invention provides an intelligent fault location system for a multi-drop power distribution line, comprising:
the acquisition module is used for carrying out fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
the judging module is used for judging the fault line based on the effective current value acquired by the intelligent ammeter at the tail end of the secondary branch line;
the distance measurement module is used for processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault distance measurement model to finish fault point position distance measurement;
and the positioning module is used for integrating the fault line judgment result and the fault point location distance measurement to complete fault positioning of the fault multi-branch distribution line.
In a third aspect, the present invention provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement an intelligent fault localization method as described above for a multi-branch distribution line.
In a fourth aspect, the present invention provides a computer program product comprising a computer program for implementing the intelligent fault location method for a multi-branch distribution line as described above when run on one or more processors.
In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is coupled to the memory and the computer program is stored in the memory, the processor executing the computer program stored in the memory when the electronic device is operating to cause the electronic device to execute instructions implementing the intelligent fault location method as described above for the multi-branch distribution line.
The invention has the beneficial effects that: through training a large number of high-dimensional samples, accurate fault point ranging under a multi-branch power distribution system can be realized; the fault point accurate positioning under the condition of the multi-branch distribution line is realized, and the application in actual engineering is realized; the method has strong universality, combines the practical distribution network topological graph training, has extremely high accuracy and strong reliability of the trained positioning network, and has a certain development prospect.
The advantages of additional aspects of the invention will be set forth in part in the description which follows, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of an intelligent fault locating method suitable for a multi-branch distribution line according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of data acquisition according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a power distribution network model according to an embodiment of the present invention.
Fig. 4 is a structural diagram of a constructed fault location model according to an embodiment of the present invention.
Fig. 5 is a schematic diagram showing the distribution of errors of AB-G faults with fault positions according to an embodiment of the present invention.
Fig. 6 is a schematic diagram showing an influence relationship between a ground resistance and a fault phase angle according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements throughout or elements having like or similar functionality. The embodiments described below by way of the drawings are exemplary only and should not be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all 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.
It will be further 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 prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, and/or groups thereof.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
In order that the invention may be readily understood, a further description of the invention will be rendered by reference to specific embodiments that are illustrated in the appended drawings and are not to be construed as limiting embodiments of the invention.
It will be appreciated by those skilled in the art that the drawings are merely schematic representations of examples and that the elements of the drawings are not necessarily required to practice the invention.
Example 1
In this embodiment 1, there is provided an intelligent fault location system suitable for a multi-branch distribution line, including:
the acquisition module is used for carrying out fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
the distance measurement module is used for processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault distance measurement model to finish fault point position distance measurement;
the judging module is used for judging the fault line based on the effective current value acquired by the intelligent ammeter at the tail end of the secondary branch line;
and the positioning module is used for integrating the fault line judgment result and the fault point location distance measurement to complete fault positioning of the fault multi-branch distribution line.
In this embodiment 1, with the system described above, an intelligent fault locating method suitable for a multi-branch distribution line is implemented, including:
performing fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location;
judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line;
and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line.
Based on the current effective value that the smart electric meter of second grade branch circuit terminal gathered, judge the fault line, include: collecting all currents I of a secondary branch terminal intelligent ammeter connected with a feeder line ki (1. Ltoreq.i.ltoreq.n) to form a vector I o The method comprises the steps of carrying out a first treatment on the surface of the Vector I e Representing a collection of branches with only small currents, the value of which is smaller than a threshold gamma; 0<p<n; n, O the nodes on the primary and secondary branches, respectively, and if p=q, it means that only one secondary branch fails, the failure line being N kp O kp The method comprises the steps of carrying out a first treatment on the surface of the When p is equal to q, the main branch N is represented k(p-1) N kp The fault can cause the power failure of a plurality of secondary branches, and the line where the fault is located can be judged.
The power distribution network fault distance measurement model comprises a self-encoder module and a long-period memory network module which are connected in parallel; the self-encoder module is used for reducing the dimension of the waveform information; the long-term and short-term memory network module is used for multiplying the cells in different time periods by taking the extracted time-related characteristic sequences as input.
Connecting t AEs in parallel to form a self-encoder module layer; the value of t is determined by the length of the input waveform; in the self-encoder module layer training process, the label output of the t self-encoder has the same dimension as the input vector, and the t self-encoder loss function is as follows:
wherein the method comprises the steps of
Representing a dataset S t Reconstructed samples of the input samples of (a); wti represents the weight of the t-th self-encoder; h t Is the number of neurons in the hidden layer; lambda, alpha are regularization parameters for adjusting the penalty term weights; KL (ρ) ti ) For Kullback-Leibler divergence, < >>
ρ ti An average activation function value representing hidden layer neuron i; ρ is a sparsity parameter.
The long-period memory network module multiplies the cells in different time periods, so that the output or error of the previous time step is the same as the output of the next time step; the loss function for training the long-short-term memory network is the mean square error:
wherein S is the total number of training samples,
the estimation result given for LSTM model, y i Representing the true value of sample i.
When training the regression distribution network fault-location model, defining a loss function to consider the effects of the self-encoder module and the long-term and short-term memory network module: l=l PAE +L LSTM ；
And determining the super parameters by adopting a grid searching and cross-validation method, and using a Sigmoid function as an activation function of a full-connection layer in the long-period memory network module.
Example 2
As shown in fig. 1 to 4, in embodiment 2, an intelligent fault locating method suitable for a multi-branch distribution line is provided, which is used for solving the problem of fault locating of the multi-branch distribution line in the prior art that the influence of measurement errors and line parameter errors is not fully considered.
In view of this, the present invention provides an intelligent fault location method suitable for multi-branch distribution lines. The method comprises the following steps:
s1, constructing a power distribution network model, and performing fault simulation on the power distribution network model to obtain phase voltage and phase current waveform information of the head end of a primary branch line;
s2, constructing a fault ranging deep learning model by using the history and simulation fault samples, and taking the trained deep learning model as a power distribution network fault ranging model;
s3, collecting effective current values collected by the intelligent ammeter at the tail end of the secondary branch circuit, and judging a fault circuit through logic reasoning;
s4, collecting phase voltage and phase current fault waveforms of the head end of the primary branch line, inputting the waveforms into a power distribution network fault ranging model, and finishing accurate ranging of fault point positions.
S5, comprehensively judging the fault line and accurately measuring the fault point to finish fault positioning of the fault multi-branch distribution line.
The step S2 specifically comprises the following steps:
after waveform information of phase voltage and phase current is obtained, data of a previous period and a last three periods of faults are taken to carry out simulation training and fault positions, and a power distribution network fault ranging model is obtained through training;
optionally, the deep learning model is composed of a parallel self-encoder (PAE) and a long-short-term memory network (LSTM) model.
1) The PAE module is used for connecting a plurality of self encoders (such as t self encoders) in parallel to form a PAE layer in order to maintain time-related characteristics in the original data. the value of t is determined by the length of the input waveform. The PAE layer is mainly used for waveform information dimension reduction. It initially contains two symmetrical parts, an encoder and a decoder, and trains the two parts together to achieve unsupervised feature learning. The fault localization model only employs the encoder layer.
During training, the tag output of the t-th self-encoder has the same dimension as its input vector, and the t-th self-encoder loss function is:
wherein the method comprises the steps of
Representing a dataset S t A reconstructed sample of the input samples of (a). W (W) ti The weight of the t-th self-encoder is represented. H t Is the number of neurons in the hidden layer. λ, α is the regularization parameter that adjusts the penalty term weights.
KL(ρ||ρ ti ) Is Kullback-Leibler divergence, and is used for constraining the sparsity of the hidden layer neurons to keep the sparsity of the hidden layer neurons at a small value. KL divergence is a standard function that measures the difference between two contributions, and is commonly used to train a self-encoder, and can be expressed as:
rho in ti Representing the mean activation function value of the hidden layer neuron i. ρ is a sparsity parameter. By setting ρ to a small value ρ ti May remain close to zero.
2) And the LSTM module is used for taking the extracted time-dependent characteristic sequence as an input of the LSTM network. The architecture consists of LSTM cells with self-junctions. It allows the value of the incoming cell (forward pass) or gradient (backward pass) to be saved and then retrieved in the required time step. The LSTM module multiplies cells of different time periods so that the output or error of the last time step is the same as the output of the next time step. The loss function used to train the LSTM network is the Mean Square Error (MSE), as shown,
where S is the total number of training samples in LSTM,
the estimation result given for LSTM model, y i Representing the true value of sample i.
In training the regression PAE-LSTM model, a loss function is defined to take into account the effects of PAE and LSTM modules, as shown in the equation,
L＝L PAE +L LSTM
the framework determines superparameters by using grid search and cross-validation methods and uses Sigmoid functions as activation functions for the full connectivity layer in LSTM.
Step S3, fault line selection judges a fault line through a current effective value of the tail end of the secondary branch, and is specifically described as follows:
collecting all current I of SMs connected to feeder ki (1. Ltoreq.i.ltoreq.n) to form a vector I o . Vector I e Representing a collection of branches with only small currents, whose value is smaller than the threshold gamma. Here, 0<p<n. N, O represent the node on the primary leg and the secondary leg distal node, respectively. If p=q, it means that only one secondary branch fails, the failure line is N kp O kp . When p is equal to q, the main branch N is represented k(p-1) N kp A failure may result in multiple secondary branches being powered down. Thus, the line where the fault is can be judged.
And S4, accurately ranging the fault position, namely inputting the first-stage branch phase voltage and current collected after the fault into a deep learning ranging model constructed by historical data and simulation data, and directly outputting the fault point by the ranging model by utilizing nonlinear fitting capacity of deep learning.
And S5, integrating the fault lines and the fault points obtained in the steps S3 and S4 to finish accurate ranging of the multi-branch distribution line.
The performance of the method is verified by modeling a typical tree-like distribution network. The network shown in fig. 3 is modeled on a MATLAB/Simulink platform, and consists of only one primary branch and three secondary branches. The voltage of the distribution network is 10kV. Four faults were simulated, single phase earth fault (A-G), relative earth fault (AB-G), relative phase short circuit fault (AB) and three phase earth fault (ABC-G). The sampling frequency of the waveform was 10kHz. Different fault parameters such as fault distance, ground resistance, phase angle, etc. are set, as shown in table 1.
Table 1 fault sample parameters
In this embodiment, in order to evaluate the performance of the proposed positioning method, the recognition rate L of the fault line selection is adopted right And error E of fault point location err_L . The two indices are defined as follows:
L right ＝N right /N total
E err_L ＝(L pre -L act )/L total
wherein N is right For the number of correct fault line selection results, N total For the number of all test samples. L (L) pre To calculate the fault distance to the measuring device, L act For the actual fault distance L total For distance between nodes, e.g. N 11 N 12 . Table 2 shows the positioning results of the trained PAE-LSTM model in the simulated source domain. The fault line can be correctly identified for all test data. The fault point positioning error is also very low, mostly less than 2%, i.e. about 60 meters.
TABLE 2 test results for different types of faults
Since the average and maximum errors of the AB-G faults are the largest among all fault types, the effectiveness of the proposed method is discussed taking the distribution of errors of AB-G faults with fault location as shown in fig. 5 for example. As can be seen from fig. 5, the positioning error eerr_l increases as the distance from the measuring device increases. The errors of the lines 1, 2 and 3 which are closer to each other are smaller than those of the lines 6 and 7 which are farther from each other. Faults with relatively large relative positions (e.g., 80% and 90%) produce larger errors than faults with relatively small relative positions within the same line segment. Obviously, as the distance of failure increases, the performance of the PAE-LSTM model decreases. But the worst case is acceptable because the error is still below 3%.
In this embodiment, the influence of the ground resistance and the phase angle of the fault was also studied, as shown in fig. 6. The error of different fault phase angles does not vary much. The average error of 90 degrees is larger and the average error of 30 degrees is the smallest. The maximum error difference is only 0.0285%. The variation of the average positioning error with ground resistance is also illustrated. Although the effect of ground resistance is reduced by normalization, the average error increases slightly as ground resistance increases. When the ground resistance reaches 50Ω, an average error of less than 2% is acceptable. According to the analysis, the fault location network based on the PAE-LSTM can accurately identify fault line segments and accurately locate fault points with low location errors. Although the positioning performance can be reduced with the increase of the fault distance and the grounding resistance, the positioning error of all simulation scenes is less than 3 percent.
Proved by verification, the method realizes accurate fault point positioning under the condition of multi-branch distribution lines. Through training a large number of high-dimensionality samples, accurate fault point ranging under the multi-branch power distribution system can be achieved. Realizing the application in practical engineering. The method has strong universality, can be combined with the training of an actual distribution network topological graph, has extremely high accuracy and strong reliability of a trained positioning network, and has a certain development prospect.
Example 3
Embodiment 3 provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement the intelligent fault location method applicable to a multi-branch distribution line as described above, the method comprising:
performing fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location;
judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line;
and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line.
Example 4
This embodiment 4 provides a computer program product comprising a computer program for implementing an intelligent fault localization method as described above for a multi-branch distribution line when run on one or more processors, the method comprising:
performing fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location;
judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line;
and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line.
Example 5
performing fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location;
judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line;
and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. 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.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it should be understood that various changes and modifications could be made by one skilled in the art without the need for inventive faculty, which would fall within the scope of the invention.
Claims (10)
1. An intelligent fault location method suitable for a multi-branch distribution line, comprising:
performing fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
judging a fault line based on the current effective value collected by the intelligent ammeter at the tail end of the secondary branch line;
processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault location model to finish fault point location;
and (5) integrating the fault line judgment result and the fault point position ranging to complete fault positioning of the fault multi-branch distribution line.
2. The intelligent fault location method for a multi-branch distribution line according to claim 1, wherein determining the fault line based on the current effective value collected by the smart meter at the end of the secondary branch line comprises: collect the second grade branch end intelligent ammeter that links to each other with feederWith current I ki (1. Ltoreq.i.ltoreq.n) to form a vector I o The method comprises the steps of carrying out a first treatment on the surface of the Vector I e Representing a collection of branches with only small currents, the value of which is smaller than a threshold gamma; 0<p<n; n, O the nodes on the primary and secondary branches, respectively, and if p=q, it means that only one secondary branch fails, the failure line being N kp O kp The method comprises the steps of carrying out a first treatment on the surface of the When p is equal to q, the main branch N is represented k(p-1) N kp The fault can cause the power failure of a plurality of secondary branches, and the line where the fault is located can be judged.
3. The intelligent fault location method for a multi-branch distribution line according to claim 1, wherein the distribution network fault location model comprises a self-encoder module and a long-term and short-term memory network module which are connected in parallel; the self-encoder module is used for reducing the dimension of the waveform information; the long-term and short-term memory network module is used for multiplying the cells in different time periods by taking the extracted time-related characteristic sequences as input.
4. The intelligent fault location method for a multi-branch distribution line according to claim 3, wherein t AEs are connected in parallel to form a self-encoder module layer; the value of t is determined by the length of the input waveform; in the self-encoder module layer training process, the label output of the t self-encoder has the same dimension as the input vector, and the t self-encoder loss function is as follows:
wherein the method comprises the steps of
Representing a dataset S t Reconstructed samples of the input samples of (a); w (W) ti Representing the weight of the t-th self-encoder; h t Is the number of neurons in the hidden layer; lambda, alpha are regularization parameters for adjusting the penalty term weights; KL (ρ) ti ) Is Kullback-LeibDegree of ler divergence->
ρ ti An average activation function value representing hidden layer neuron i; ρ is a sparsity parameter.
5. The intelligent fault location method for multi-branch distribution lines according to claim 4, wherein the long-short term memory network module multiplies the cells of different time periods so that the output or error of the previous time step is the same as the output of the next time step; the loss function for training the long-short-term memory network is the mean square error:
wherein S is the total number of training samples,
the estimation result given for LSTM model, y i Representing the true value of sample i.
6. The intelligent fault location method for a multi-branch distribution line according to claim 5, wherein the loss function is defined to take into account the effects of the self-encoder module and the long and short term memory network module when training the regression distribution network fault ranging model: l=l PAE +L LSTM ；
And determining the super parameters by adopting a grid searching and cross-validation method, and using a Sigmoid function as an activation function of a full-connection layer in the long-period memory network module.
7. An intelligent fault location system for a multi-branch distribution line, comprising:
the acquisition module is used for carrying out fault simulation on the power distribution network model by utilizing a pre-constructed power distribution network model to acquire phase voltage and phase current waveform information of the head end of the primary branch line; acquiring a current effective value acquired by an intelligent ammeter at the tail end of a secondary branch circuit;
the judging module is used for judging the fault line based on the effective current value acquired by the intelligent ammeter at the tail end of the secondary branch line;
the distance measurement module is used for processing the acquired phase voltage and phase current waveform information of the head end of the primary branch line by using a pre-trained power distribution network fault distance measurement model to finish fault point position distance measurement;
and the positioning module is used for integrating the fault line judgment result and the fault point location distance measurement to complete fault positioning of the fault multi-branch distribution line.
8. A non-transitory computer readable storage medium storing computer instructions which, when executed by a processor, implement the intelligent fault location method of any of claims 1-6 adapted to a multi-branch distribution line.
9. A computer program product comprising a computer program for implementing the intelligent fault location method for a multi-branch electrical distribution line as claimed in any of claims 1 to 6 when run on one or more processors.
10. An electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and wherein the computer program is stored in the memory, said processor executing the computer program stored in said memory when the electronic device is running, to cause the electronic device to execute instructions implementing the intelligent fault location method for a multi-branch distribution line according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310042798.5A CN116298670A (en) | 2023-01-28 | 2023-01-28 | Intelligent fault positioning method and system suitable for multi-branch distribution line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310042798.5A CN116298670A (en) | 2023-01-28 | 2023-01-28 | Intelligent fault positioning method and system suitable for multi-branch distribution line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116298670A true CN116298670A (en) | 2023-06-23 |
Family
ID=86796781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310042798.5A Pending CN116298670A (en) | 2023-01-28 | 2023-01-28 | Intelligent fault positioning method and system suitable for multi-branch distribution line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116298670A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117074869A (en) * | 2023-10-16 | 2023-11-17 | 盛隆电气集团有限公司 | Distribution line fault positioning method and system |
-
2023
- 2023-01-28 CN CN202310042798.5A patent/CN116298670A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117074869A (en) * | 2023-10-16 | 2023-11-17 | 盛隆电气集团有限公司 | Distribution line fault positioning method and system |
| CN117074869B (en) * | 2023-10-16 | 2023-12-19 | 盛隆电气集团有限公司 | Distribution line fault positioning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109088407B (en) | Power distribution network state estimation method based on deep belief network pseudo-measurement modeling | |
| Mestav et al. | State estimation for unobservable distribution systems via deep neural networks | |
| Cheng et al. | Enhanced state estimation and bad data identification in active power distribution networks using photovoltaic power forecasting | |
| CN104897784A (en) | Transformer fault diagnosis method based on coupled hidden Markov model | |
| CN110879377B (en) | Metering device fault tracing method based on deep belief network | |
| Niu et al. | Lebesgue sampling based deep belief network for lithium-ion battery diagnosis and prognosis | |
| Ma et al. | Topology identification of distribution networks using a split-EM based data-driven approach | |
| CN116298670A (en) | Intelligent fault positioning method and system suitable for multi-branch distribution line | |
| CN113937764A (en) | Low-voltage distribution network high-frequency measurement data processing and topology identification method | |
| CN116401532A (en) | Method and system for recognizing frequency instability of power system after disturbance | |
| CN106372440B (en) | A kind of adaptive robust state estimation method of the power distribution network of parallel computation and device | |
| Roy et al. | Demand forecasting in smart grid using long short-term memory | |
| CN114997566A (en) | Power grid blocking risk assessment method and system considering node connectivity loss | |
| Nguyen et al. | Electricity demand forecasting for smart grid based on deep learning approach | |
| CN112232570A (en) | Forward active total electric quantity prediction method and device and readable storage medium | |
| Xu et al. | An improved ELM-WOA–based fault diagnosis for electric power | |
| Wang et al. | Joint prediction of Li-ion battery state of charge and state of health based on the DRSN-CW-LSTM model | |
| CN109459609B (en) | Distributed power supply frequency detection method based on artificial neural network | |
| CN116565856A (en) | Power distribution network state estimation method considering unknown topology change | |
| CN113627655B (en) | Method and device for simulating and predicting pre-disaster fault scene of power distribution network | |
| CN111061708A (en) | Electric energy prediction and restoration method based on LSTM neural network | |
| CN115130662A (en) | Power distribution network time-varying topological state estimation method based on transfer learning | |
| Rosli et al. | Improving state estimation accuracy through incremental meter placement using new evolutionary strategy | |
| Wu et al. | Convolutional deep leaning-based distribution system topology identification with renewables | |
| Xie et al. | Harmonic state estimation based on network equivalence and closed loop GAN |
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 |