CN116559582A - Power distribution network fault detection method and system - Google Patents
Power distribution network fault detection method and system Download PDFInfo
- Publication number
- CN116559582A CN116559582A CN202310466041.9A CN202310466041A CN116559582A CN 116559582 A CN116559582 A CN 116559582A CN 202310466041 A CN202310466041 A CN 202310466041A CN 116559582 A CN116559582 A CN 116559582A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- distribution network
- power distribution
- fault detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 55
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 33
- 230000001052 transient effect Effects 0.000 claims abstract description 19
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 13
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 11
- 238000003745 diagnosis Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 4
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 239000004065 semiconductor Substances 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution network fault detection method and a system, wherein the method comprises the following steps: collecting parameter data of each node of the power system through an intelligent terminal; preprocessing parameter data by utilizing a transient component decomposition technology; classifying the preprocessed data set based on a K-NN algorithm, and performing fault analysis on the classified data set through neural network learning; the type and the position coordinates of the faults are determined according to the analysis result, so that the fault of the power distribution network is detected, and the accuracy and the robustness of the fault detection are improved; the invention is suitable for different types of intelligent terminal distribution network systems, can be used in combination with other fault detection methods and equipment, can detect and diagnose different types of faults, and has wider application range.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a power distribution network fault detection method and system.
Background
In an electric power system, a distribution network is one of indispensable important components, and distribution network automation specifically refers to taking a primary network frame and related equipment as a basis, taking a distribution automation system as a core, realizing monitoring on the running state of the distribution system by means of various communication modes, and scientifically and normalized managing the distribution system through information integration with other systems, wherein the realization of the aim is realized by virtue of the distribution automation system, and the system has the functions including feeder line automation, distribution SCADA, communication monitoring, fault processing, system interconnection and power grid analysis, and mainly comprises the following parts: the power distribution main station, the terminal, the substation and the communication channel, wherein the main station is a core part, the terminal is generally installed on a distribution network site, and the substation can realize information gathering, fault processing and communication monitoring functions in a controlled range.
At present, the utilization degree of the distribution network for synchronously measuring the big data mining is insufficient, the existing method only uses the traditional method of constructing a network parameter matrix and a traveling wave method to realize the whole network to be considerable, but the problem that the fault characteristics are difficult to extract under the multi-influence factors is not fundamentally solved, the fault identification and the positioning are difficult to carry out under the condition that the grounding signal of the big resistance is weak, and the method cannot be suitable for faults of various complex types.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description summary and in the title of the application, to avoid obscuring the purpose of this section, the description summary and the title of the invention, which should not be used to limit the scope of the invention.
The present invention has been made in view of the above-described problems.
In a first aspect of an embodiment of the present invention, a method for detecting a fault in a power distribution network is provided, including: collecting parameter data of each node of the power system through an intelligent terminal; preprocessing the parameter data by utilizing a transient component decomposition technology; classifying the preprocessed data set based on a K-NN algorithm, and performing fault analysis on the classified data set through neural network learning; and determining the type and position coordinates of the faults according to the analysis result, and detecting the faults of the power distribution network.
As a preferable scheme of the power distribution network fault detection method of the present invention, the method comprises: the collection of the parameter data of each node of the power system comprises,
installing monitoring equipment in the power system according to the acquisition requirement, and acquiring voltage, current and power parameters of each node in real time, wherein the monitoring equipment comprises a digital multifunctional power instrument and a digital current/voltage transformer;
and connecting the monitoring equipment with a data acquisition terminal through an RS485 communication interface, transmitting the acquired data to a processing and analyzing system through a communication line, and storing and backing up parameter data.
As a preferable scheme of the power distribution network fault detection method of the present invention, the method comprises: the process of the pre-treatment comprises the steps of,
decomposing the data into transient components of direct current, positive sequence, negative sequence and zero sequence by utilizing a transient component decomposition technology, cleaning the decomposed data, filling missing values, detecting abnormal values, and removing noise data;
converting the processed parameter data from a high-dimensional space to a low-dimensional space through linear transformation, and simultaneously retaining the category information of the data;
data integration is constructed, data from different data sources are combined and stored in the same database, query and association operations are carried out through SQL sentences, repeated data are searched and deleted, and a new data set is generated.
As a preferable scheme of the power distribution network fault detection method of the present invention, the method comprises: classifying the preprocessed data set includes,
dividing the preprocessed data set into a test set and a training set, and calculating the distance between the test set and the training set, wherein the calculation formula is as follows:
d=max(|x 1 -x 2 |,|y 1 -y 2 |)
where d represents the distance between the test set and the training set, x 1 The abscissa, x, representing test set data 2 Representing the abscissa, y, of the training set data 1 Representing the ordinate, y, of the test set data 2 Representing the ordinate of the training set data;
sorting the calculated distances according to the increasing sequence, selecting the first K data and counting the occurrence frequency of the first K data types;
and taking the type with the highest occurrence frequency as the prediction type of the test set, and simultaneously calculating the proportion value of all data which do not belong to the prediction type to the first K data, wherein the value of K is a positive integer.
As a preferable scheme of the power distribution network fault detection method of the present invention, the method comprises: the performing fault analysis on the classified data set includes,
extracting the characteristics of the classified data set, and selectively constructing forgetting gates, input gates and output gates by the extracted characteristics through the operation of activating a nerve layer of a function through sigmoid and multiplying the characteristics point by point;
taking the output of the two-way long-short-term memory neural network structure and the characteristic vector information as the input of the attention layer, and distributing different weights to the characteristic information vector;
and inputting the characteristic information vectors with different assigned weights into a full-connection layer to integrate data text information, and taking the integrated text information as the input of a fault detection model output layer, thereby realizing the analysis and the processing of the classified data set.
As a preferable scheme of the power distribution network fault detection method of the present invention, the method comprises: the method further comprises the steps of, in addition,
in different fault types, the amplitude, frequency and phase characteristics extracted in the characteristic extraction process show different rules and trends in a normal state and an abnormal state;
for short circuit faults, the transient component exhibits a high amplitude, high frequency characteristic, while for ground faults it typically exhibits a low amplitude, low frequency characteristic.
As a preferable scheme of the power distribution network fault detection method of the present invention, the method comprises: the determination of the type and location coordinates of the fault includes,
constructing an adjusting function according to the analysis result to determine the type and position coordinates of the fault;
the calculation of the adjustment function includes,
wherein m represents the adjustment result, a 1 Representing the distance of fault data, a 2 Representing the distance of the data to be detected, l 1 Representing the number of samples of fault data, l 2 Representing the number of samples of the data to be detected, b 1 Representing the standard error of the fault data, b 2 Representing standard error of data to be detected;
and the characteristics of different fault types are learned and generalized by adopting a mode identification method, so that the accuracy and the robustness of fault diagnosis are improved.
In a second aspect of the embodiment of the present invention, there is provided a power distribution network fault detection system, including:
the data processing unit is used for acquiring parameter data of each node of the power system through the intelligent terminal and preprocessing the parameter data by utilizing a transient component decomposition technology;
the fault diagnosis unit is used for classifying the preprocessed data set based on a K-NN algorithm and performing fault analysis on the classified data set through neural network learning;
and the analysis and detection unit is used for determining the type and the position coordinates of the faults according to the analysis result so as to realize the detection of the faults of the power distribution network.
In a third aspect of embodiments of the present invention, there is provided an apparatus, comprising,
a processor;
a memory for storing processor-executable instructions;
the processor is configured to invoke the instructions stored in the memory to perform the method according to any of the embodiments of the present invention.
In a fourth aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer program instructions comprising:
the computer program instructions, when executed by a processor, implement a method according to any of the embodiments of the present invention.
The invention has the beneficial effects that: the invention provides a power distribution network fault detection method and system, which are characterized in that parameter data of each node of a power system is collected through an intelligent terminal, and the parameter data is preprocessed by utilizing a transient component decomposition technology, so that the help is provided for realizing high-precision fault detection subsequently; the preprocessed data set is classified based on the K-NN algorithm, and the classified data set is subjected to fault analysis through neural network learning, so that the accurate diagnosis of fault types and fault positions can be realized, and the accuracy and the robustness of fault detection are improved; the type and the position coordinates of the faults are determined according to the analysis result, so that the real-time detection of the faults of the power distribution network is realized, the faults can be responded in time, and the efficiency and the safety of fault processing are improved; in addition, the invention is suitable for different types of intelligent terminal distribution network systems, can be used in combination with other fault detection methods and equipment, can detect and diagnose different types of faults, and has a wider application range.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is an overall flowchart of a power distribution network fault detection method and system provided by the invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, in one embodiment of the present invention, a power distribution network fault detection method is provided, including:
s1: parameter data of each node of the power system are collected through the intelligent terminal, and the parameter data are preprocessed through a transient component decomposition technology. It should be noted that:
the collection of parameter data for each node of the power system includes,
installing monitoring equipment in the power system according to the acquisition requirement, and acquiring voltage, current and power parameters of each node in real time, wherein the monitoring equipment comprises a digital multifunctional power instrument and a digital current/voltage transformer;
connecting the monitoring equipment with the data acquisition terminal through an RS485 communication interface, transmitting the acquired data to a processing and analyzing system through a communication line, and storing and backing up parameter data;
further, the pretreatment process comprises the steps of,
decomposing the data into transient components of direct current, positive sequence, negative sequence and zero sequence by utilizing a transient component decomposition technology, cleaning the decomposed data, filling missing values, detecting abnormal values, removing noise data, and the code is as follows:
it should be noted that data cleansing includes removing the same data that appears multiple times in the dataset to avoid duplicate calculations and analysis; filling the missing value comprises filling the missing value into the sample with the missing data by adopting an interpolation method or deleting the sample containing the missing value; the abnormal value detection comprises the steps of detecting and processing data with abnormal values by adopting a statistical method or a visual method; the normalization processing comprises the steps of normalizing or normalizing the data, eliminating errors caused by different data scales and ensuring the comparability between different data;
converting the processed parameter data from a high-dimensional space to a low-dimensional space through linear transformation, and simultaneously retaining the category information of the data;
data integration is built, data from different data sources are combined and stored in the same database, query and association operations are carried out through SQL sentences, repeated data are searched and deleted, and a new data set is generated for subsequent analysis and modeling.
S2: classifying the preprocessed data set based on a K-NN algorithm, and performing fault analysis on the classified data set through neural network learning. It should be noted that:
classifying the preprocessed data set includes,
dividing the preprocessed data set into a test set and a training set, and calculating the distance between the test set and the training set, wherein the calculation formula is as follows:
d=max(|x 1 -x 2 |,|y 1 -y 2 |)
where d represents the distance between the test set and the training set, x 1 The abscissa, x, representing test set data 2 Representing the abscissa, y, of the training set data 1 Representing the ordinate, y, of the test set data 2 Representing the ordinate of the training set data;
sorting the calculated distances according to the increasing sequence, selecting the first K data and counting the occurrence frequency of the first K data types;
taking the type with the highest occurrence frequency as the prediction type of the test set, and simultaneously calculating the proportion value of all data which do not belong to the prediction type to the previous K data, wherein the value of K is a positive integer;
further, performing fault analysis on the classified data set includes,
extracting the characteristics of the classified data set, and selectively constructing forgetting gates, input gates and output gates by the extracted characteristics through the operation of activating a nerve layer of a function through sigmoid and multiplying the characteristics point by point;
taking the output of the two-way long-short-term memory neural network structure and the characteristic vector information as the input of the attention layer, and distributing different weights to the characteristic information vector;
the characteristic information vectors with different assigned weights are input into the full-connection layer to integrate data text information, the integrated text information is used as input of the fault detection model output layer, and therefore analysis and processing of the classified data set are achieved, and the code is as follows:
s3: and determining the type and position coordinates of the fault according to the analysis result, and detecting the fault of the power distribution network. It should be noted that:
in different fault types, the amplitude, frequency and phase characteristics extracted in the characteristic extraction process show different rules and trends in a normal state and an abnormal state;
for short circuit faults, the transient component exhibits high amplitude, high frequency characteristics, while for ground faults, it generally exhibits low amplitude, low frequency characteristics;
further, constructing an adjusting function according to the analysis result to determine the type and position coordinates of the fault;
in particular, the calculation of the adjustment function includes,
wherein m represents the adjustment result, a 1 Representing the distance of fault data, a 2 Representing the distance of the data to be detected, l 1 Representing the number of samples of fault data, l 2 Representing the number of samples of the data to be detected, b 1 Representing the standard error of the fault data, b 2 Representing standard error of data to be detected;
and the characteristics of different fault types are learned and generalized by adopting a mode identification method, so that the accuracy and the robustness of fault diagnosis are improved.
It should be noted that the invention provides a power distribution network fault detection method and system, which collect parameter data of each node of a power system through an intelligent terminal, and pre-process the parameter data by utilizing a transient component decomposition technology, thereby providing assistance for realizing high-precision fault detection subsequently; the preprocessed data set is classified based on the K-NN algorithm, and the classified data set is subjected to fault analysis through neural network learning, so that the accurate diagnosis of fault types and fault positions can be realized, and the accuracy and the robustness of fault detection are improved; the type and the position coordinates of the faults are determined according to the analysis result, so that the real-time detection of the faults of the power distribution network is realized, the faults can be responded in time, and the efficiency and the safety of fault processing are improved; in addition, the invention is suitable for different types of intelligent terminal distribution network systems, can be used in combination with other fault detection methods and equipment, can detect and diagnose different types of faults, and has a wider application range.
In a second aspect of the present disclosure,
there is provided a power distribution network fault detection system comprising:
the data processing unit is used for acquiring the parameter data of each node of the power system through the intelligent terminal and preprocessing the parameter data by utilizing a transient component decomposition technology;
the fault diagnosis unit is used for classifying the preprocessed data set based on a K-NN algorithm and performing fault analysis on the classified data set through neural network learning;
and the analysis and detection unit is used for determining the type and position coordinates of the fault according to the analysis result and realizing the detection of the fault of the power distribution network.
In a third aspect of the present disclosure,
there is provided an apparatus comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of the preceding.
In a fourth aspect of the present disclosure,
there is provided a computer readable storage medium having stored thereon computer program instructions comprising:
the computer program instructions, when executed by a processor, implement a method of any of the preceding.
The present invention may be a method, apparatus, system, and/or computer program product, which may include a computer-readable storage medium having computer-readable program instructions embodied thereon for performing various aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
Example 2
The embodiment is different from the first embodiment in that a verification test of a power distribution network fault detection method and a power distribution network fault detection system are provided, and technical effects adopted in the method are verified and described.
In order to verify that the method has higher diagnosis accuracy and instantaneity compared with the traditional method, the traditional power distribution network fault detection method and the method are adopted to respectively compare the identification error rate of the power distribution network, the intelligent terminal is used for collecting the parameter data of each node of the power system, as shown in the table 1, and the transient component decomposition technology is used for preprocessing the parameter data;
table 1: and a parameter data table collected by the power system.
Time | Node 1 voltage/V | Node 1 current/A | Node 2 voltage/V | Node 2 current/A |
0 | 220 | 2.5 | 220 | 2.5 |
1 | 221 | 2.7 | 219 | 2.3 |
2 | 220.5 | 2.6 | 219.5 | 2.4 |
3 | 220 | 2.8 | 219 | 2.2 |
4 | 219.5 | 2.7 | 219.5 | 2.5 |
5 | 219 | 2.6 | 220 | 2.3 |
Importing the data of the power distribution network into a simulation platform, simulating the waveform with faults, starting automatic test equipment and detecting by using MATLB; the error detection is firstly carried out on the traditional method, then the error detection is carried out on the method, the running programs of the traditional method and the method are respectively encoded, and the encoded programs are imported into MATLB software for simulation test, and the results are shown in Table 2.
Table 2: error data versus table.
As can be seen from table 2, the method of the present invention has higher accuracy, lower error rate and greatly shortened maintenance time compared with the conventional power distribution network fault detection method.
Therefore, the invention can realize the detection of the faults of the power distribution network, improves the accuracy and the robustness of the fault detection, is suitable for different types of intelligent terminal power distribution network systems, can be used in combination with other fault detection methods and equipment, detects and diagnoses different types of faults, and has wider application range.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. A power distribution network fault detection method, comprising:
collecting parameter data of each node of the power system through an intelligent terminal;
preprocessing the parameter data by utilizing a transient component decomposition technology;
classifying the preprocessed data set based on a K-NN algorithm, and performing fault analysis on the classified data set through neural network learning;
and determining the type and position coordinates of the faults according to the analysis result, and detecting the faults of the power distribution network.
2. The power distribution network fault detection method as claimed in claim 1, wherein: the collection of the parameter data of each node of the power system comprises,
installing monitoring equipment in the power system according to the acquisition requirement, and acquiring voltage, current and power parameters of each node in real time, wherein the monitoring equipment comprises a digital multifunctional power instrument and a digital current/voltage transformer;
and connecting the monitoring equipment with a data acquisition terminal through an RS485 communication interface, transmitting the acquired data to a processing and analyzing system through a communication line, and storing and backing up parameter data.
3. The power distribution network fault detection method as claimed in claim 2, wherein: the process of the pre-treatment comprises the steps of,
decomposing the data into transient components of direct current, positive sequence, negative sequence and zero sequence by utilizing a transient component decomposition technology, cleaning the decomposed data, filling missing values, detecting abnormal values, and removing noise data;
converting the processed parameter data from a high-dimensional space to a low-dimensional space through linear transformation, and simultaneously retaining the category information of the data;
data integration is constructed, data from different data sources are combined and stored in the same database, query and association operations are carried out through SQL sentences, repeated data are searched and deleted, and a new data set is generated.
4. A power distribution network fault detection method as claimed in claim 3, wherein: classifying the preprocessed data set includes,
dividing the preprocessed data set into a test set and a training set, and calculating the distance between the test set and the training set, wherein the calculation formula is as follows:
d=max(|x 1 -x 2 |,|y 1 -y 2 |)
where d represents the distance between the test set and the training set, x 1 The abscissa, x, representing test set data 2 Representing the abscissa, y, of the training set data 1 Representing the ordinate, y, of the test set data 2 Representing the ordinate of the training set data;
sorting the calculated distances according to the increasing sequence, selecting the first K data and counting the occurrence frequency of the first K data types;
and taking the type with the highest occurrence frequency as the prediction type of the test set, and simultaneously calculating the proportion value of all data which do not belong to the prediction type to the first K data, wherein the value of K is a positive integer.
5. A power distribution network fault detection method as claimed in any one of claims 1 to 4, wherein: the performing fault analysis on the classified data set includes,
extracting the characteristics of the classified data set, and selectively constructing forgetting gates, input gates and output gates by the extracted characteristics through the operation of activating a nerve layer of a function through sigmoid and multiplying the characteristics point by point;
taking the output of the two-way long-short-term memory neural network structure and the characteristic vector information as the input of the attention layer, and distributing different weights to the characteristic information vector;
and inputting the characteristic information vectors with different assigned weights into a full-connection layer to integrate data text information, and taking the integrated text information as the input of a fault detection model output layer, thereby realizing the analysis and the processing of the classified data set.
6. The power distribution network fault detection method as claimed in claim 5, wherein: also included is a method of manufacturing a semiconductor device,
in different fault types, the amplitude, frequency and phase characteristics extracted in the characteristic extraction process show different rules and trends in a normal state and an abnormal state;
for short circuit faults, the transient component exhibits a high amplitude, high frequency characteristic, while for ground faults it typically exhibits a low amplitude, low frequency characteristic.
7. The power distribution network fault detection method as claimed in claim 6, wherein: the determination of the type and location coordinates of the fault includes,
constructing an adjusting function according to the analysis result to determine the type and position coordinates of the fault;
the calculation of the adjustment function includes,
wherein m represents the adjustment result, a 1 Representing the distance of fault data, a 2 Representing the distance of the data to be detected, l 1 Representing the number of samples of fault data, l 2 Representing the number of samples of the data to be detected, b 1 Representing the standard error of the fault data, b 2 Representing standard error of data to be detected;
and the characteristics of different fault types are learned and generalized by adopting a mode identification method, so that the accuracy and the robustness of fault diagnosis are improved.
8. A power distribution network fault detection system, comprising:
the data processing unit is used for acquiring parameter data of each node of the power system through the intelligent terminal and preprocessing the parameter data by utilizing a transient component decomposition technology;
the fault diagnosis unit is used for classifying the preprocessed data set based on a K-NN algorithm and performing fault analysis on the classified data set through neural network learning;
and the analysis and detection unit is used for determining the type and the position coordinates of the faults according to the analysis result so as to realize the detection of the faults of the power distribution network.
9. An apparatus, characterized in that the apparatus comprises,
a processor;
a memory for storing processor-executable instructions;
the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310466041.9A CN116559582A (en) | 2023-04-26 | 2023-04-26 | Power distribution network fault detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310466041.9A CN116559582A (en) | 2023-04-26 | 2023-04-26 | Power distribution network fault detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116559582A true CN116559582A (en) | 2023-08-08 |
Family
ID=87493936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310466041.9A Pending CN116559582A (en) | 2023-04-26 | 2023-04-26 | Power distribution network fault detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116559582A (en) |
-
2023
- 2023-04-26 CN CN202310466041.9A patent/CN116559582A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104966161B (en) | A kind of power quality recorder data calculation and analysis methods based on gauss hybrid models | |
CN103996077A (en) | Electric equipment fault forecasting method based on multi-dimension time sequence | |
CN107992447A (en) | A kind of feature selecting decomposition method applied to river level prediction data | |
CN103745119A (en) | Oil-immersed transformer fault diagnosis method based on fault probability distribution model | |
CN110619479B (en) | Fault judgment model modeling method and fault judgment method for photovoltaic module | |
CN112508105A (en) | Method for detecting and retrieving faults of oil extraction machine | |
CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
CN113435759B (en) | Primary equipment risk intelligent assessment method based on deep learning | |
CN115170000A (en) | Remote monitoring method and system based on electric energy meter communication module | |
CN113011481A (en) | Electric energy meter function abnormity evaluation method and system based on decision tree algorithm | |
CN113987294A (en) | CVT (continuously variable transmission) online fault diagnosis method based on genetic optimization GRU (generalized regression Unit) neural network | |
CN116956215A (en) | Fault diagnosis method and system for transmission system | |
CN114519514A (en) | Low-voltage transformer area reasonable line loss value measuring and calculating method, system and computer equipment | |
CN117748507B (en) | Distribution network harmonic access uncertainty assessment method based on Gaussian regression model | |
CN115015683A (en) | Cable production performance test method, device, equipment and storage medium | |
Ye et al. | Single pole‐to‐ground fault location method for mmc‐hvdc system using wavelet decomposition and dbn | |
CN117057666B (en) | Distribution quality evaluation method and system for digital distribution network | |
CN116520068B (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
CN112000831B (en) | Abnormal data identification optimization method based on substation graph transformation | |
CN111737993B (en) | Method for extracting equipment health state from fault defect text of power distribution network equipment | |
CN111475548A (en) | Power utilization abnormity analysis decision system based on big data mining technology | |
CN116559582A (en) | Power distribution network fault detection method and system | |
CN116699254A (en) | Electromagnetic interference prevention method and equipment for equipment in machine room | |
CN116126807A (en) | Log analysis method and related device | |
CN115880472A (en) | Intelligent diagnosis and analysis system for electric power infrared image data |
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 |