CN112415331A - Power grid secondary system fault diagnosis method based on multi-source fault information - Google Patents
Power grid secondary system fault diagnosis method based on multi-source fault information Download PDFInfo
- Publication number
- CN112415331A CN112415331A CN202011163422.2A CN202011163422A CN112415331A CN 112415331 A CN112415331 A CN 112415331A CN 202011163422 A CN202011163422 A CN 202011163422A CN 112415331 A CN112415331 A CN 112415331A
- Authority
- CN
- China
- Prior art keywords
- fault
- information
- element set
- alarm
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003745 diagnosis Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000007499 fusion processing Methods 0.000 claims abstract description 9
- 238000010219 correlation analysis Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000005065 mining Methods 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000007500 overflow downdraw method Methods 0.000 claims description 4
- 238000012097 association analysis method Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000007418 data mining Methods 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—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
Abstract
The utility model provides a power grid secondary system fault diagnosis method and system based on multi-source fault information, which comprises the following steps: acquiring fault alarm information and topological structure information of the power distribution network; determining a suspicious element set of the fault equipment according to the acquired information; calculating the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determining fault equipment; otherwise, executing the next step; carrying out correlation analysis on the fault alarm information by adopting an Apriori algorithm to obtain a target element set of the fault equipment; and performing fusion processing on the suspicious element set and the target element set to determine the fault equipment. By combining time-oriented, space-oriented and other multi-dimensional fault information big data mining analysis and artificial intelligence fault diagnosis based on a Bayesian algorithm, the target fault element diagnosis method suitable for power distribution network fault location is provided, faults are located quickly and accurately, faults are eliminated in time, and stability and safety of system operation are improved.
Description
Technical Field
The disclosure relates to the technical field of power grid secondary system fault diagnosis, in particular to a power grid secondary system fault diagnosis method based on multi-source fault information.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Although the power system in China is in the world advanced level in the fields of power generation and power transmission, the development of the field of power distribution networks is still in the starting stage. In recent years, along with the gradual attention of people to the power distribution network, a large number of new technologies, new equipment and various advanced intelligent equipment are widely applied to the field of the power distribution network, so that the power distribution network is automated to a great extent. The working state of the power distribution network has great influence on the reliability of power supply and the quality of electric energy, so that the improvement of the rapidity and the accuracy of fault location of the power distribution network is of great importance, and the traditional fault section location method of the power distribution network is not completely suitable for an active power distribution network, so that the accurate and rapid active power distribution network fault section location technology has higher practical value.
The existing active power distribution network fault section positioning method can be divided into two types: online diagnosis and offline diagnosis. The inventor finds that the existing fault section positioning method often adopts a single fault positioning method, and has the problems of inaccurate positioning and slow response speed. In addition, at present, expert scholars apply artificial intelligence algorithms such as a genetic algorithm, a rough set theory, a neural network theory, a Bayesian theory and the like to fault diagnosis of the power distribution network, and the application of the algorithms depends on power distribution network monitoring information provided by a power distribution automation system data platform, and a certain fault tolerance capability on data noise in the information is required. However, compared with the power transmission network, the degree of automation of the power distribution network in many areas of China is lower, many areas are still in a starting stage, monitoring data cannot be comprehensively acquired, and the application of the intelligent algorithms is limited to a great extent.
Disclosure of Invention
The invention provides a power grid secondary system fault diagnosis method and system based on multi-source fault information, combines time-oriented, space-oriented and other multi-dimensional fault information big data mining analysis and artificial intelligence fault diagnosis based on a Bayesian algorithm, and provides a target fault element diagnosis method suitable for power distribution network fault location, so that faults can be located quickly and accurately, faults can be eliminated timely, and the stability and safety of system operation are improved.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
one or more embodiments provide a power grid secondary system fault diagnosis method based on multi-source fault information, which includes the following steps:
acquiring fault alarm information and topological structure information of the power distribution network;
determining a suspicious element set of the fault equipment according to the acquired information;
calculating the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determining fault equipment; otherwise, executing the next step;
carrying out correlation analysis on the fault alarm information by adopting an Apriori algorithm to obtain a target element set of the fault equipment;
and performing fusion processing on the suspicious element set and the target element set to determine the fault equipment.
One or more embodiments provide a power grid secondary system fault diagnosis system based on multi-source fault information, including:
an acquisition module: the power distribution network fault alarm system is configured to be used for acquiring power distribution network fault alarm information and power distribution network topological structure information;
a suspect component set establishment module: a suspicious element set configured for determining a faulty device based on the obtained information;
a judging module: the device is configured to calculate the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determine fault equipment; otherwise, turning to a mining analysis module;
a mining analysis module: the fault alarm information association analysis method comprises the steps that association analysis is conducted on fault alarm information through an Apriori algorithm, and a target element set of fault equipment is obtained;
a fusion output module: and the system is configured to perform fusion processing on the suspicious element set and the target element set to determine a fault device.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the above method.
Compared with the prior art, the beneficial effect of this disclosure is:
(1) according to the method, the fault element is judged and determined by adopting the Bayesian algorithm, when the fault equipment cannot be determined, the intelligent association algorithm is fused to carry out association analysis based on the multidimensional information of the alarm information, the big data mining analysis facing the multidimensional fault information such as time and space and the like is combined with the artificial intelligent fault diagnosis based on the Bayesian algorithm, the association relation among the information can be mined according to the limited information, more effective information can be obtained, the fault equipment can be effectively judged, the fault location is realized, and the accuracy and the rapidity of the fault location are improved.
(2) The target certainty degree provided by the embodiment integrates the Apriori algorithm correlation confidence degree and the fault probability obtained by adopting the Bayesian algorithm, and the accuracy of fault judgment is improved by combining the two algorithms.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure.
FIG. 1 is a flow chart of a diagnostic method of embodiment 1 of the disclosure;
fig. 2 is a schematic structural diagram of a fault-alarm directed bipartite graph according to embodiment 1 of the present disclosure;
FIG. 3 is an association rule diagnostic diagram of embodiment 1 of the present disclosure;
FIG. 4 is a flow chart of the Apriori algorithm of example 1 of the present disclosure;
FIG. 5 is a flow chart of target element set construction according to embodiment 1 of the present disclosure;
fig. 6 is a flowchart of a fusion method according to embodiment 1 of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. 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 disclosure 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 example embodiments according to the present disclosure. 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. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments in the present disclosure may be combined with each other. The embodiments will be described in detail below with reference to the accompanying drawings.
Example 1
In the technical solutions disclosed in one or more embodiments, as shown in fig. 1 to 6, a method for diagnosing a fault of a secondary system of a power grid based on multi-source fault information includes the following steps:
step 1: acquiring fault alarm information and topological structure information of the power distribution network;
step 2: determining a suspicious element set of the fault equipment according to the acquired information;
and step 3: calculating the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determining fault equipment; otherwise, executing the next step;
step 4, carrying out correlation analysis on the fault alarm information by adopting an Apriori algorithm to obtain a target element set of the fault equipment;
and 5, fusing the suspicious element set and the target element set to determine the fault equipment.
In the embodiment, firstly, a Bayesian algorithm is adopted to judge and determine the fault element, when the fault equipment cannot be determined, an intelligent association algorithm is fused to carry out association analysis based on multi-dimensional information of alarm information, and the big data mining analysis facing multi-dimensional fault information such as time and space and the like is combined with artificial intelligent fault diagnosis based on the Bayesian algorithm, so that the fault equipment can be effectively judged, fault positioning is realized, and the accuracy and the rapidness of fault positioning are improved.
In this embodiment, the faulty component and the faulty device are only power devices in the power system, and the faulty device is represented by a symbol, and may become a faulty component when being an element in each set.
In step 1, fault alarm information may be obtained from a power distribution network fault information system, an integrated automation system, and a scheduling center, and may include secondary system IED alarm information, communication network fault alarm information, power distribution network topology information, secondary system static configuration information, and the like.
The screening preprocessing is performed on the fault information, and the following steps can be adopted:
step 11, filling vacancy values in data through data cleaning, removing noise data and correcting inconsistent data;
and 12, merging data from different data sources through data integration to form unified data storage, removing redundant attributes, searching and deleting repeated data, and obtaining fault characteristic quantity for fault diagnosis through screening.
The preprocessing enables the cleaned and integrated data to be more suitable for application of various data mining methods through data transformation, and enables the data to be smooth and normalized.
Optionally, the alarm information may include fault occurrence time, fault occurrence location, and fault alarm information content;
optionally, in step 2, in the process of determining the suspicious element set, the method further includes dividing the power grid secondary system into fault no-flow areas according to the topology structure of the power distribution network secondary system, and using devices in the no-flow areas as elements of the suspicious element set.
When the secondary equipment of the system breaks down, the corresponding protection can timely act to remove the fault to form a corresponding fault no-flow area, so that the safe operation of the normal area of the power distribution network is ensured. According to fault warning information obtained by a distribution network station control center and a dispatching center, a distribution network secondary system topological structure is combined, a fault no-flow area is divided for the distribution network secondary system, and elements with real faults can be guaranteed to be contained in a suspicious element set.
In a further technical scheme, before calculating the failure probability of each element in the suspicious element set by adopting a Bayesian algorithm in step 3, the method further comprises the following steps:
step 31, establishing a fault-alarm directed bipartite graph based on the relation between the fault and the alarm information to obtain a fault-alarm incidence matrix;
step 32, establishing a fault-alarm directed bipartite model based on the fault-alarm directed bipartite graph, wherein the fault-alarm directed bipartite model data is used as input data of a Bayesian algorithm;
the fault-alarm directed bipartite model may include a set of suspect target elements, a set of multi-source fault alarm information, a historical probability of a suspect target element failing, and an incidence matrix of the set of suspect target elements and the set of multi-source fault alarm information.
Establishing a power distribution network fault expression model, wherein the power distribution network fault expression model can be specifically a fault-alarm directed bipartite graph, and the incidence relation in the bipartite graph can be pointed to fault alarm information by a fault element.
Optionally, the imaging constraint relationship represented in the fault-alarm directed bipartite graph may be expressed in the form of an incidence matrix, and the obtained fault-alarm incidence matrix may be used as input data of a bayesian algorithm.
Optionally, the fault-alarm directed bipartite model is established based on a fault-alarm directed bipartite graph, and the model may include a suspicious target element set, a multi-source fault alarm information set, a historical probability of a fault occurring in a suspicious target element, and an incidence matrix of the suspicious target element set and the multi-source fault alarm information set.
Specifically, in this embodiment, the fault-alarm directed bipartite graph is shown in fig. 2, and the fault-alarm directed bipartite model may be specifically represented as:
X＝{F，S，PF，PF*S}
wherein, F is a suspicious target element set, and S is a multi-source fault alarm information set. PFHistorical probability set for failure of suspected target element, failure fiThe prior probability of occurrence is p (f)i)，PF＝{p(fi)|fi∈F}。
PF*SA correlation matrix for the set of suspect target elements and the set of multi-source fault alarm information, a fault-alarm condition probability matrix PF×S＝{p(sj|fi)|fi∈F，sj∈SN}. when PF×SIs a non-deterministic model when belongs to (0, 1), when PF×SAnd when the element belongs to {0, 1}, the model is deterministic.
The fault-alarm model of the present embodiment is a deterministic model.
For the set of alarm information actually observable in the system, the alarm information field F(s)i) Representing and informingAlarm information siA set of all suspected failed elements associated; suspicious element characteristic alarm information set S (f)i) Representative and failure element fiAnd (4) the set of all the associated alarm information.
In step 3, a bayesian algorithm is used to calculate the failure probability of each element in the suspicious element set, which may be a bayesian algorithm in a ratio form, specifically, the failure probability calculation formula is as follows:
wherein, p(s)j|fi) For failure prior probability, expressed at element fiIn case of failure, alarm information s appearsjThe probability of (c) can be obtained by mining the history. p (f)i|sj) For posterior probability, indicating the occurrence of alarm information sjIn the case of (2), element fiProbability of failure. p (f)i|sj) The larger the value, the fault fiInterpreting alarm information sjThe greater the likelihood.
P(f,SN) For Bayesian suspicion, the fault warning information S is obtained in this embodimentNIn the case of (3), the probability of failure of each element in the suspected element set is larger as the bayesian suspected degree value of the suspected failed element is larger, indicating that the element has a failure.
Calculating the failure probability of each element in the suspicious element set according to the formulas (1) and (2), storing the failure probability in the suspicious element set, and arranging according to the failure probability; in the suspicious element set, the failure calculation probability is 1, which indicates that the element has failed under the condition of complete alarm information, and if the failure calculation probability is not 1, which indicates that the alarm information is incomplete, the failure diagnosis needs to be performed by combining a data mining algorithm based on multi-dimensional failure information.
In step 4, a method for performing association analysis on the fault alarm information by using Apriori algorithm to obtain a target element set of the faulty device is shown in fig. 5, and includes the following steps:
step 41, establishing an association rule set according to the acquired fault alarm information of the power distribution network;
establishing an association rule set to extract multidimensional information of fault warning information, wherein the multidimensional information can comprise information contents of fault occurrence time, fault occurrence place, fault equipment and fault warning information, and performing data mining based on the multidimensional information.
Specifically, the association rule set H is used to represent a fault information set of the secondary device, as shown in the following formula (3).
H＝{I，J，K，L}。 (3)
In the formula: i, J, K and L are vectors representing fault information of different types respectively, the vector I represents time of fault occurrence of the secondary equipment, the vector J represents a fault occurrence place, the vector K represents fault secondary equipment, and the vector L represents fault alarm information sent by a system when the fault occurs.
And 2, screening frequent item sets and mining association rules based on an Apriori algorithm according to the association set rule set, calculating the association confidence of each device with a fault, and selecting the device with the threshold value larger than the set association confidence as an element of the target element set.
In this embodiment, each fault sample in the association rule set is a point in a 4-dimensional space constructed by 4 types of fault information, and the association relationship between the fault device and other three types of fault information can be established by mining the most frequent "4 item sets" through Apriori algorithm, and using fig. 3 as the association rule diagnosis idea.
Fig. 4 shows a flow chart of Apriori algorithm, and the steps of screening frequent item sets and mining association rules based on Apriori algorithm include the following steps:
(1) and (3) retrieving all frequent item sets in the fault record sample through an Apriori iterative algorithm, namely the item set with the support degree not lower than the minimum support degree set artificially.
(2) And determining the direct strong association rule of each fault information (fault time, fault location, fault equipment and fault alarm information) by comparing the confidence coefficient and the minimum confidence coefficient of each frequent item set.
The following describes the establishment process of the target component set by using a specific example.
Suppose that the fault occurs in a rural power distribution network in 1 month, and the fault alarm information is accompanied by communication link alarm information, switch communication port alarm information and the like.
Suppose that the distribution network fault records of 2019 years of a certain county in our province are obtained from a distribution network automation system, and an alarm database D is established. After data preprocessing, the D contains 1000 sets of fault alarm data, and table 1 is a simple example for D.
TABLE 1
Discretizing the failure time data, and expressing the specific time of failure by the numerical value of the month. As shown in table 2.
TABLE 2
| TID | Time of occurrence of failure (continuous value) | Time of occurrence of failure (discrete value)/ |
| 1 | 2019-12-30 18:38 | 12 |
| 2 | 2019-1-30 19:51 | 1 |
The attribute values of "failed device" and "failed region" and "failure alarm information" are integrated as shown in table 3.
TABLE 3
Converting the quantitative data in the database D into Boolean data to form a new database D', collecting the items I in the DmEach discrete value of (2) and i in the D' term setn' correspond to each other. The specific conversion results are shown in table 4 below.
TABLE 4
The Apriori algorithm is applied to mine a frequent item set, a minimum confidence threshold value Min _ confidence is set to be 50%, faults occurring in 1 month and in rural areas are screened out, fault alarm information is communication link alarm information, switch communication port alarm information and the like, and the rule confidence degree of the correlation between the corresponding suspicious element and the fault information is shown in table 5.
TABLE 5
The corresponding rule is as follows:
under the condition of meeting the fault information, the probability of the fault occurring on the communication link is 50 percent; the probability of occurring at the switch equipment is 70%.
Devices with a confidence greater than 50% comprise the target component set. Target element set W ═ switch, communication link … … }.
In step 5, the specific fusion method may be: and taking the intersection of the suspicious element set and the target element set as a final element set, and determining the element with the maximum target certainty in the final element set as a fault device, wherein the target element certainty is defined as the reliability of the element diagnosed as an actual fault element by the size, and the final element certainty target set is represented by Z.
The specific steps of the fusion method, as shown in fig. 6, may be as follows:
step 51, establishing a diagnosis information matrix of the elements of the final element set according to the final element set, wherein the diagnosis information matrix comprises the failure probability of the elements and the failure confidence of the elements;
the final element diagnostic information matrix is F, specifically:
M1,M2…Mnprobability of failure of N elements, N1,N2…NnIs the fault confidence for n elements.
Step 52, aiming at each device, establishing a weight vector matrix according to the association confidence coefficient of the device by adopting an Apriori algorithm and the failure probability weight obtained by adopting a Bayesian algorithm;
the weight phasor is represented by D, the weight of the confidence coefficient of the final target element is Q%, and the weight of the fault probability obtained by the intelligent algorithm is P%.
D＝[P％，Q％]
And step 53, calculating the target certainty factor of each target element according to the diagnosis information matrix and the weight vector matrix.
And calculating the target certainty degree by adopting the following formula:
Z＝D×F＝[Z1,Z2…Zn]
Z1,Z2…Zndefinition of target element, ZnThe calculation formula of (c) is as follows.
Zn＝Mn·P％+Nn·Q％
The target certainty degree provided by the embodiment integrates the Apriori algorithm correlation confidence degree and the fault probability obtained by adopting the Bayesian algorithm, and the accuracy of fault judgment is improved by combining the two algorithms.
Example 2
Based on embodiment 1, this embodiment provides a power grid secondary system fault diagnosis system based on multisource fault information, including:
an acquisition module: the power distribution network fault alarm system is configured to be used for acquiring power distribution network fault alarm information and power distribution network topological structure information;
a suspect component set establishment module: a suspicious element set configured for determining a faulty device based on the obtained information;
a judging module: the device is configured to calculate the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determine fault equipment; otherwise, turning to a mining analysis module;
a mining analysis module: the fault alarm information association analysis method comprises the steps that association analysis is conducted on fault alarm information through an Apriori algorithm, and a target element set of fault equipment is obtained;
a fusion output module: and the system is configured to perform fusion processing on the suspicious element set and the target element set to determine a fault device.
Example 3
The present embodiment provides a computer readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of embodiment 1.
It should be understood that in the present disclosure, the processor may be a central processing unit CPU, but may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The steps of a method disclosed in connection with the present disclosure may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here. Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a division of one logic function, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. The method for diagnosing the fault of the power grid secondary system based on the multi-source fault information is characterized by comprising the following steps of:
acquiring fault alarm information and topological structure information of the power distribution network;
determining a suspicious element set of the fault equipment according to the acquired information;
calculating the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determining fault equipment; otherwise, executing the next step;
carrying out correlation analysis on the fault alarm information by adopting an Apriori algorithm to obtain a target element set of the fault equipment;
and performing fusion processing on the suspicious element set and the target element set to determine the fault equipment.
2. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 1, wherein: before the failure probability of each element in the suspicious element set is calculated by adopting a Bayesian algorithm, the method also comprises the following steps:
establishing a fault-alarm directed bipartite graph based on the relation between the fault and the alarm information to obtain a fault-alarm incidence matrix;
and establishing a fault-alarm directed bipartite model based on the fault-alarm directed bipartite graph, wherein the fault-alarm directed bipartite model data is used as input data of a Bayesian algorithm.
3. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 2, characterized in that: the fault-alarm directed bipartite model may include a set of suspect target elements, a set of multi-source fault alarm information, a historical probability of a suspect target element failing, and an incidence matrix of the set of suspect target elements and the set of multi-source fault alarm information.
4. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 1, wherein: and calculating the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, wherein the Bayesian algorithm in a ratio form is adopted.
5. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 1, wherein: the method for performing correlation analysis on the fault alarm information by using the Apriori algorithm to obtain the target element set of the fault equipment comprises the following steps of:
establishing an association rule set according to the acquired fault warning information of the power distribution network;
according to the association set rule set, screening frequent item sets and mining association rules based on an Apriori algorithm, calculating association confidence of each device with faults, and selecting the devices with the thresholds larger than the set association confidence as elements of the target element set.
6. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 5, characterized in that: the association rule set comprises multidimensional information of fault alarm information, wherein the multidimensional information comprises information contents of fault occurrence time, fault occurrence place, fault equipment and fault alarm information.
7. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 1, wherein: and performing fusion processing on the suspicious element set and the target element set, wherein a specific fusion method can be as follows: and taking the intersection of the suspicious element set and the target element set as a final element set, and determining the element with the maximum target certainty in the final element set as the fault equipment.
8. The power grid secondary system fault diagnosis method based on multi-source fault information as claimed in claim 1, wherein:
the fusion processing is carried out on the suspicious element set and the target element set, and the fusion processing method comprises the following steps:
establishing a diagnosis information matrix of the elements of the final element set according to the final element set, wherein the diagnosis information matrix comprises the failure probability of the elements and the failure confidence coefficient of the elements;
aiming at each device, establishing a weight vector matrix according to the relevance confidence of the device by adopting an Apriori algorithm and the failure probability weight obtained by adopting a Bayesian algorithm;
and calculating the target certainty degree of each target element according to the diagnosis information matrix and the weight vector matrix.
9. Power grid secondary system fault diagnosis system based on multisource fault information, characterized by includes:
an acquisition module: the power distribution network fault alarm system is configured to be used for acquiring power distribution network fault alarm information and power distribution network topological structure information;
a suspect component set establishment module: a suspicious element set configured for determining a faulty device based on the obtained information;
a judging module: the device is configured to calculate the fault probability of each element in the suspicious element set by adopting a Bayesian algorithm, and if the fault efficiency is 1, determine fault equipment; otherwise, turning to a mining analysis module;
a mining analysis module: the fault alarm information association analysis method comprises the steps that association analysis is conducted on fault alarm information through an Apriori algorithm, and a target element set of fault equipment is obtained;
a fusion output module: and the system is configured to perform fusion processing on the suspicious element set and the target element set to determine a fault device.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011163422.2A CN112415331B (en) | 2020-10-27 | 2020-10-27 | Power grid secondary system fault diagnosis method based on multi-source fault information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011163422.2A CN112415331B (en) | 2020-10-27 | 2020-10-27 | Power grid secondary system fault diagnosis method based on multi-source fault information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112415331A true CN112415331A (en) | 2021-02-26 |
| CN112415331B CN112415331B (en) | 2024-04-09 |
Family
ID=74840696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011163422.2A Active CN112415331B (en) | 2020-10-27 | 2020-10-27 | Power grid secondary system fault diagnosis method based on multi-source fault information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112415331B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065580A (en) * | 2021-03-17 | 2021-07-02 | 国能大渡河大数据服务有限公司 | Power plant equipment management method and system based on multi-information fusion |
| CN113591393A (en) * | 2021-08-10 | 2021-11-02 | 国网河北省电力有限公司电力科学研究院 | Fault diagnosis method, device, equipment and storage medium of intelligent substation |
| CN113691311A (en) * | 2021-08-27 | 2021-11-23 | 中国科学院半导体研究所 | Fault positioning method of optical network, electronic equipment and computer readable storage medium |
| CN114710398A (en) * | 2022-06-02 | 2022-07-05 | 深圳嘉麟科技有限责任公司 | Abnormal accident alarm device for information system |
| CN116223971A (en) * | 2023-02-24 | 2023-06-06 | 合肥威标科技有限公司 | Auxiliary positioning system for fault area of power distribution network based on multi-source information |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441718A (en) * | 2008-12-19 | 2009-05-27 | 福建三元达通讯股份有限公司 | Sensor information fuse device and method |
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN103986238A (en) * | 2014-05-28 | 2014-08-13 | 山东大学 | Intelligent substation fault diagnosis method based on probability weighting bipartite graph method |
| CN105467975A (en) * | 2015-12-29 | 2016-04-06 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method |
| CN105678337A (en) * | 2016-01-12 | 2016-06-15 | 国网技术学院 | Information fusion method in intelligent transformer station fault diagnosis |
| CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
| CN109697210A (en) * | 2018-12-26 | 2019-04-30 | 天津瑞源电气有限公司 | A kind of Wind turbines relevant fault inline diagnosis method |
| US20190149565A1 (en) * | 2017-11-13 | 2019-05-16 | International Business Machines Corporation | Anomaly detection using cognitive computing |
| WO2020073301A1 (en) * | 2018-10-12 | 2020-04-16 | Powerchaintech Beijing Company | Systems and methods for monitoring a blockchain-based energy grid |
-
2020
- 2020-10-27 CN CN202011163422.2A patent/CN112415331B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441718A (en) * | 2008-12-19 | 2009-05-27 | 福建三元达通讯股份有限公司 | Sensor information fuse device and method |
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN103986238A (en) * | 2014-05-28 | 2014-08-13 | 山东大学 | Intelligent substation fault diagnosis method based on probability weighting bipartite graph method |
| CN105467975A (en) * | 2015-12-29 | 2016-04-06 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method |
| CN105678337A (en) * | 2016-01-12 | 2016-06-15 | 国网技术学院 | Information fusion method in intelligent transformer station fault diagnosis |
| CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
| US20190149565A1 (en) * | 2017-11-13 | 2019-05-16 | International Business Machines Corporation | Anomaly detection using cognitive computing |
| WO2020073301A1 (en) * | 2018-10-12 | 2020-04-16 | Powerchaintech Beijing Company | Systems and methods for monitoring a blockchain-based energy grid |
| CN109697210A (en) * | 2018-12-26 | 2019-04-30 | 天津瑞源电气有限公司 | A kind of Wind turbines relevant fault inline diagnosis method |
Non-Patent Citations (3)
| Title |
|---|
| 朱蕾;杨毅;: "改进贝叶斯算法在配网故障诊断中的研究", 三峡大学学报(自然科学版), no. 02, pages 72 - 77 * |
| 李雷: "基于聚类分析的软件多故障定位技术", 空间控制技术与应用, vol. 45, no. 5, pages 55 - 62 * |
| 聂倩雯: "基于关联规则数据挖掘和扩展贝叶斯网络的电网故障诊断方法研究", 硕士电子期刊, no. 10, pages 1 - 83 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065580A (en) * | 2021-03-17 | 2021-07-02 | 国能大渡河大数据服务有限公司 | Power plant equipment management method and system based on multi-information fusion |
| CN113065580B (en) * | 2021-03-17 | 2024-04-16 | 国能大渡河大数据服务有限公司 | Power plant equipment management method and system based on multi-information fusion |
| CN113591393A (en) * | 2021-08-10 | 2021-11-02 | 国网河北省电力有限公司电力科学研究院 | Fault diagnosis method, device, equipment and storage medium of intelligent substation |
| CN113691311A (en) * | 2021-08-27 | 2021-11-23 | 中国科学院半导体研究所 | Fault positioning method of optical network, electronic equipment and computer readable storage medium |
| CN114710398A (en) * | 2022-06-02 | 2022-07-05 | 深圳嘉麟科技有限责任公司 | Abnormal accident alarm device for information system |
| CN114710398B (en) * | 2022-06-02 | 2022-08-09 | 深圳嘉麟科技有限责任公司 | Abnormal accident alarm device for information system |
| CN116223971A (en) * | 2023-02-24 | 2023-06-06 | 合肥威标科技有限公司 | Auxiliary positioning system for fault area of power distribution network based on multi-source information |
| CN116223971B (en) * | 2023-02-24 | 2023-12-12 | 合肥威标科技有限公司 | Auxiliary positioning system for fault area of power distribution network based on multi-source information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112415331B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112415331B (en) | Power grid secondary system fault diagnosis method based on multi-source fault information | |
| CN106779505B (en) | Power transmission line fault early warning method and system based on big data driving | |
| CN107527114B (en) | A kind of route platform area exception analysis method based on big data | |
| WO2021213247A1 (en) | Anomaly detection method and device | |
| CN109840157A (en) | Method, apparatus, electronic equipment and the storage medium of fault diagnosis | |
| CN110968069B (en) | Fault prediction method of wind generating set, corresponding device and electronic equipment | |
| CN101783749B (en) | Network fault positioning method and device | |
| CN112217674B (en) | Alarm root cause identification method based on causal network mining and graph attention network | |
| CN106021771A (en) | Method and device for diagnosing faults | |
| CN104732276A (en) | On-line diagnosing method for faults of metering production facility | |
| CN112559237B (en) | Operation and maintenance system troubleshooting method and device, server and storage medium | |
| CN112559376A (en) | Automatic positioning method and device for database fault and electronic equipment | |
| CN115237717A (en) | Micro-service abnormity detection method and system | |
| CN113572625A (en) | Fault early warning method, early warning device, equipment and computer medium | |
| CN113900844A (en) | Service code level-based fault root cause positioning method, system and storage medium | |
| CN117041029A (en) | Network equipment fault processing method and device, electronic equipment and storage medium | |
| Lv et al. | A data fusion and data cleaning system for smart grids big data | |
| Liu et al. | Research on the strategy of locating abnormal data in IOT management platform based on improved modified particle swarm optimization convolutional neural network algorithm | |
| Wang et al. | Software defect fault intelligent location and identification method based on data mining | |
| Kumar et al. | Deep Learning based Fault Detection in Power Transmission Lines | |
| CN117034149A (en) | Fault processing strategy determining method and device, electronic equipment and storage medium | |
| CN110399278B (en) | Alarm fusion system and method based on data center anomaly monitoring | |
| CN117221087A (en) | Alarm root cause positioning method, device and medium | |
| CN116668264A (en) | Root cause analysis method, device, equipment and storage medium for alarm clustering | |
| Pan et al. | Study on intelligent anti–electricity stealing early-warning technology based on convolutional neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |