CN111443259A - Active power distribution network fault diagnosis method and system based on local abnormal factor detection - Google Patents
Active power distribution network fault diagnosis method and system based on local abnormal factor detection Download PDFInfo
- Publication number
- CN111443259A CN111443259A CN202010235364.3A CN202010235364A CN111443259A CN 111443259 A CN111443259 A CN 111443259A CN 202010235364 A CN202010235364 A CN 202010235364A CN 111443259 A CN111443259 A CN 111443259A
- Authority
- CN
- China
- Prior art keywords
- fault
- power distribution
- distribution network
- matrix
- characteristic quantity
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention belongs to the field of power distribution network fault diagnosis, and particularly relates to an active power distribution network fault diagnosis method and system based on local abnormal factor detection. The method comprises the steps of obtaining operating electrical parameters of the active power distribution network in real time and preprocessing the operating electrical parameters to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence; fusing a plurality of one-dimensional fault characteristic quantity column matrixes of different fault types in space to form a plurality of fault characteristic quantity monitoring matrixes of the same time sequence, and fusing a plurality of multi-dimensional fault characteristic quantity monitoring matrixes based on a plurality of time sequences to form a high-dimensional fault characteristic quantity monitoring matrix; carrying out dimensionality reduction on the high-dimensional fault characteristic quantity monitoring matrix, and solving the first two characteristic roots of the matrix after dimensionality reduction and orthogonal characteristic vectors corresponding to the two characteristic roots; and performing local abnormal factor detection based on density on a column matrix consisting of the two orthogonal characteristic vectors to obtain abnormal physical nodes, and obtaining a fault diagnosis result by obtaining fault sections corresponding to the abnormal physical nodes through the network topology of the power distribution network.
Description
Technical Field
The invention belongs to the field of power distribution network fault diagnosis, and particularly relates to an active power distribution network fault diagnosis method and system based on local abnormal factor detection.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the increasing penetration rate of distributed power sources in power distribution networks, the operational reliability of power distribution networks becomes more and more important. If the active power distribution network fails to diagnose the line fault in time, the normal life of residents is affected, and the failure and paralysis of the whole system and the huge loss of personnel and production can be caused. Therefore, the method has important practical significance for accurately diagnosing the faults of the active power distribution network.
The existing fault diagnosis methods mainly comprise a fault diagnosis method based on uncertainty knowledge, a fault diagnosis method based on waveform similarity and a fault diagnosis method based on system direction element logic relation. The methods have advantages and disadvantages, wherein the fault diagnosis method with uncertain knowledge can realize fault diagnosis under the condition of information loss, but is not suitable for large-scale active power distribution networks; the fault diagnosis based on the waveform similarity directly utilizes the time sequence of the extracted signals to measure the waveform similarity, but the principle of the fault diagnosis needs to be further verified; the fault diagnosis method based on the logical relationship of the system direction elements converts the fault diagnosis problem into a mathematical optimization and planning problem, but does not fully utilize fault information. The inventor finds that when mass fault information is inrush, the existing fault diagnosis method has the problems of difficult convergence, large calculated amount, no consideration for distributed power supply and the like, has certain limitation, is not suitable for a large-scale active power distribution network, and further influences the accuracy of fault diagnosis of the active power distribution network.
Disclosure of Invention
In order to solve the problems, the invention provides an active power distribution network fault diagnosis method and system based on local abnormal factor detection, wherein a plurality of one-dimensional fault characteristic quantity column matrixes of different fault types are fused in space and a multidimensional fault characteristic quantity monitoring matrix based on at least two time sequences is fused and expanded in dimension to form a high-dimensional fault characteristic quantity monitoring matrix, and then the size of a local abnormal factor value is calculated after the dimension of the high-dimensional fault characteristic quantity monitoring matrix is reduced.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides an active power distribution network fault diagnosis method based on local abnormal factor detection.
An active power distribution network fault diagnosis method based on local abnormal factor detection comprises the following steps:
acquiring operating electrical parameters of the active power distribution network in real time and preprocessing the operating electrical parameters to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence; the one-dimensional fault characteristic quantity column matrix is a single fault characteristic quantity monitoring matrix, the number of physical nodes is taken as a row, and the number of sampling points in one power frequency sampling time is taken as a column;
fusing a plurality of one-dimensional fault characteristic quantity column matrixes of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and further fusing and expanding dimensions based on the multi-dimensional fault characteristic quantity monitoring matrixes of at least two different time sequences to form a high-dimensional fault characteristic quantity monitoring matrix;
carrying out dimensionality reduction on the high-dimensional fault characteristic quantity monitoring matrix, screening two characteristic roots of the matrix after dimensionality reduction, and calculating orthogonal characteristic vectors corresponding to the two characteristic roots;
and performing density-based local abnormal factor detection on a column matrix consisting of two orthogonal characteristic vectors to detect abnormal physical nodes, and obtaining fault sections corresponding to the abnormal physical nodes according to the network topology of the power distribution network to obtain fault diagnosis results.
The invention provides an active power distribution network fault diagnosis system based on local abnormal factor detection.
An active power distribution network fault diagnosis system based on local abnormal factor detection comprises:
the electric parameter acquisition and preprocessing module is used for acquiring and preprocessing the operating electric parameters of the active power distribution network in real time to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence; the one-dimensional fault characteristic quantity column matrix is a single fault characteristic quantity monitoring matrix, the number of physical nodes is taken as a row, and the number of sampling points in one power frequency sampling time is taken as a column;
the monitoring matrix forming module is used for fusing the one-dimensional fault characteristic quantity column matrixes of a plurality of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and further fusing and expanding the dimension based on the multi-dimensional fault characteristic quantity monitoring matrixes of at least two different time sequences to form a high-dimensional fault characteristic quantity monitoring matrix;
the dimensionality reduction processing module is used for carrying out dimensionality reduction processing on the high-dimensional fault characteristic quantity monitoring matrix, screening two characteristic roots of the matrix after dimensionality reduction, and calculating orthogonal characteristic vectors corresponding to the two characteristic roots;
and the fault diagnosis module is used for detecting local abnormal factors based on density of a column matrix formed by the two orthogonal characteristic vectors, detecting abnormal physical nodes, obtaining fault sections corresponding to the abnormal physical nodes according to the network topology of the power distribution network and obtaining a fault diagnosis result.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method for diagnosing faults of an active power distribution network based on local anomaly factor detection as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method for diagnosing faults of an active power distribution network based on local anomaly factor detection as described above when executing the program.
The invention has the beneficial effects that:
according to the invention, a plurality of one-dimensional fault characteristic quantity column matrixes of different fault types are fused in space, and a multi-dimensional fault characteristic quantity monitoring matrix based on at least two different time sequences is further fused and expanded in dimension to form a high-dimensional fault characteristic quantity monitoring matrix, so that fault characteristic quantities can be extracted more, and a more comprehensive data basis is provided for fault diagnosis of an active power distribution network;
according to the invention, the local abnormal factor value is calculated after the dimension reduction of the high-dimensional fault characteristic quantity monitoring matrix, the calculated quantity of fault diagnosis is reduced by screening after the dimension reduction of the importance of the fault information characteristic, the transverse comparison of each electrical parameter of each physical node is realized, and the accuracy of the fault diagnosis of the active power distribution network is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a process diagram for fault diagnosis in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of local anomaly detection according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a model of an active radial power distribution network according to an embodiment of the present invention;
fig. 4(a) is a simulation result of a single-phase ground fault occurring in the bus bar segment 1 in the power distribution network model of fig. 3;
FIG. 4(b) is a simulation of a single-phase ground fault occurring in the bus section 4 of the power distribution network model of FIG. 3;
fig. 4(c) is a simulation of a single-phase ground fault occurring in the bus section 14 of the power distribution network model of fig. 3.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all 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 is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present invention, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only terms of relationships determined for convenience of describing structural relationships of the parts or elements of the present invention, and are not intended to refer to any parts or elements of the present invention, and are not to be construed as limiting the present invention.
In the present invention, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be determined according to specific situations by persons skilled in the relevant scientific or technical field, and are not to be construed as limiting the present invention.
Example one
As shown in fig. 1, the method for diagnosing a fault of an active power distribution network based on local abnormal factor detection in this embodiment includes:
step 1: and acquiring the operating electrical parameters of the active power distribution network in real time, and preprocessing the operating electrical parameters to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence. In this embodiment, the operating electrical parameters of the active power distribution network include three-phase current, zero-sequence current, negative-sequence current, and zero-sequence active and reactive power.
In this embodiment, the time-series-based one-dimensional fault feature quantity column matrix is a single fault feature quantity monitoring matrix based on a single feature quantity within a power frequency sampling time, and the format of the single fault feature quantity monitoring matrix is that the number of physical nodes is taken as a row, and the number of sampling points within a power frequency sampling time is taken as a column, so that each physical node performs outlier detection under the same time series.
Specifically, the preprocessing operation for acquiring the running electrical parameters of the active power distribution network in real time comprises selection of fault characteristic quantities, construction of a network incidence matrix and regional differentiation processing.
In specific implementation, the measurement and control integrated terminal can be adopted to collect the operating electrical parameters of the active power distribution network. In addition, the measurement and control integrated terminal can also transmit a tripping isolation command, wherein the tripping isolation command is issued by the data processing center and is transmitted by the measurement and control integrated terminal to control the tripping of the physical node switch. And the data processing center sends a tripping command to the fault physical node according to the fault diagnosis result to isolate the fault section, so that the whole fault diagnosis process is completed.
In this embodiment, the measurement and control integrated terminal includes a power distribution terminal unit DTU, a feeder terminal unit FTU, a remote terminal unit RTU, a power distribution comprehensive monitoring unit PDK, etc., each unit is installed in a physical node under different environments, and node electrical parameters are uploaded to a data processing center through wired and wireless transmission. According to the embodiment, the fault diagnosis criterion can be started only by uploading the line electrical parameters to the data processing center in real time by the terminal, so that the manual inspection and maintenance time is greatly shortened.
Step 2: the method comprises the steps of fusing a plurality of one-dimensional fault characteristic quantity column matrixes of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and further fusing and expanding dimensions based on the multi-dimensional fault characteristic quantity monitoring matrixes of at least two different time sequences to form a high-dimensional fault characteristic quantity monitoring matrix.
And step 3: and carrying out dimensionality reduction on the high-dimensional fault characteristic quantity monitoring matrix, screening two characteristic roots of the matrix after dimensionality reduction, and calculating orthogonal characteristic vectors corresponding to the two characteristic roots.
In specific implementation, data analysis is carried out on a high-dimensional fault characteristic quantity monitoring matrix formed by data fusion, multi-dimensional scale dimensionality reduction is carried out, useless data and low-contribution data in the high-dimensional matrix are removed, high-value data are reserved, a low-dimensional fault characteristic quantity matrix is formed, and a characteristic root and a corresponding characteristic vector of the low-dimensional fault characteristic quantity matrix are calculated. In selecting a feature root, for example: the feature roots after matrix solution can be arranged from left to right, and the first two feature roots close to the left are selected. It should be noted that the selected feature root can also be randomly selected.
And 4, step 4: and performing density-based local abnormal factor detection on a column matrix consisting of two orthogonal characteristic vectors to detect abnormal physical nodes, and obtaining fault sections corresponding to the abnormal physical nodes according to the network topology of the power distribution network to obtain fault diagnosis results.
As shown in fig. 2, the process of performing the density-based local anomaly detection on the column matrix composed of two orthogonal feature vectors is as follows: calculating the K distance of each element in a column matrix consisting of two orthogonal feature vectors, namely taking the current element as an original point, calculating the distance from the K-th element closest to the original point except the original point, then calculating the K distance neighborhood of each element according to the K distance, further determining the local reachable distance and the local reachable density of each element, and finally calculating the local abnormal factor of each element corresponding to each physical node. The specific process is as follows:
step 1), inputting a two-dimensional fault characteristic quantity monitoring matrix with the scale of n × 2 and recorded as G:
G＝[G1G2](1)
where n represents the number of node elements.
Step 2): calculating the K distance between each node element and the Euclidean distance dist (P) between every two node elements. Wherein, the K distance between the node elements is marked as Kdist(P) represents a certain node element as a circle center P, and the K distance of P is defined as the distance between P and the nearest K-th element except P.
Step 3): computing K distance neighborhood Nk(P), representing all points within and including the kth distance of P:
Nk(P)＝{Q∈G/{P}|dist(P,Q)≤Kdist(P)} (2)
step 4): according to Kdist(Q) determining the local reachable distance K from dist (P, Q)reach(P,Q)：
Kreach(P,Q)＝max{Kdist(Q),dist(P,Q)} (3)
Step 5): calculating the local achievable density I of each elementrdk(P)：
Step 6) finally solving the local anomaly factor L OF OF each elementk(P)：
For example, the fault diagnosis is based on comparing electrical parameter information OF each physical node in the power distribution network in the same operation state, such as zero sequence current and negative sequence current information uploaded by each node OF the power distribution network when a single-phase earth fault occurs in a certain section, constructing a fault characteristic quantity monitoring matrix by using the node information and the fault characteristic quantity information, carrying out multi-dimensional scale scaling dimension reduction, solving the first two characteristic values OF the matrix after dimension reduction and the corresponding first two characteristic vectors, combining the two characteristic vectors to obtain a two-dimensional matrix, inputting the two-dimensional matrix into a density-based local anomaly factor detection algorithm, obtaining L OF values (local anomaly factor values) OF each node element in a two-dimensional plane, namely the degree OF clustering, and processing the clustered nodes according to the degree OF clustering to obtain a fault diagnosis result.
Under the normal operation state, L OF values calculated by all physical nodes OF the power distribution network are approximately equal to 1, when the power distribution network has a section fault, the OF values OF nodes L adjacent to nodes at the bus nodes OF the substation outlet and upstream OF the fault section are all far larger than 1, in order to guarantee reliability, L OF threshold values are set as the average values OF the OF values OF all the nodes L, and fault section diagnosis is completed according to the OF values OF the nodes L.
The present embodiment, as shown in fig. 3, models a radial active power distribution network comprising four feeders, wherein the distributed power sources are connected to feeder L1, and the rest of the feeders have no distributed power sources.
The simulation results are shown in fig. 4(a) -4 (c), in which the horizontal axis represents the node number and the vertical axis represents L OF values, fig. 4(a) shows that a single-phase ground fault occurs in the bus section 1, the L OF value OF the substation outlet bus node is 350.38 and is larger than the average value OF L OF values 18.75, fig. 4(b) shows that a single-phase ground fault occurs in the section 4, the L OF values OF the substation outlet bus node and the node 4 are 6.25 and 4.25, respectively, and are larger than the average value OF L OF values 1.31, and it is determined that a single-phase ground fault occurs in the section 4, fig. 4(c) shows that a single-phase ground fault occurs in the section 14, the L OF value OF the substation outlet bus node is 312.40, the L OF value OF the node 14 is 936.05, and the remaining nodes L OF values are all smaller than 7.
Example two
The embodiment provides an active power distribution network fault diagnosis system based on local abnormal factor detection, which includes:
(1) the electric parameter acquisition and preprocessing module is used for acquiring and preprocessing the operating electric parameters of the active power distribution network in real time to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence; the one-dimensional fault characteristic quantity column matrix is a single fault characteristic quantity monitoring matrix based on a single characteristic quantity in a power frequency sampling time, the number of physical nodes is used as a row, and the number of sampling points in the power frequency sampling time is used as a column.
Specifically, the preprocessing operation for acquiring the running electrical parameters of the active power distribution network in real time comprises selection of fault characteristic quantities, construction of a network incidence matrix and regional differentiation processing.
In a specific implementation, the operating electrical parameters of the active power distribution network include three-phase current, zero-sequence current, negative-sequence current, and zero-sequence active and reactive power. Specifically, the measurement and control integrated terminal can be adopted to collect the operating electrical parameters of the active power distribution network. In addition, the measurement and control integrated terminal can also transmit a tripping isolation command, wherein the tripping isolation command is issued by the data processing center and is transmitted by the measurement and control integrated terminal to control the tripping of the physical node switch. And the data processing center sends a tripping command to the fault physical node according to the fault diagnosis result to isolate the fault section, so that the whole fault diagnosis process is completed.
In this embodiment, the measurement and control integrated terminal includes a power distribution terminal unit DTU, a feeder terminal unit FTU, a remote terminal unit RTU, a power distribution comprehensive monitoring unit PDK, etc., each unit is installed in a physical node under different environments, and node electrical parameters are uploaded to a data processing center through wired and wireless transmission. According to the embodiment, the fault diagnosis criterion can be started only by uploading the line electrical parameters to the data processing center in real time by the terminal, so that the manual inspection and maintenance time is greatly shortened.
(2) And the monitoring matrix forming module is used for fusing the one-dimensional fault characteristic quantity column matrixes of a plurality of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and further fusing and expanding the dimension based on the multi-dimensional fault characteristic quantity monitoring matrixes of at least two different time sequences to form a high-dimensional fault characteristic quantity monitoring matrix.
(3) And the dimension reduction processing module is used for carrying out dimension reduction processing on the high-dimensional fault characteristic quantity monitoring matrix, screening two characteristic roots of the matrix after dimension reduction, and calculating orthogonalized characteristic vectors corresponding to the two characteristic roots.
In specific implementation, data analysis is carried out on a high-dimensional fault characteristic quantity monitoring matrix formed by data fusion, multi-dimensional scale dimensionality reduction is carried out, useless data and low-contribution data in the high-dimensional matrix are removed, high-value data are reserved, a low-dimensional fault characteristic quantity matrix is formed, and a characteristic root and a corresponding characteristic vector of the low-dimensional fault characteristic quantity matrix are calculated. In selecting a feature root, for example: the feature roots after matrix solution can be arranged from left to right, and the first two feature roots close to the left are selected. It should be noted that the selected feature root can also be randomly selected.
(4) And the fault diagnosis module is used for detecting local abnormal factors based on density of a column matrix formed by the two orthogonal characteristic vectors, detecting abnormal physical nodes, obtaining fault sections corresponding to the abnormal physical nodes according to the network topology of the power distribution network and obtaining a fault diagnosis result.
As shown in fig. 2, the process of performing the density-based local anomaly detection on the column matrix composed of two orthogonal feature vectors is as follows: calculating the K distance of each element in a column matrix consisting of two orthogonal feature vectors, namely taking the current element as an original point, calculating the distance from the K-th element closest to the original point except the original point, then calculating the K distance neighborhood of each element according to the K distance, further determining the local reachable distance and the local reachable density of each element, and finally calculating the local abnormal factor of each element corresponding to each physical node. The specific process is as follows:
step 1), inputting a two-dimensional fault characteristic quantity monitoring matrix with the scale of n × 2 and recorded as G:
G＝[G1G2](1)
where n represents the number of node elements.
Step 2): calculating the K distance between each node element and the Euclidean distance dist (P) between every two node elements. Wherein, the K distance between the node elements is marked as Kdist(P) represents a certain node element as a circle center P, and the K distance of P is defined as the distance between P and the nearest K-th element except P.
Step 3): computing K distance neighborhood Nk(P), representing all points within and including the kth distance of P:
Nk(P)＝{Q∈G/{P}|dist(P,Q)≤Kdist(P)} (2)
step 4): according to Kdist(Q) determining the local reachable distance K from dist (P, Q)reach(P,Q)：
Kreach(P,Q)＝max{Kdist(Q),dist(P,Q)} (3)
Step 5): calculating the local achievable density I of each elementrdk(P)：
Step 6) finally solving the local anomaly factor L OF OF each elementk(P)：
For example, the fault diagnosis is based on comparing electrical parameter information OF each physical node in the power distribution network in the same operation state, such as zero sequence current and negative sequence current information uploaded by each node OF the power distribution network when a single-phase earth fault occurs in a certain section, constructing a fault characteristic quantity monitoring matrix by using the node information and the fault characteristic quantity information, carrying out multi-dimensional scale scaling dimension reduction, solving the first two characteristic values OF the matrix after dimension reduction and the corresponding first two characteristic vectors, combining the two characteristic vectors to obtain a two-dimensional matrix, inputting the two-dimensional matrix into a density-based local anomaly factor detection algorithm, obtaining L OF values (local anomaly factor values) OF each node element in a two-dimensional plane, namely the degree OF clustering, and processing the clustered nodes according to the degree OF clustering to obtain a fault diagnosis result.
Under the normal operation state, L OF values calculated by all physical nodes OF the power distribution network are approximately equal to 1, when the power distribution network has a section fault, the OF values OF nodes L adjacent to nodes at the bus nodes OF the substation outlet and upstream OF the fault section are all far larger than 1, in order to guarantee reliability, L OF threshold values are set as the average values OF the OF values OF all the nodes L, and fault section diagnosis is completed according to the OF values OF the nodes L.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the steps in the method for diagnosing faults of an active power distribution network based on local abnormal factor detection according to the first embodiment.
Example four
The embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the steps in the method for diagnosing a fault of an active power distribution network based on local abnormal factor detection according to the first embodiment are implemented.
As will be appreciated by one skilled in the art, 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 a hardware embodiment, a 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, 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 flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An active power distribution network fault diagnosis method based on local abnormal factor detection is characterized by comprising the following steps:
acquiring operating electrical parameters of the active power distribution network in real time and preprocessing the operating electrical parameters to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence; the one-dimensional fault characteristic quantity column matrix is a single fault characteristic quantity monitoring matrix, the number of physical nodes is taken as a row, and the number of sampling points in one power frequency sampling time is taken as a column;
fusing a plurality of one-dimensional fault characteristic quantity column matrixes of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and further fusing and expanding dimensions based on the multi-dimensional fault characteristic quantity monitoring matrixes of at least two different time sequences to form a high-dimensional fault characteristic quantity monitoring matrix;
carrying out dimensionality reduction on the high-dimensional fault characteristic quantity monitoring matrix, screening two characteristic roots of the matrix after dimensionality reduction, and calculating orthogonal characteristic vectors corresponding to the two characteristic roots;
and performing density-based local abnormal factor detection on a column matrix consisting of two orthogonal characteristic vectors to detect abnormal physical nodes, and obtaining fault sections corresponding to the abnormal physical nodes according to the network topology of the power distribution network to obtain fault diagnosis results.
2. The active power distribution network fault diagnosis method based on local anomaly factor detection according to claim 1, wherein the preprocessing operation for acquiring the operating electrical parameters of the active power distribution network in real time comprises selection of fault characteristic quantities, construction of network incidence matrixes and regional difference processing.
3. The active power distribution network fault diagnosis method based on local anomaly factor detection according to claim 1, characterized in that the active power distribution network operating electrical parameters comprise three phase currents, zero sequence currents, negative sequence currents and zero sequence active and reactive powers.
4. The method for diagnosing the faults of the active power distribution network based on the local abnormal factor detection as claimed in claim 1, wherein the process of performing the density-based local abnormal factor detection on the column matrix consisting of two orthogonal eigenvectors comprises the following steps:
calculating the K distance of each element in a column matrix consisting of two orthogonal feature vectors, namely taking the element as an original point, calculating the distance from the K-th element closest to the original point except the original point, then calculating the K distance neighborhood of each element according to the K distance, further determining the local reachable distance and the local reachable density of each element, and finally calculating the local abnormal factor of each element corresponding to each physical node.
5. The active power distribution network fault diagnosis method based on local abnormal factor detection according to claim 1, characterized in that the process of detecting the abnormal physical node is as follows:
and comparing the local abnormal factor of the physical node with a set local abnormal factor threshold, wherein if the local abnormal factor is smaller than the threshold, the physical node is normal, and if the local abnormal factor is larger than the threshold, the physical node is failed.
6. An active power distribution network fault diagnosis system based on local abnormal factor detection is characterized by comprising:
the electric parameter acquisition and preprocessing module is used for acquiring and preprocessing the operating electric parameters of the active power distribution network in real time to obtain a one-dimensional fault characteristic quantity column matrix based on a time sequence; the one-dimensional fault characteristic quantity column matrix is a single fault characteristic quantity monitoring matrix, the number of physical nodes is taken as a row, and the number of sampling points in one power frequency sampling time is taken as a column;
the monitoring matrix forming module is used for fusing the one-dimensional fault characteristic quantity column matrixes of a plurality of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and further fusing and expanding the dimension based on the multi-dimensional fault characteristic quantity monitoring matrixes of at least two different time sequences to form a high-dimensional fault characteristic quantity monitoring matrix;
the dimensionality reduction processing module is used for carrying out dimensionality reduction processing on the high-dimensional fault characteristic quantity monitoring matrix, screening two characteristic roots of the matrix after dimensionality reduction, and calculating orthogonal characteristic vectors corresponding to the two characteristic roots;
and the fault diagnosis module is used for detecting local abnormal factors based on density of a column matrix formed by the two orthogonal characteristic vectors, detecting abnormal physical nodes, obtaining fault sections corresponding to the abnormal physical nodes according to the network topology of the power distribution network and obtaining a fault diagnosis result.
7. The active power distribution network fault diagnosis system based on local anomaly factor detection according to claim 6, wherein in the electrical parameter acquisition and preprocessing module, preprocessing operation for acquiring the operating electrical parameters of the active power distribution network in real time comprises selection of fault characteristic quantities, construction of network association matrix and regional differentiation processing.
8. The system for diagnosing faults of an active power distribution network based on local abnormal factor detection according to claim 6, wherein in the fault diagnosis module, the process of performing the local abnormal factor detection based on density on a column matrix composed of two orthogonal feature vectors is as follows:
calculating the K distance of each element in a column matrix consisting of two orthogonal feature vectors, namely taking the element as an original point, calculating the distance from the K-th element closest to the original point except the original point, then calculating the K distance neighborhood of each element according to the K distance, further determining the local reachable distance and the local reachable density of each element, and finally calculating the local abnormal factor of each element corresponding to each physical node.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method for diagnosing faults of an active distribution network based on the detection of local anomaly factors according to any one of claims 1 to 5.
10. Computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, carries out the steps of the method for diagnosing faults in an active power distribution network based on local anomaly factor detection according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010235364.3A CN111443259A (en) | 2020-03-30 | 2020-03-30 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010235364.3A CN111443259A (en) | 2020-03-30 | 2020-03-30 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111443259A true CN111443259A (en) | 2020-07-24 |
Family
ID=71649248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010235364.3A Pending CN111443259A (en) | 2020-03-30 | 2020-03-30 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111443259A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112083371A (en) * | 2020-08-07 | 2020-12-15 | 国网山东省电力公司济宁供电公司 | LOF-based abnormal high-pressure metering point screening method and system |
| CN112492633A (en) * | 2020-11-25 | 2021-03-12 | 中国电子科技集团公司第五十四研究所 | Wireless node fault diagnosis method based on improved local abnormal factor |
| CN112702877A (en) * | 2020-12-16 | 2021-04-23 | 南京中兴力维软件有限公司 | Cabinet interior remote monitoring and diagnosis method and system, cabinet device and storage medium |
| CN113156247A (en) * | 2021-04-23 | 2021-07-23 | 北京建筑大学 | Early warning method and device for low-frequency oscillation of power system |
| CN113315663A (en) * | 2021-05-28 | 2021-08-27 | 广东电网有限责任公司 | Carrier network fault diagnosis method and system based on service characteristics |
| CN113325267A (en) * | 2021-05-20 | 2021-08-31 | 国网辽宁省电力有限公司 | Power distribution network fault diagnosis system and method and computer program product |
| CN113325270A (en) * | 2021-06-03 | 2021-08-31 | 广东电网有限责任公司 | Optical cable transmission line monitoring method and device |
| CN113466609A (en) * | 2021-05-21 | 2021-10-01 | 国网江苏省电力有限公司淮安供电分公司 | Distribution network fault diagnosis micro synchronous measurement terminal deployment method considering DG access |
| CN113640675A (en) * | 2021-07-29 | 2021-11-12 | 南京航空航天大学 | Aviation lithium battery abnormity detection method based on Snippets characteristic extraction |
| CN113657622A (en) * | 2021-07-13 | 2021-11-16 | 国网河北省电力有限公司电力科学研究院 | Method, device, terminal and storage medium for fusing multidimensional state data of electrical equipment |
| CN115241901A (en) * | 2022-07-27 | 2022-10-25 | 天津大学 | Intelligent energy storage soft switch data driving voltage control method considering data quality |
| CN115959552A (en) * | 2023-03-15 | 2023-04-14 | 北京博华信智科技股份有限公司 | Escalator fault prediction method, device, equipment and medium |
| CN115980279A (en) * | 2023-02-14 | 2023-04-18 | 博纯材料股份有限公司 | Stability optimization method and system of neon purity detection system |
| CN116955895A (en) * | 2023-09-21 | 2023-10-27 | 山东博诚电气有限公司 | Transformer operation abnormity monitoring method and system |
| CN117110798A (en) * | 2023-10-25 | 2023-11-24 | 国网江苏省电力有限公司苏州供电分公司 | Fault detection method and system for intelligent power distribution network |
| CN117289085A (en) * | 2023-11-22 | 2023-12-26 | 武汉宏联电线电缆有限公司 | Multi-line fault analysis and diagnosis method and system |
| CN117651256A (en) * | 2023-11-28 | 2024-03-05 | 佛山科学技术学院 | Node energy consumption monitoring method and system based on outlier detection |
| CN117651256B (en) * | 2023-11-28 | 2024-06-07 | 佛山科学技术学院 | Node energy consumption monitoring method and system based on outlier detection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106093703A (en) * | 2016-06-07 | 2016-11-09 | 湖南大学 | The identification of a kind of intelligent distribution network fault and localization method |
| WO2019080367A1 (en) * | 2017-10-25 | 2019-05-02 | 南京航空航天大学 | Method for evaluating health status of mechanical device |
| CN110410282A (en) * | 2019-07-24 | 2019-11-05 | 河北工业大学 | Wind turbines health status on-line monitoring and method for diagnosing faults based on SOM-MQE and SFCM |
| CN110865260A (en) * | 2019-11-29 | 2020-03-06 | 南京信息工程大学 | Method for monitoring and evaluating MOV actual state based on outlier detection |
| CN110930057A (en) * | 2019-12-06 | 2020-03-27 | 国网湖北省电力有限公司电力科学研究院 | Quantitative evaluation method for reliability of distribution transformer test result based on LOF algorithm |
-
2020
- 2020-03-30 CN CN202010235364.3A patent/CN111443259A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106093703A (en) * | 2016-06-07 | 2016-11-09 | 湖南大学 | The identification of a kind of intelligent distribution network fault and localization method |
| WO2019080367A1 (en) * | 2017-10-25 | 2019-05-02 | 南京航空航天大学 | Method for evaluating health status of mechanical device |
| CN110410282A (en) * | 2019-07-24 | 2019-11-05 | 河北工业大学 | Wind turbines health status on-line monitoring and method for diagnosing faults based on SOM-MQE and SFCM |
| CN110865260A (en) * | 2019-11-29 | 2020-03-06 | 南京信息工程大学 | Method for monitoring and evaluating MOV actual state based on outlier detection |
| CN110930057A (en) * | 2019-12-06 | 2020-03-27 | 国网湖北省电力有限公司电力科学研究院 | Quantitative evaluation method for reliability of distribution transformer test result based on LOF algorithm |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112083371A (en) * | 2020-08-07 | 2020-12-15 | 国网山东省电力公司济宁供电公司 | LOF-based abnormal high-pressure metering point screening method and system |
| CN112492633A (en) * | 2020-11-25 | 2021-03-12 | 中国电子科技集团公司第五十四研究所 | Wireless node fault diagnosis method based on improved local abnormal factor |
| CN112492633B (en) * | 2020-11-25 | 2022-04-22 | 中国电子科技集团公司第五十四研究所 | Wireless node fault diagnosis method based on improved local abnormal factor |
| CN112702877A (en) * | 2020-12-16 | 2021-04-23 | 南京中兴力维软件有限公司 | Cabinet interior remote monitoring and diagnosis method and system, cabinet device and storage medium |
| CN113156247A (en) * | 2021-04-23 | 2021-07-23 | 北京建筑大学 | Early warning method and device for low-frequency oscillation of power system |
| CN113156247B (en) * | 2021-04-23 | 2024-04-23 | 北京建筑大学 | Early warning method and device for low-frequency oscillation of power system |
| CN113325267A (en) * | 2021-05-20 | 2021-08-31 | 国网辽宁省电力有限公司 | Power distribution network fault diagnosis system and method and computer program product |
| CN113466609A (en) * | 2021-05-21 | 2021-10-01 | 国网江苏省电力有限公司淮安供电分公司 | Distribution network fault diagnosis micro synchronous measurement terminal deployment method considering DG access |
| CN113466609B (en) * | 2021-05-21 | 2024-04-30 | 国网江苏省电力有限公司淮安供电分公司 | Deployment method of miniature synchronous measurement terminal for distribution network fault diagnosis |
| CN113315663B (en) * | 2021-05-28 | 2022-05-10 | 广东电网有限责任公司 | Carrier network fault diagnosis method and system based on service characteristics |
| CN113315663A (en) * | 2021-05-28 | 2021-08-27 | 广东电网有限责任公司 | Carrier network fault diagnosis method and system based on service characteristics |
| CN113325270A (en) * | 2021-06-03 | 2021-08-31 | 广东电网有限责任公司 | Optical cable transmission line monitoring method and device |
| CN113657622A (en) * | 2021-07-13 | 2021-11-16 | 国网河北省电力有限公司电力科学研究院 | Method, device, terminal and storage medium for fusing multidimensional state data of electrical equipment |
| CN113657622B (en) * | 2021-07-13 | 2024-02-27 | 国网河北省电力有限公司电力科学研究院 | Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment |
| CN113640675B (en) * | 2021-07-29 | 2022-05-20 | 南京航空航天大学 | Aviation lithium battery abnormity detection method based on Snippets characteristic extraction |
| CN113640675A (en) * | 2021-07-29 | 2021-11-12 | 南京航空航天大学 | Aviation lithium battery abnormity detection method based on Snippets characteristic extraction |
| CN115241901B (en) * | 2022-07-27 | 2023-06-20 | 天津大学 | Intelligent energy storage soft switch data driving voltage control method considering data quality |
| CN115241901A (en) * | 2022-07-27 | 2022-10-25 | 天津大学 | Intelligent energy storage soft switch data driving voltage control method considering data quality |
| CN115980279A (en) * | 2023-02-14 | 2023-04-18 | 博纯材料股份有限公司 | Stability optimization method and system of neon purity detection system |
| CN115959552A (en) * | 2023-03-15 | 2023-04-14 | 北京博华信智科技股份有限公司 | Escalator fault prediction method, device, equipment and medium |
| CN116955895A (en) * | 2023-09-21 | 2023-10-27 | 山东博诚电气有限公司 | Transformer operation abnormity monitoring method and system |
| CN116955895B (en) * | 2023-09-21 | 2023-12-15 | 山东博诚电气有限公司 | Transformer operation abnormity monitoring method and system |
| CN117110798A (en) * | 2023-10-25 | 2023-11-24 | 国网江苏省电力有限公司苏州供电分公司 | Fault detection method and system for intelligent power distribution network |
| CN117110798B (en) * | 2023-10-25 | 2024-02-13 | 国网江苏省电力有限公司苏州供电分公司 | Fault detection method and system for intelligent power distribution network |
| CN117289085A (en) * | 2023-11-22 | 2023-12-26 | 武汉宏联电线电缆有限公司 | Multi-line fault analysis and diagnosis method and system |
| CN117651256A (en) * | 2023-11-28 | 2024-03-05 | 佛山科学技术学院 | Node energy consumption monitoring method and system based on outlier detection |
| CN117651256B (en) * | 2023-11-28 | 2024-06-07 | 佛山科学技术学院 | Node energy consumption monitoring method and system based on outlier detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111443259A (en) | Active power distribution network fault diagnosis method and system based on local abnormal factor detection | |
| Guo et al. | Probabilistic framework for assessing the accuracy of data mining tool for online prediction of transient stability | |
| CN111474442B (en) | Power distribution network single-phase earth fault positioning method and system | |
| AU2020103179A4 (en) | A Fault Locating Method of Power Grid Based on Network Theory | |
| CN109165504B (en) | Power system false data attack identification method based on anti-generation network | |
| CN105322519B (en) | A kind of intelligent distribution network big data convergence analysis and method for monitoring operation states | |
| CN106526419A (en) | Distribution network fault tolerance on-line fault location method based on prediction correction technology | |
| CN111064180B (en) | Medium-voltage distribution network topology detection and identification method based on AMI (advanced mechanical arm) power flow matching | |
| CN111914486A (en) | Power system transient stability evaluation method based on graph attention network | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN110348114B (en) | Non-precise fault identification method for power grid completeness state information reconstruction | |
| CN108199891B (en) | Cps network attack identification method based on artificial neural network multi-angle comprehensive decision | |
| CN103728507A (en) | Grid fault diagnosis method based on data mining | |
| CN110943453A (en) | Power system fault sample generation and model construction method facing transfer learning | |
| CN113740666B (en) | Method for positioning root fault of storm alarm in power system of data center | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN110412417B (en) | Micro-grid data fault diagnosis method based on intelligent power monitoring instrument | |
| CN110443481B (en) | Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm | |
| CN111896845A (en) | Power distribution network fault diagnosis method and system based on multi-source information fusion | |
| CN111414957A (en) | D-PMU disturbance classification method based on PCA algorithm and XGboost algorithm | |
| CN114720819A (en) | Fault section binary positioning method based on self-checking learning | |
| CN107742883A (en) | A kind of power system topology island system for rapidly identifying and method based on Spark | |
| CN116581890B (en) | Intelligent monitoring method and system for operation stability of power grid | |
| CN113837423A (en) | Power grid operation situation prediction method based on energy internet electric power big data | |
| CN111965442A (en) | Energy internet fault diagnosis method and device under digital twin environment |
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 |