CN114113887A - Power distribution network fault positioning method and system - Google Patents
Power distribution network fault positioning method and system Download PDFInfo
- Publication number
- CN114113887A CN114113887A CN202111384728.5A CN202111384728A CN114113887A CN 114113887 A CN114113887 A CN 114113887A CN 202111384728 A CN202111384728 A CN 202111384728A CN 114113887 A CN114113887 A CN 114113887A
- Authority
- CN
- China
- Prior art keywords
- fault
- identification
- information
- equipment
- neural network
- 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.)
- Granted
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
-
- 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)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a method and a system for positioning a power distribution network fault, wherein the method and the system preliminarily determine a fault area by combining information reported by a user, and then determine fault equipment and the position thereof from the fault area, thereby reducing data processing amount and improving efficiency; and training two neural network models by different methods, fusing the two neural network models, and determining the fault equipment and the position thereof by the recognition results of the three neural network models, so that the method is more accurate.
Description
Technical Field
The invention relates to the technical field of power distribution networks, in particular to a power distribution network fault positioning method and system.
Background
With the continuous enlargement of the scale of the power distribution network and the continuous increase of the power consumption demand, the probability of the power grid failure is increased, and the power supply reliability requirements of power consumption customers are higher and higher. At present, after a power failure event occurs, a power utilization client is mainly used for dialing 95598, but the method cannot accurately position fault equipment and influences power supply rush repair.
Disclosure of Invention
The invention aims to provide a power distribution network fault positioning method and system, which can be used for quickly and accurately positioning power distribution network fault equipment.
The embodiment of the invention provides a power distribution network fault positioning method, which comprises the following steps:
step S10, power failure information reported by a user is obtained, a user number is extracted from the power failure information, and a fault area in the power distribution network is determined according to the user number;
step S20, sending an electrical parameter acquisition request to each intelligent terminal in the fault area to acquire the current electrical parameters of each branch line in the fault area; each branch line of the power distribution network is provided with one intelligent terminal;
step S30, acquiring topology information of the power distribution network;
step S40, inputting the electrical parameters and the power distribution network topology information into a first neural network model trained in advance for recognition, and obtaining a first recognition result; the first identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
step S50, inputting the electrical parameters and the power distribution network topology information into a pre-trained second neural network model for recognition to obtain a second recognition result; the first neural network model and the second neural network model are obtained by adopting different model structures and training modes respectively, and the second identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
step S60, inputting the electrical parameters and the distribution network topology information into a pre-trained third neural network model for recognition, and obtaining a third recognition result; the third neural network model is obtained by fusing the first neural network model and the second neural network model, and the third identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
and S70, comparing the first identification result, the second identification result and the third identification result, and determining the fault equipment and the position of the fault equipment according to the comparison result.
Preferably, the step S70 includes:
and if the first recognition result, the second recognition result and the third recognition result are different, re-executing the steps S20 to S70.
Preferably, the step S70 includes:
and if the equipment information of the fault equipment and the position information of the branch line where the fault equipment is located in any two identification results of the first identification result, the second identification result and the third identification result are the same, determining the fault equipment and the position where the fault equipment is located according to any one of the two identification results.
Preferably, the step S70 includes:
if the position information of the branch line where the fault equipment of any two identification results of the first identification result, the second identification result and the third identification result is located is the same, and the equipment information of the fault equipment is different, the position of the fault equipment is determined according to any one of the two identification results, the historical electrical parameter and the current electrical parameter of the fault equipment of the two identification results are obtained, the historical electrical parameter and the current electrical parameter are compared, and the fault equipment is determined according to the comparison result.
Preferably, the location information of the branch line where the fault equipment is located is a line number.
The embodiment of the invention also provides a power distribution network fault positioning system, which comprises:
the system comprises a fault area determining unit, a fault area determining unit and a fault area determining unit, wherein the fault area determining unit is used for acquiring power failure information reported by a user, extracting a user number from the power failure information and determining a fault area in the power distribution network according to the user number;
the electric parameter acquisition unit is used for sending an electric parameter acquisition request to each intelligent terminal in the fault area so as to acquire the current electric parameters of each branch line in the fault area; each branch line of the power distribution network is provided with one intelligent terminal;
the distribution network topology acquisition unit is used for acquiring distribution network topology information;
the first identification unit is used for inputting the electrical parameters and the distribution network topology information into a first neural network model trained in advance for identification to obtain a first identification result; the first identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
the second identification unit is used for inputting the electrical parameters and the distribution network topology information into a pre-trained second neural network model for identification to obtain a second identification result; the first neural network model and the second neural network model are obtained by adopting different model structures and training modes respectively, and the second identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
the third identification unit is used for inputting the electrical parameters and the distribution network topology information into a third neural network model which is trained in advance for identification to obtain a third identification result; the third neural network model is obtained by fusing the first neural network model and the second neural network model, and the third identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located; and
and the fault identification unit is used for comparing the first identification result, the second identification result and the third identification result and determining the fault equipment and the position of the fault equipment according to the comparison result.
Preferably, the fault recognition unit is specifically configured to re-execute steps S20 to S70 if the first recognition result, the second recognition result, and the third recognition result are different.
Preferably, the fault identifying unit is specifically configured to determine the faulty device and the location thereof according to any one of the first identification result, the second identification result, and the third identification result, if the device information of the faulty device and the location information of the branch line where the faulty device and the branch line are located are the same.
Preferably, the fault identification unit is specifically configured to, if the location information of the branch line where the faulty device is located in any two identification results of the first identification result, the second identification result, and the third identification result is the same, and the device information of the faulty device is different, determine the location of the faulty device according to any one of the two identification results, obtain the historical electrical parameter and the current electrical parameter of the faulty device in the two identification results, compare the historical electrical parameter with the current electrical parameter, and determine the faulty device according to the comparison result.
Preferably, the location information of the branch line where the fault equipment is located is a line number.
The embodiment of the invention has the following beneficial effects:
the method comprises the steps of preliminarily determining a fault area by combining information reported by a user, and then determining fault equipment and the position of the fault equipment from the fault area, so that the data processing amount is reduced, and the efficiency is improved; and training two neural network models by different methods, fusing the two neural network models, and determining the fault equipment and the position thereof by the recognition results of the three neural network models, so that the method is more accurate.
Additional features and advantages of embodiments of the invention will be set forth in the description which follows.
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 is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a power distribution network fault location method in an embodiment of the present invention.
Fig. 2 is a schematic diagram of a local topology of a power distribution network in an embodiment of the present invention.
Fig. 3 is a structural diagram of a power distribution network fault location system in an embodiment of the present invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In addition, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known means have not been described in detail so as not to obscure the present invention.
Referring to fig. 1, an embodiment of the present invention provides a power distribution network fault location method, including the following steps:
step S10, power failure information reported by a user is obtained, a user number is extracted from the power failure information, and a fault area in the power distribution network is determined according to the user number;
specifically, the user can report the power failure information by dialing 95598, and after acquiring the user code, the area where the user is located can be determined according to the user code. The power distribution network can be divided into a plurality of user areas, and the branch where the user in each user area is located is associated, so that after a certain user reports power failure information, the user area corresponding to the user can only be determined firstly, and the user area is determined as a fault area;
step S20, sending an electrical parameter acquisition request to each intelligent terminal in the fault area to acquire the current electrical parameters of each branch line in the fault area; each branch line of the power distribution network is provided with one intelligent terminal;
each intelligent terminal is arranged on each branch line in the fault area, as shown in fig. 2, the electrical parameters may include current, voltage, active and reactive parameters, and the like;
step S30, acquiring topology information of the power distribution network;
step S40, inputting the electrical parameters and the power distribution network topology information into a first neural network model trained in advance for recognition, and obtaining a first recognition result; the first identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
step S50, inputting the electrical parameters and the power distribution network topology information into a pre-trained second neural network model for recognition to obtain a second recognition result; the first neural network model and the second neural network model are obtained by adopting different model structures and training modes respectively, and the second identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
step S60, inputting the electrical parameters and the distribution network topology information into a pre-trained third neural network model for recognition, and obtaining a third recognition result; the third neural network model is obtained by fusing the first neural network model and the second neural network model, and the third identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
and S70, comparing the first identification result, the second identification result and the third identification result, and determining the fault equipment and the position of the fault equipment according to the comparison result.
Further, the step S70 includes:
if the equipment information of the fault equipment and the position information of the branch line where the fault equipment is located in any two identification results of the first identification result, the second identification result and the third identification result are the same, determining the fault equipment and the position where the fault equipment is located according to any one of the two identification results;
by way of example, the first recognition result includes a faulty device 1 (location 1) and a faulty device 2 (location 2), the second recognition result includes a faulty device 3 (location 3) and a faulty device 4 (location 4), and the third recognition result includes a faulty device 5 (location 5), a faulty device 6 (location 6) and a faulty device 7 (location 7); and if the fault equipment 1 is the same as the fault equipment 3, the position 1 is the same as the position 3, the fault equipment 2 is the same as the fault equipment 4, and the position 2 is the same as the position 4, determining the fault equipment and the position thereof according to the first identification result or the second identification result. Since the third neural network model is obtained by fusing the first neural network model and the second neural network model, in the actual recognition process, if the first recognition result and the second recognition result are the same, the third recognition result will be the same as the first recognition result and the second recognition result in general.
If the position information of the branch line where the fault equipment of any two identification results of the first identification result, the second identification result and the third identification result is located is the same, and the equipment information of the fault equipment is different, determining the position of the fault equipment according to any one of the two identification results, acquiring historical electrical parameters and current electrical parameters of the fault equipment of the two identification results, comparing the historical electrical parameters with the current electrical parameters, and determining the fault equipment according to the comparison result;
by way of example, the first recognition result includes a faulty device 1 (location 1) and a faulty device 2 (location 2), the second recognition result includes a faulty device 3 (location 3) and a faulty device 4 (location 4), and the third recognition result includes a faulty device 5 (location 5) and a faulty device 6 (location 6); if the fault equipment 1 is the same as the fault equipment 3 and the fault equipment 5, and the position 1 is the same as the position 3 and the position 5, determining that the fault equipment 1 on the branch where the position 1 is located has a fault; if the position 2, the position 4 and the position 6 are the same, and the fault equipment 2, the fault equipment 4 and the fault equipment 6 are different, determining that a fault exists on a branch circuit where the position 1, the position 3 and the position 5 are located, and cannot determine that the equipment has a fault, then acquiring historical electrical parameters of the fault equipment 2, the fault equipment 4 and the fault equipment 6, and comparing the current electrical parameters with the historical electrical parameters to determine the equipment which is most likely to have the fault; preferably, the historical electrical parameter may be data under the same condition as the current condition, such as time, weather, and the like, so as to improve the reliability of the comparison result.
And if the first recognition result, the second recognition result and the third recognition result are different, re-executing the steps S20 to S70.
Further, the location information of the branch line where the faulty device is located is a line number.
Referring to fig. 2, the intelligent terminal is configured to be disposed on each branch line of the power distribution network, and is configured to collect electrical parameters, such as current, voltage, active and reactive parameters, of each branch line, and send the electrical parameters to the server, where the server is used as an execution main body for executing the method in this embodiment; the server is used for training the neural network model through training data, and the training data can comprise electrical parameters of branch lines, positions of fault equipment and topological information of the power distribution network. The server is also used for inputting the electric parameters and the topological information acquired when the fault occurs into the trained neural network model, and recognizing the position of the fault equipment in the power distribution network. The intelligent terminal can be arranged on each branch line and collects the electrical parameters of the branch. The three intelligent terminals on the right side are located on the next-stage branch lines 11, 12 and 13, and the intelligent terminal on the left side is located on the upper-stage branch line 1. Theoretically, the electrical parameters of the three branch lines collected by the three intelligent terminals on the right side correspond to the electrical parameters of one branch line collected by one intelligent terminal on the left side. For example, the sum of the currents/powers of the three branch lines on the left side is equal to the current/power of the branch line on the right side.
The embodiment of the invention preliminarily determines the fault area by combining the information reported by the user, and then determines the fault equipment and the position thereof from the fault area, thereby reducing the data processing amount and improving the efficiency; and training two neural network models by different methods, fusing the two neural network models, and determining the fault equipment and the position thereof by the recognition results of the three neural network models, so that the method is more accurate.
For example, the training process of the first neural network model includes the following steps:
step A1, extracting the characteristics of each training data in the training set;
acquiring a training set, wherein the training set comprises electric parameters (voltage, current, active and reactive parameters and the like) of a plurality of branch lines, the position of fault equipment of a power distribution network and topological information of the power distribution network; after a training set is obtained, extracting information such as numerical values, positions, topology and the like of data from the training set as characteristics;
step A2, dividing the characteristics of each training data in the training set into Q characteristic subsets;
wherein Q is greater than 1, and the number of features contained in each feature subset is not less than 1;
for example, the features of each training data in the training set may be randomly divided into Q feature subsets according to clustering partition and other manners;
the clustering is divided into: setting the number of clustering centers as Q, and clustering the original data features into Q parts by using a clustering algorithm; the random division is: creating Q feature subsets, and randomly selecting features for each feature subset in sequence to enable the scale of each feature subset to be equivalent;
step A3, training a first neural sub-network based on the Q feature subsets to obtain Q first neural sub-networks;
first, the number of hidden layer nodes of the first neural subnetwork corresponding to the feature subset is calculated
To get the integer operator, { FQiIs the feature subset FQiThe number of included features, N being the number of features of the original data set;
then, determining a target training subset corresponding to each feature subset according to each feature subset;
let T bejExtracting the training set and the feature T for the jth feature in the ith feature subsetjCorresponding data columns form the jth column of the ith target training subset corresponding to the ith feature subset, and the steps are repeated, namely the data columns corresponding to the features in the ith feature subset in the training set are extracted to form the ith target training subset corresponding to the ith feature subset; the final target training subset obtained is M Ni' dimensional, where M is the number of data corresponding to a feature in the training set, and Ni' is the number of features contained in the ith feature subset;
secondly, training a first neural subnetwork corresponding to each feature subset based on the number of hidden layer nodes and a target training subset;
with KiTaking each piece of data in the ith target training subset as input data and output data of the ith first neural subnetwork (i.e. making the input data and the output data of the first neural subnetwork the same), and calculating the ith first neural subnetwork by adopting a two-stage methodParameters of the network, wherein the parameters of the ith first neural sub-network comprise the center and width of the hidden layer node of the first neural sub-network, the weight of the hidden layer node and the output layer node, and the like; optionally, the training process for training the corresponding first neural sub-networks may be performed in parallel, that is, the training on the Q first neural sub-networks may be performed simultaneously, based on each feature subset and the target training subset corresponding to each feature subset, so as to achieve the purposes of shortening the time and increasing the training speed;
step A4, splicing the Q first neural sub-networks into a first neural network model in parallel; arranging the Q trained first neural sub-networks obtained in the step, and splicing the Q trained first neural sub-networks into a wider neural network in parallel;
step A5, training a first neural network model based on each training data and a preset classification of each training data;
inputting each training data in the training set into an input layer of a first neural network model, and calculating an output matrix of hidden layer nodes of the first neural network model; and calculating the weight from the hidden layer to the output layer in the first neural network model based on the output matrix and the preset classification of each training data in the training set.
For example, the training process of the second neural network model comprises the following steps:
step B1, acquiring a training set;
the training set comprises electric parameters (voltage, current, active and reactive parameters and the like) of a plurality of branch lines, the position of fault equipment of the power distribution network and topology information of the power distribution network;
step B2, training the second neural network model by adopting the training set to obtain a plurality of weights and thresholds which meet the preset requirements of the second neural network model;
step B3, determining the optimal weight and the optimal threshold of the second neural network model from the multiple weights and thresholds by adopting an algorithm;
the specific process is as follows:
1) randomly generating a plurality of individuals to generate a parent particle swarm; each individual corresponds to a set of weights and thresholds of the neural network model; calculating the fitness of each particle in the parent particle swarm;
2) selecting the greater value of the fitness of the target particle in the parent particle swarm and the fitness of the individual optimal position of the target particle as the individual extreme value of the target particle, wherein the target particle is any one particle in the parent particle swarm;
3) selecting the maximum value of the fitness of each particle in the parent particle swarm and the fitness of the optimal position of the swarm of the parent particle swarm as a local extreme value of the parent particle swarm;
4) updating the position and the speed of the particles according to the individual extreme value and the local extreme value to generate a child particle swarm, taking the child particle swarm as a parent particle swarm of the next iteration, and updating the learning factor and the inertia factor;
5) if the current iteration times reach the preset maximum iteration times, outputting an optimal weight and an optimal threshold;
step B4, taking the optimal weight and the optimal threshold as the initial value of the weight and the initial value of the threshold of the second neural network model, and training the second neural network model again to obtain the trained second neural network model;
the process of training the neural network model in the step B2 and the step B4 is the same, except that the initial value of the weight value is different from the initial value of the threshold value.
For example, after obtaining the trained first neural network model and the trained second neural network model, fusing the first neural network model and the second neural network model to obtain a third neural network model;
suppose the input channel of the first neural network model is X1,X2,...,XcThe input channel of the second neural network model is Y1,Y2,...,YcAfter the first neural network model and the second neural network model are fused, the output channel is
K is a fusion coefficient;
the fused third neural network model comprises an input layer, a nonlinear transformation layer, a linear fusion layer and an output layer; the input layer comprises two first branches with the same network structure, and each first branch comprises a convolution layer and a correction linear unit; the nonlinear transformation layer comprises two second branches which have the same network structure and are respectively connected with the corresponding first branches, each second branch comprises a 5-layer network, and each layer network comprises a convolution layer, a batch normalization and a ReLU activation function; the linear fusion layer fuses the results of the two second branches of the nonlinear conversion layer to obtain an output result; the output layer comprises a global average pooling layer, a random discarded neuron connection and a full connection layer, and the output result of the linear fusion layer is output to the global average pooling layer.
Referring to fig. 3, another embodiment of the present invention provides a power distribution network fault location system, where the system of this embodiment corresponds to the method of the foregoing embodiment, and the system of this embodiment includes:
the system comprises a fault area determining unit 1, a power failure information processing unit and a power distribution network management unit, wherein the fault area determining unit 1 is used for acquiring power failure information reported by a user, extracting a user number from the power failure information, and determining a fault area in the power distribution network according to the user number;
the electrical parameter acquisition unit 2 is used for sending an electrical parameter acquisition request to each intelligent terminal in the fault area so as to acquire the current electrical parameters of each branch line in the fault area; each branch line of the power distribution network is provided with one intelligent terminal;
the distribution network topology acquisition unit 3 is used for acquiring distribution network topology information;
the first identification unit 4 is used for inputting the electrical parameters and the distribution network topology information into a first neural network model trained in advance for identification to obtain a first identification result; the first identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
the second identification unit 5 is used for inputting the electrical parameters and the distribution network topology information into a pre-trained second neural network model for identification to obtain a second identification result; the first neural network model and the second neural network model are obtained by adopting different model structures and training modes respectively, and the second identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
the third identification unit 6 is used for inputting the electrical parameters and the distribution network topology information into a third neural network model trained in advance for identification to obtain a third identification result; the third neural network model is obtained by fusing the first neural network model and the second neural network model, and the third identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located; and
and the fault identification unit 7 is used for comparing the first identification result, the second identification result and the third identification result and determining the fault equipment and the position of the fault equipment according to the comparison result.
Further, the fault recognition unit 7 is specifically configured to re-execute step S20 to step S70 if the first recognition result, the second recognition result, and the third recognition result are different.
Further, the fault identifying unit 7 is specifically configured to determine the faulty device and the location thereof according to any one of the two identification results, if the device information of the faulty device and the location information of the branch line where the faulty device and the branch line where the faulty device are located in any two identification results of the first identification result, the second identification result, and the third identification result are the same.
Further, the fault identification unit 7 is specifically configured to, if the position information of the branch line where the faulty device is located in any two identification results of the first identification result, the second identification result, and the third identification result is the same, and the device information of the faulty device is different, determine the location of the faulty device according to any one of the two identification results, acquire a historical electrical parameter and a current electrical parameter of the faulty device in the two identification results, compare the historical electrical parameter with the current electrical parameter, and determine the faulty device according to a comparison result.
Further, the location information of the branch line where the faulty device is located is a line number.
The system of the present embodiment corresponds to the method of the foregoing embodiment, and therefore, parts of the system of the present embodiment that are not described in detail can be obtained by referring to the method of the foregoing embodiment, and are not described again here.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A power distribution network fault positioning method is characterized by comprising the following steps:
step S10, power failure information reported by a user is obtained, a user number is extracted from the power failure information, and a fault area in the power distribution network is determined according to the user number;
step S20, sending an electrical parameter acquisition request to each intelligent terminal in the fault area to acquire the current electrical parameters of each branch line in the fault area; each branch line of the power distribution network is provided with one intelligent terminal;
step S30, acquiring topology information of the power distribution network;
step S40, inputting the electrical parameters and the power distribution network topology information into a first neural network model trained in advance for recognition, and obtaining a first recognition result; the first identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
step S50, inputting the electrical parameters and the power distribution network topology information into a pre-trained second neural network model for recognition to obtain a second recognition result; the first neural network model and the second neural network model are obtained by adopting different model structures and training modes respectively, and the second identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
step S60, inputting the electrical parameters and the distribution network topology information into a pre-trained third neural network model for recognition, and obtaining a third recognition result; the third neural network model is obtained by fusing the first neural network model and the second neural network model, and the third identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
and S70, comparing the first identification result, the second identification result and the third identification result, and determining the fault equipment and the position of the fault equipment according to the comparison result.
2. The method according to claim 1, wherein the step S70 includes:
and if the first recognition result, the second recognition result and the third recognition result are different, re-executing the steps S20 to S70.
3. The method according to claim 2, wherein the step S70 includes:
and if the equipment information of the fault equipment and the position information of the branch line where the fault equipment is located in any two identification results of the first identification result, the second identification result and the third identification result are the same, determining the fault equipment and the position where the fault equipment is located according to any one of the two identification results.
4. The method according to claim 3, wherein the step S70 includes:
if the position information of the branch line where the fault equipment of any two identification results of the first identification result, the second identification result and the third identification result is located is the same, and the equipment information of the fault equipment is different, the position of the fault equipment is determined according to any one of the two identification results, the historical electrical parameter and the current electrical parameter of the fault equipment of the two identification results are obtained, the historical electrical parameter and the current electrical parameter are compared, and the fault equipment is determined according to the comparison result.
5. The method according to any of claims 1-4, characterized in that the location information of the branch line where the faulty device is located is a line number.
6. A power distribution network fault location system, comprising:
the system comprises a fault area determining unit, a fault area determining unit and a fault area determining unit, wherein the fault area determining unit is used for acquiring power failure information reported by a user, extracting a user number from the power failure information and determining a fault area in the power distribution network according to the user number;
the electric parameter acquisition unit is used for sending an electric parameter acquisition request to each intelligent terminal in the fault area so as to acquire the current electric parameters of each branch line in the fault area; each branch line of the power distribution network is provided with one intelligent terminal;
the distribution network topology acquisition unit is used for acquiring distribution network topology information;
the first identification unit is used for inputting the electrical parameters and the distribution network topology information into a first neural network model trained in advance for identification to obtain a first identification result; the first identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
the second identification unit is used for inputting the electrical parameters and the distribution network topology information into a pre-trained second neural network model for identification to obtain a second identification result; the first neural network model and the second neural network model are obtained by adopting different model structures and training modes respectively, and the second identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located;
the third identification unit is used for inputting the electrical parameters and the distribution network topology information into a third neural network model which is trained in advance for identification to obtain a third identification result; the third neural network model is obtained by fusing the first neural network model and the second neural network model, and the third identification result comprises equipment information of at least one fault equipment and position information of a branch line where the fault equipment is located; and
and the fault identification unit is used for comparing the first identification result, the second identification result and the third identification result and determining the fault equipment and the position of the fault equipment according to the comparison result.
7. The system according to claim 6, wherein the fault recognition unit is specifically configured to re-execute steps S20 to S70 if the first recognition result, the second recognition result, and the third recognition result are different.
8. The system according to claim 7, wherein the fault identifying unit is specifically configured to determine the faulty device and the location thereof according to any one of the first identification result, the second identification result, and the third identification result, if the device information of the faulty device and the location information of the branch line where the faulty device is located of any two identification results are the same.
9. The system according to claim 8, wherein the fault identification unit is specifically configured to, if the location information of the branch line where the faulty device is located is the same and the device information of the faulty device is different for any two of the first identification result, the second identification result, and the third identification result, determine the location of the faulty device according to any one of the two identification results, obtain a historical electrical parameter and a current electrical parameter of the faulty device for the two identification results, compare the historical electrical parameter with the current electrical parameter, and determine the faulty device according to a comparison result.
10. The system according to any one of claims 6-9, wherein the location information of the branch line in which the faulty device is located is a line number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111384728.5A CN114113887B (en) | 2021-11-22 | 2021-11-22 | Fault positioning method and system for power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111384728.5A CN114113887B (en) | 2021-11-22 | 2021-11-22 | Fault positioning method and system for power distribution network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114113887A true CN114113887A (en) | 2022-03-01 |
| CN114113887B CN114113887B (en) | 2023-06-20 |
Family
ID=80439145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111384728.5A Active CN114113887B (en) | 2021-11-22 | 2021-11-22 | Fault positioning method and system for power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114113887B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115639327A (en) * | 2022-12-21 | 2023-01-24 | 南方电网数字电网研究院有限公司 | Sleeve fault detection method and device based on oil-immersed sleeve gas detection |
| CN115980512A (en) * | 2022-12-28 | 2023-04-18 | 山东恒道信息技术有限公司 | Fault positioning method for power transmission and distribution network |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187687A (en) * | 2007-12-21 | 2008-05-28 | 清华大学 | High resistance earthing fault detection method based on transient traveling wave |
| CN106291245A (en) * | 2016-08-25 | 2017-01-04 | 国网山东省电力公司青岛供电公司 | A kind of distribution network failure actively generates and sends repaiies method and apparatus |
| CN107942183A (en) * | 2017-10-23 | 2018-04-20 | 珠海许继芝电网自动化有限公司 | A kind of singlephase earth fault detection and localization processing method and its system |
| CN110501615A (en) * | 2019-09-29 | 2019-11-26 | 国网上海市电力公司 | Three facies pattern cable fault positioning system of medium voltage distribution network and method |
| CN110531261A (en) * | 2019-08-27 | 2019-12-03 | 国网江苏省电力有限公司检修分公司 | A kind of non-intrusion type initial failure of asynchronous electromotor detection method and system |
| CN111796166A (en) * | 2020-08-27 | 2020-10-20 | 广东电网有限责任公司电力调度控制中心 | Power distribution network single-phase high-resistance earth fault line selection method, system and equipment |
| CN111880044A (en) * | 2020-06-30 | 2020-11-03 | 国网浙江省电力有限公司电力科学研究院 | Online fault positioning method for power distribution network with distributed power supply |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
-
2021
- 2021-11-22 CN CN202111384728.5A patent/CN114113887B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187687A (en) * | 2007-12-21 | 2008-05-28 | 清华大学 | High resistance earthing fault detection method based on transient traveling wave |
| CN106291245A (en) * | 2016-08-25 | 2017-01-04 | 国网山东省电力公司青岛供电公司 | A kind of distribution network failure actively generates and sends repaiies method and apparatus |
| CN107942183A (en) * | 2017-10-23 | 2018-04-20 | 珠海许继芝电网自动化有限公司 | A kind of singlephase earth fault detection and localization processing method and its system |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| CN110531261A (en) * | 2019-08-27 | 2019-12-03 | 国网江苏省电力有限公司检修分公司 | A kind of non-intrusion type initial failure of asynchronous electromotor detection method and system |
| CN110501615A (en) * | 2019-09-29 | 2019-11-26 | 国网上海市电力公司 | Three facies pattern cable fault positioning system of medium voltage distribution network and method |
| CN111880044A (en) * | 2020-06-30 | 2020-11-03 | 国网浙江省电力有限公司电力科学研究院 | Online fault positioning method for power distribution network with distributed power supply |
| CN111796166A (en) * | 2020-08-27 | 2020-10-20 | 广东电网有限责任公司电力调度控制中心 | Power distribution network single-phase high-resistance earth fault line selection method, system and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 赵传宗 等: "基于小波变换和遗传算法的小电流接地故障定位技术研究" * |
| 钟高文: "基于故障特征匹配的配电网故障区间定位软件开发" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115639327A (en) * | 2022-12-21 | 2023-01-24 | 南方电网数字电网研究院有限公司 | Sleeve fault detection method and device based on oil-immersed sleeve gas detection |
| CN115980512A (en) * | 2022-12-28 | 2023-04-18 | 山东恒道信息技术有限公司 | Fault positioning method for power transmission and distribution network |
| CN115980512B (en) * | 2022-12-28 | 2023-08-15 | 山东恒道信息技术有限公司 | Fault positioning method for transmission and distribution network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114113887B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114113887B (en) | Fault positioning method and system for power distribution network | |
| CN112803404B (en) | Self-healing reconstruction planning method and device for power distribution network and terminal | |
| Castellano et al. | Cumulative merging percolation and the epidemic transition of the susceptible-infected-susceptible model in networks | |
| CN104156774B (en) | A kind of electric power support method for considering adjacent system | |
| Wang et al. | A hierarchical power grid fault diagnosis method using multi-source information | |
| CN106327357A (en) | Load identification method based on improved probabilistic neural network | |
| CN112485587B (en) | Layered positioning method for fault section of distribution network containing distributed photovoltaic | |
| CN111537831B (en) | Power distribution network line fault positioning method and device | |
| CN109685251A (en) | A kind of electronic facility charging station Optimization Method for Location-Selection, device and storage medium | |
| CN116203351A (en) | Method and system for detecting abnormal line impedance | |
| CN116467648A (en) | Early monitoring method for nonlinear platform power failure based on Internet of things table | |
| CN115842342A (en) | Topology identification method and device for distributed power distribution network | |
| Elyas et al. | A multi-objective optimization algorithm for bus type assignments in random topology power grid model | |
| CN116432136A (en) | Distributed electricity consumption abnormality detection method based on electricity consumption acquisition system | |
| CN116826743A (en) | Power load prediction method based on federal graph neural network | |
| CN115456109A (en) | Power grid fault element identification method and system, computer equipment and storage medium | |
| CN116975742A (en) | Partial discharge pattern recognition method, apparatus, device, and storage medium | |
| CN110391935B (en) | Measurement degree evaluation method and system considering information physical coupling characteristics and information disturbance | |
| CN108090616A (en) | A kind of electric system Active Splitting optimal section searching method | |
| CN114665481A (en) | Urban power grid partitioning method and device based on power grid node vectorization | |
| CN110889614A (en) | Power grid system important user power supply risk analysis method based on SCADA big data | |
| CN113312518A (en) | Grid structure analysis method, device and equipment based on CIM (common information model) of power distribution network | |
| CN109598330B (en) | Minimum collision set method considering topology characteristics of power distribution network | |
| CN113569904B (en) | Bus wiring type identification method, system, storage medium and computing device | |
| CN116109108B (en) | Distribution network automatic switch position distribution generation method, device 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |