CN111784537B - Power distribution network state parameter monitoring method and device and electronic equipment - Google Patents

Power distribution network state parameter monitoring method and device and electronic equipment Download PDF

Info

Publication number
CN111784537B
CN111784537B CN202010622269.9A CN202010622269A CN111784537B CN 111784537 B CN111784537 B CN 111784537B CN 202010622269 A CN202010622269 A CN 202010622269A CN 111784537 B CN111784537 B CN 111784537B
Authority
CN
China
Prior art keywords
power distribution
distribution network
historical
parameter
data
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.)
Active
Application number
CN202010622269.9A
Other languages
Chinese (zh)
Other versions
CN111784537A (en
Inventor
张维
刘玉民
李温静
刘柱
张骁
孟洪民
李艺欣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Information and Telecommunication Co Ltd
Original Assignee
State Grid Information and Telecommunication Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Information and Telecommunication Co Ltd filed Critical State Grid Information and Telecommunication Co Ltd
Priority to CN202010622269.9A priority Critical patent/CN111784537B/en
Publication of CN111784537A publication Critical patent/CN111784537A/en
Application granted granted Critical
Publication of CN111784537B publication Critical patent/CN111784537B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The application discloses a method, a device and electronic equipment for monitoring state parameters of a power distribution network, wherein power distribution network monitoring data of the power distribution network at a target time are obtained, and the power distribution network monitoring data comprise a plurality of state parameters; obtaining a target parameter set corresponding to the monitoring data of the power distribution network from a set containing a plurality of preset parameter sets, wherein the target parameter set contains a plurality of state parameters; the method comprises the steps that a preset parameter set in a set is generated based on power distribution network historical data corresponding to a plurality of historical moments of a power distribution network respectively, the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data; and under the condition that the parameter similarity value meets the preset alarm condition, outputting an alarm result corresponding to the monitoring data of the power distribution network.

Description

Power distribution network state parameter monitoring method and device and electronic equipment
Technical Field
The application relates to the technical field of power, in particular to a power distribution network state parameter monitoring method and device and electronic equipment.
Background
The distribution network is located at the end of the power system and interacts directly with most consumers of electricity, and the operation status of the distribution network will directly affect the reliability of power supply and the electricity consumption experience of the consumers. At present, statistical analysis of average outage time data of clients shows that 90% of outage time is caused by power distribution network faults. Therefore, it is necessary to monitor whether the power distribution network has a fault state in real time.
Currently, when monitoring a fault state of a power distribution network, a fixed threshold is usually set for collected current and voltage data of the power distribution network to determine whether state parameters such as current or voltage are abnormal.
However, in an actual environment, different characteristics may occur in the power distribution network due to a change in the power consumption client or a change in the user state of the power consumption client, for example, the power consumption, and the like may be different due to a change in the user client, so that when a single fixed threshold is used for monitoring the state parameter of the power distribution network, there may be a situation that the monitoring is inaccurate.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus and an electronic device for monitoring a state parameter of a power distribution network, as follows:
A method for monitoring a state parameter of a power distribution network, the method comprising:
acquiring power distribution network monitoring data of a power distribution network at a target time, wherein the power distribution network monitoring data comprises a plurality of state parameters;
obtaining a target parameter set corresponding to the power distribution network monitoring data from a set containing a plurality of preset parameter sets, wherein the target parameter set contains a plurality of state parameters;
the method comprises the steps that a preset parameter set in a set is generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical moments, wherein the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data;
and under the condition that the parameter similarity value meets the preset alarm condition, outputting an alarm result corresponding to the power distribution network monitoring data.
The above method, preferably, the method further comprises:
the method for obtaining the set corresponding to the power distribution network in advance specifically comprises the following steps:
obtaining first historical state data, wherein the first historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
Carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the first historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set;
generating an initial fuzzy rule statement corresponding to each historical moment according to a fuzzy set and a membership value in fuzzy data corresponding to each historical moment;
screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value;
and performing anti-blurring processing on the target fuzzy rule sentences respectively to obtain preset parameter sets corresponding to each target fuzzy rule sentence, wherein the preset parameter sets corresponding to each history moment form a set corresponding to the power distribution network.
In the above method, preferably, before performing the defuzzification processing on the target fuzzy rule statement, the method further includes:
Screening at least two fuzzy rule sentences meeting the logic contradiction conditions in the target fuzzy rule sentences according to the interestingness values of the fuzzy rule sentences to delete the fuzzy rule sentences with the interestingness values smaller than or equal to the interestingness threshold value in the fuzzy rule sentences meeting the logic contradiction conditions;
wherein the logical contradictory conditions include: at least one fuzzy set corresponding to the state parameter is different among the fuzzy rule sentences.
In the above method, preferably, before the initial fuzzy rule sentence is screened according to the minimum confidence value and the minimum support value of the fuzzy rule sentence, the method further includes:
merging the same fuzzy rule sentences in the initial fuzzy rule sentences, wherein the same fuzzy rule sentences are as follows: the fuzzy set corresponding to each state parameter and the membership value corresponding to the fuzzy set are the same among the fuzzy rule sentences.
In the above method, preferably, in a set including a plurality of preset parameter sets, obtaining a target parameter set corresponding to the monitoring data of the power distribution network includes:
at least one first state parameter corresponding to the power distribution network monitoring data is obtained from a plurality of state parameters in the power distribution network monitoring data;
And obtaining a target parameter set in a set containing a plurality of preset parameter sets according to the first state parameter, wherein the target parameter set contains at least one second state parameter which is matched with the first state parameter.
In the above method, preferably, the parameter similarity value meets a preset alarm condition, including:
the parameter similarity value is smaller than or equal to a similarity threshold value;
wherein the similarity threshold is obtained by:
obtaining second historical state data, wherein the second historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the second historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set;
Generating an initial fuzzy rule statement corresponding to each historical moment according to a fuzzy set and a membership value in fuzzy data corresponding to each historical moment;
screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value;
performing anti-blurring processing on the target fuzzy rule sentences respectively to obtain preset parameter groups corresponding to each target fuzzy rule sentence;
obtaining a minimum similarity value between the preset parameter set and the power distribution network historical data in the second historical state data;
and obtaining a similarity threshold according to the minimum similarity value.
The method preferably outputs an alarm result corresponding to the monitoring data of the power distribution network, and the method comprises the following steps:
outputting a first alarm result, wherein the first alarm result is used for prompting the abnormal state parameters of the power distribution network;
and/or the number of the groups of groups,
outputting a second alarm result, wherein the second alarm result is used for prompting the abnormality of a target state parameter in the power distribution network; wherein the target state parameter is determined by:
Obtaining parameter error data between each state parameter in the power distribution network monitoring data and the corresponding state parameter in the target parameter set;
and determining the state parameter corresponding to the parameter error data meeting the error abnormal condition as a target state parameter.
In the above method, preferably, the error exception condition includes: the relative error value in the parameter error data is the largest in the parameter error data corresponding to all the state parameters;
wherein the relative error value is: the ratio between the parameter difference and the parameter value of the corresponding state parameter in the target parameter set is that: and a difference value of a parameter value between the state parameter in the power distribution network monitoring data and a corresponding state parameter in the target parameter set.
A power distribution network state parameter monitoring device, the device comprising:
the power distribution network monitoring system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring power distribution network monitoring data of a power distribution network at a target time, and the power distribution network monitoring data comprise a plurality of state parameters;
a second obtaining unit, configured to obtain, in a set including a plurality of preset parameter sets, a target parameter set corresponding to the power distribution network monitoring data, where the target parameter set includes a plurality of state parameters, where the preset parameter set in the set is generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical moments, each of the power distribution network historical data corresponding to a historical moment includes a plurality of state parameters, and the historical moment is a moment selected in a fault-free time period of the power distribution network;
The third acquisition unit is used for acquiring a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data;
and the output unit is used for outputting an alarm result corresponding to the power distribution network monitoring data under the condition that the parameter similarity value meets a preset alarm condition.
An electronic device, the electronic device comprising:
a memory for storing an application program and data generated by the operation of the application program;
a processor for executing the application program to realize: acquiring power distribution network monitoring data of a power distribution network at a target time, wherein the power distribution network monitoring data comprises a plurality of state parameters;
obtaining a target parameter set corresponding to the power distribution network monitoring data from a set containing a plurality of preset parameter sets, wherein the target parameter set contains a plurality of state parameters;
the method comprises the steps that a preset parameter set in a set is generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical moments, wherein the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
Obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data;
and under the condition that the parameter similarity value meets the preset alarm condition, outputting an alarm result corresponding to the power distribution network monitoring data.
According to the power distribution network state parameter monitoring method, device and electronic equipment disclosed by the application, after power distribution network monitoring data comprising a plurality of state parameters of a power distribution network at a target time are obtained, a target parameter set which corresponds to the power distribution network monitoring data and also comprises the plurality of state parameters is obtained from a set comprising a plurality of preset parameter sets, the preset parameter sets in the set are generated based on power distribution network historical data which correspond to the power distribution network at a plurality of historical times respectively, the historical times are selected in a fault-free time period of the power distribution network, and based on the fact, the method, device and electronic equipment output an alarm result corresponding to the power distribution network monitoring data by obtaining parameter similarity values between the state parameters in the target parameter sets and the state parameters in the power distribution network monitoring data under the condition that the parameter similarity values meet preset alarm conditions. Therefore, the power distribution network monitoring method and device can monitor whether the power distribution network is abnormal according to the parameter similarity by acquiring the parameter similarity between the state parameters in the power distribution network monitoring data and the historical state parameters of the power distribution network in the fault-free period, and avoid the inaccurate condition when a single and fixed threshold is monitored.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, 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 application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for monitoring a state parameter of a power distribution network according to a first embodiment of the present application;
FIG. 2 is a partial flow chart of a first embodiment of the present application;
FIG. 3 is a diagram showing the triangle membership function in the present embodiment;
FIG. 4 is a partial flow chart of a first embodiment of the present application;
fig. 5 is a schematic structural diagram of a power distribution network state parameter monitoring device according to a second embodiment of the present application;
fig. 6 is a schematic structural diagram of another power distribution network state parameter monitoring device according to the second embodiment of the present application;
fig. 7 is a schematic structural diagram of another power distribution network state parameter monitoring device according to the second embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to a third embodiment of the present application;
fig. 9 is a schematic block diagram of a power distribution network state parameter monitoring scheme according to an embodiment of the present application.
Detailed Description
At present, when monitoring the fault state of the power distribution network, a fixed threshold is usually set for collected power distribution network current and voltage data to determine whether state parameters such as current or voltage are abnormal or not.
According to the power distribution network state parameter monitoring method, the power distribution network state parameter monitoring device and the power distribution network state parameter monitoring method are further researched, so that monitoring efficiency can be improved, and fault states of the power distribution network can be monitored more accurately. The method comprises the following steps:
firstly, acquiring power distribution network monitoring data of a power distribution network at a target time, wherein the power distribution network monitoring data comprise a plurality of state parameters; then, in a set containing a plurality of preset parameter sets, obtaining a target parameter set corresponding to the power distribution network monitoring data, wherein the target parameter set contains a plurality of state parameters, the preset parameter sets in the set are generated based on power distribution network historical data respectively corresponding to the power distribution network at a plurality of historical moments, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; and finally, obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data, and outputting an alarm result corresponding to the power distribution network monitoring data under the condition that the parameter similarity value meets a preset alarm condition.
Therefore, the parameter similarity of the power distribution monitoring data and the target parameter set is obtained by obtaining the state parameters in the power distribution network monitoring data and the state parameters in the set of the target parameter set, and the state judgment is carried out according to the parameter similarity, so that the power distribution network normal state parameter reasoning and state judgment monitoring early warning are realized.
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
As shown in fig. 1, a method for monitoring a state parameter of a power distribution network according to an embodiment of the present application may be applied to an electronic device capable of performing data processing, such as a computer or a server. The electronic equipment in the application can be edge computing equipment in a power distribution network area, such as intelligent distribution transformer equipment in a transformer area. The technical scheme in the embodiment is mainly used for judging the state according to the parameter similarity based on the acquired power distribution monitoring data and the parameter similarity of the state parameter of the power distribution network in the fault-free state when the fault state of the power distribution network is monitored, so that the monitoring and early warning of the power distribution network state are realized.
In a specific implementation, the method in this embodiment may include the following steps:
step 101: and obtaining the monitoring data of the power distribution network at the target time.
Wherein the power distribution network monitoring data includes a plurality of status parameters. The state parameters refer to corresponding parameters of the power grid on corresponding power distribution and transformation projects, such as three-phase voltage, current, active power, reactive power, frequency, voltage-current unbalance degree, frequency deviation, transformer area load rate and the like of the power distribution and transformation.
The target time may be the current real-time or a time in a past history period.
In a specific implementation, in this embodiment, power distribution network monitoring data of a power distribution network at a target time may be collected by using power distribution network equipment, for example, state parameters such as three-phase voltage, current, active power, reactive power, frequency, voltage-current imbalance, frequency deviation, and platform load factor of a distribution transformer on a power distribution network at a current real-time are collected by using a current transformer and a voltage transformer.
Step 102: and obtaining a target parameter set corresponding to the monitoring data of the power distribution network from a set containing a plurality of preset parameter sets.
Wherein the target parameter group comprises a plurality of state parameters.
The preset parameter sets in the set are generated based on the power distribution network historical data respectively corresponding to a plurality of historical moments of the power distribution network, the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
in a specific implementation, in this embodiment, a plurality of historical time periods may be selected in a non-fault period of the power distribution network, then, power distribution network historical data corresponding to each historical time period is collected in a historical database, wherein the power distribution network historical data corresponding to each historical time period includes a plurality of state parameters, a plurality of preset parameter sets are obtained based on the state parameters in the power distribution network historical data, and each obtained preset parameter set includes a plurality of state parameters. Based on this, a target parameter set matched with the distribution network monitoring data is obtained from the preset parameter sets in step 102. For example, in 2018, when no fault occurs in the power distribution network, the power distribution network history data corresponding to the two historic moments of 1 month and 2 months in 2018 may be selected and a plurality of preset parameter sets may be generated based on the power distribution network history data corresponding to the two historic moments of 1 month and 2 months in 2018, where the power distribution network history data corresponding to the two months in 2018 includes state parameters such as three-phase voltage and current on the low-voltage side of the power distribution network, and the power distribution network history data corresponding to the two months in 2018 includes state parameters such as active power and reactive power. In the method, the preset parameter sets corresponding to each historical moment are obtained based on the historical data of the power distribution network respectively, the preset parameter sets at the moment are data sets formed by state parameters of the 2018 power distribution network in a normal state, namely in a fault-free state, based on the data sets, target parameter sets corresponding to monitoring data of the power distribution network are obtained from the preset parameter sets, and the target parameter sets also comprise a plurality of state parameters. It should be noted that the state parameters in the target parameter set are matched in kind with the state parameters in the monitoring data of the power distribution network.
Step 103: and obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data.
In a specific implementation, in this embodiment, a similarity function may be constructed to obtain a parameter similarity value between a state parameter in the target parameter set and a state parameter in the monitoring data of the power distribution network.
It should be noted that, the parameter similarity value between the state parameter in the target parameter set and the state parameter in the power distribution network monitoring data may be understood as a similarity value between the target parameter set and the power distribution network monitoring data with respect to the state parameter contained in each of them, where the parameter similarity value characterizes the similarity between the target parameter set and the power distribution network monitoring data.
Step 104: and under the condition that the parameter similarity value meets the preset alarm condition, outputting an alarm result corresponding to the monitoring data of the power distribution network.
The parameter similarity value characterizes the similarity between the target parameter set and the power distribution network monitoring data, the alarm condition characterizes the condition capable of triggering the alarm mechanism, and correspondingly, the alarm mechanism is triggered under the condition that the parameter similarity value meets the alarm condition, and the information of the output alarm result can contain the information of the power distribution network monitoring data with faults and also can contain the information of the faults of one or more state parameters in the power distribution network monitoring data.
In a specific implementation, the alarm condition in this embodiment may be: the parameter similarity value is less than or equal to the similarity threshold. Correspondingly, in the embodiment, under the condition that the parameter similarity value is smaller than or equal to the similarity threshold value, an alarm result corresponding to the monitoring data of the power distribution network is output.
As can be seen from the foregoing, in the method for monitoring a state parameter of a power distribution network according to the first embodiment of the present application, after obtaining power distribution network monitoring data including a plurality of state parameters of the power distribution network at a target time, a target parameter set including a plurality of state parameters corresponding to the power distribution network monitoring data is obtained through a set including a plurality of preset parameter sets, where the preset parameter sets in the set are generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical times respectively, and the historical times are selected times in a fault-free time period of the power distribution network. Therefore, the power distribution network monitoring method and device can monitor whether the power distribution network is abnormal according to the parameter similarity by acquiring the parameter similarity between the state parameters in the power distribution network monitoring data and the historical state parameters of the power distribution network in the fault-free period, and avoid the inaccurate condition when a single and fixed threshold is monitored.
Based on the method disclosed in fig. 1 in the embodiment of the present application, if the parameter similarity is to be known, a set corresponding to the power distribution network needs to be obtained in advance, and a specific implementation process is shown in fig. 2:
step 201: first historical state data is obtained.
The first historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a power distribution network fault-free moment section.
In a specific implementation, in this embodiment, a plurality of history times may be selected in a non-fault period of the power distribution network, a front history time in the non-fault period may be selected, a rear history time in the non-fault period may also be selected, a history time in a middle part in the non-fault period may be selected optimally, and then a plurality of state parameters corresponding to the history times may be obtained as first history state data, where the first history state data includes a plurality of power distribution network history state parameters corresponding to the plurality of history times respectively. For example, in 2017, the power distribution network has no faults, 6 months and 7 months in 2017 are selected as a first historical time period, current state parameters and voltage state parameters at a plurality of moments in 2017, 6 months in 2017 are obtained, a group of power distribution network historical data corresponding to each moment in the obtained state parameters is formed, frequency state parameters and active power state parameters at a plurality of moments in 2017 are obtained, and a group of power distribution network historical data corresponding to each moment in the obtained state parameters is formed. The plurality of sets of power distribution network historical data form first historical state data.
Step 202: and carrying out blurring processing on the power distribution network historical data corresponding to each historical moment in the first historical state data so as to obtain fuzzy data corresponding to each historical moment.
The fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the historical data of the power distribution network and a membership value corresponding to the fuzzy set.
Specifically, in this embodiment, the fuzzy controller may be used to perform fuzzy processing on the historical data of the power distribution network, so as to obtain fuzzy data corresponding to each historical moment.
Wherein, the fuzzification refers to a process that the fuzzy controller converts a determined value of the input quantity of the fuzzy controller into a corresponding fuzzy language variable value. The blurring processing in this embodiment is to convert the historical data of the power distribution network into the output of the fuzzy language variable values of different state parameters under the normal state parameter domain.
For example, in this embodiment, the fuzzy argument [ -6,6] is preset to be 7-level, each level determines a fuzzy set, each fuzzy set corresponds to a linguistic variable which sequentially represents NB (negative big), NM (negative middle), NS (negative small), Z (zero), PS (positive small), PM (median), and PB (positive big), and is represented by a triangular membership function, as shown in fig. 3, the triangular membership function in the graph refers to NB, NM, NS, Z, PS, PM, PB, the first fuzzy set refers to a numerical set from 0 to c2, the second fuzzy set refers to a numerical set from c1 to c3, the third fuzzy set refers to a numerical set from c2 to c4, the fourth fuzzy set refers to a numerical set from c3 to c5, the fifth fuzzy set refers to a numerical set from c4 to c6, the sixth fuzzy set refers to a numerical set from c5 to c7, the seventh fuzzy set refers to a numerical set from c6 to a numerical set from c2, wherein each fuzzy set from c1 to c7 represents a central point fuzzy set.
In a specific implementation, in this embodiment, the fuzzy processing of the hierarchical fuzzy aggregation method may be performed on the power distribution network history data corresponding to each history time in the first history state data, so as to obtain fuzzy data corresponding to each history time, where the fuzzy data corresponding to each history time includes a fuzzy set corresponding to each state parameter in the power distribution network history data and a membership value corresponding to the fuzzy set. For example, in this embodiment, the voltage state parameter and the current state parameter of the power distribution network corresponding to a certain historical time in 5 months of 2018 are subjected to the blurring processing of the hierarchical blurring method, so as to obtain blurring data corresponding to 5 months of 2018, where the blurring data includes blurring sets corresponding to the voltage state parameter and the current state parameter, and membership values corresponding to the blurring sets where the voltage state parameter and the current state parameter are located.
Step 203: and generating an initial fuzzy rule statement corresponding to each historical moment according to the fuzzy set and the membership value in the fuzzy data corresponding to each historical moment.
In specific implementation, in this embodiment, according to the fuzzy set and membership value in the fuzzy data corresponding to each historical moment, mining and reasoning obtain the initial fuzzy rule statement corresponding to each distribution and transformation state parameter in each historical moment. For example, according to the fuzzy set and the membership value in the fuzzy data corresponding to a certain historical time in the 1 month of 2018, mining and reasoning to obtain an initial fuzzy rule statement corresponding to the current state parameter and the voltage state parameter corresponding to the historical time in the 1 month of 2018.
The initial fuzzy rule statement may be understood as an association relationship between each state parameter in the power distribution network history data or description statement data of an association rule. For example, the association rule may employ an If-Then statement, described as follows:
If X 1 ＝X 1 i ，
Then X 2 ＝X 2 i ,X 3 ＝X 3 i ,…,X n ＝X n i
wherein: x is X 1 -X n Representing the state parameters of n distribution transformers at the same moment, X 2～n Represents dividing X 1 An external distribution power state parameter, wherein n represents the number of the state parameters of the distribution power at the same moment; i represents the sequence number of the association rule.
For example, the initial fuzzy rule sentence corresponding to the current state parameter and the voltage state parameter corresponding to a certain historical time a in month 1 of 2018 may be:
If X 1 ＝I 1 A ，
Then X 2 ＝U 2 A ；
wherein I is 1 A For the fuzzy set corresponding to the current state parameter corresponding to the historical moment A, U 2 A And the fuzzy set is a fuzzy set corresponding to the voltage state parameter corresponding to the historical moment A.
Step 204: and screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value.
Where confidence refers to the probability of B occurring in the case of a occurring in all transactions, and support refers to the probability of a and B occurring simultaneously in all transactions. In this embodiment, the association rule uses a minimum support s and a minimum confidence c as selection criteria, and the expressions of the minimum support s and the minimum confidence c are as shown in formula (1) and formula (2):
In the above formula, μ (X) represents X (X) 1 To X n ) D represents the total number of transactions in the X dataset. In the application, the minimum support degree and the minimum confidence degree of each initial fuzzy rule statement can be obtained in the above manner, then the initial fuzzy rule statement is screened according to the preset confidence degree threshold value and the preset support degree threshold value, and the screened initial fuzzy rule statement has the minimum support degree and the minimum confidence degree which must be achieved, such as a formula (3):
s(X 1 ∪X 2～n )≥s min ,c(X 1 ∪X 2～n )≥c min formula (3)
Wherein s is min Is a supportA duration threshold, c min Is a confidence threshold.
In a specific implementation, in this embodiment, at least the initial fuzzy rule statement is screened according to the minimum confidence value and the minimum support value of the fuzzy rule statement, and a target fuzzy rule statement with the minimum confidence value being greater than or equal to the confidence threshold and the minimum support value being greater than or equal to the support threshold is screened. For example, if the confidence threshold and the support threshold are respectively 0.3 and 0.6, the minimum support and the minimum confidence in each initial fuzzy rule sentence are respectively compared with the corresponding support threshold and confidence threshold to filter the initial fuzzy rule sentence, so as to obtain the minimum support s in the initial fuzzy rule sentence min Greater than or equal to the support threshold and minimum confidence level c min Target fuzzy rule statements greater than or equal to a confidence threshold.
Step 205: and respectively performing anti-blurring processing on the target fuzzy rule sentences to obtain a preset parameter set corresponding to each target fuzzy rule sentence.
The preset parameter sets corresponding to each historical moment form a set corresponding to the power distribution network. Defuzzification refers to the conversion of inferred fuzzy values into numerical values of well-defined state parameters.
In a specific implementation, in this embodiment, the fuzzy rule sentences obtained by the fuzzy processing performed in the foregoing are subjected to anti-fuzzy processing, so as to obtain numerical data of different state parameters under the normal state of each target fuzzy rule sentence, and the numerical data are stored in xml configuration files, that is, the corresponding set of the power distribution network.
In one implementation, step 205 further includes the following method before performing the defuzzification processing on the target fuzzy rule sentence in the fuzzy rule sentence set:
screening at least two fuzzy rule sentences meeting logic contradiction conditions in the target fuzzy rule sentences in the fuzzy rule sentence set according to the interestingness values of the fuzzy rule sentences to delete the target fuzzy rule sentences with the interestingness values smaller than or equal to the interestingness threshold value from the fuzzy rule sentences meeting the logic contradiction conditions, and finally obtaining the target fuzzy rule sentences reserved after screening.
Wherein the logical contradiction conditions include: at least one fuzzy set corresponding to the state parameter is different among the fuzzy rule sentences. For example, the fuzzy sets corresponding to the current state parameters in the target fuzzy rule sentence a and the target fuzzy rule sentence B are matched, for example, are all in a small fuzzy set, but the fuzzy sets corresponding to the voltage state parameters are respectively in a small fuzzy set and a medium fuzzy set, so that the fuzzy sets corresponding to the voltage state parameters of the target fuzzy rule sentence a and the target fuzzy rule sentence B are different, which is not in line with logic, and therefore, one sentence of the target fuzzy rule sentence a and the target fuzzy rule sentence B needs to be deleted. Specifically, one fuzzy rule sentence of which the interest value is smaller than or equal to the interest threshold value in the target fuzzy rule sentence a and the target fuzzy rule sentence B may be deleted.
Specifically, the interestingness I is a measure for representing the interesting degree of the rule, the larger the interestingness value is, the better the parameter relevance is under the guidance of the rule, and the expression is shown as a formula (4):
based on this, in this embodiment, for two or more target fuzzy rule sentences satisfying the logic contradiction condition, respective interestingness values of each target fuzzy rule sentence are obtained, and fuzzy rule sentences with interestingness values smaller than or equal to an interestingness threshold value in the target fuzzy rule sentences are deleted, for example, there are three target fuzzy rule sentences with different fuzzy sets corresponding to at least one state parameter, screening is performed according to the interestingness values of the fuzzy rule sentences in the three target fuzzy rule sentences, the interestingness threshold value of the fuzzy rule sentences is 0.5, and the target fuzzy rule sentences with interestingness values smaller than or equal to 0.5 are deleted.
In one implementation, step 204, before filtering the initial fuzzy rule sentence according to the minimum confidence value and the minimum support value of the fuzzy rule sentence, further includes the following method:
merging the same fuzzy rule sentences in the initial fuzzy rule sentences, wherein the same fuzzy rule sentences are as follows: the fuzzy set corresponding to each state parameter and the membership value corresponding to the fuzzy set are the same among the fuzzy rule sentences.
In particular implementation, in this embodiment, fuzzy sets corresponding to each state parameter between fuzzy rule statements in the initial fuzzy rule statements and initial fuzzy rule statements with the same membership value corresponding to the fuzzy sets are combined, for example, the fuzzy sets corresponding to the voltage state parameters in the two initial fuzzy rule statements and the membership values corresponding to the fuzzy sets are NB, and then the two initial fuzzy rule statements are combined, i.e. one of the initial fuzzy rule statements is deleted.
In one implementation, when the target parameter set is obtained in step 102, the target parameter set matched with the power distribution network monitoring data may be determined in the plan according to the state parameter in the power distribution network monitoring data. The method comprises the following steps:
Firstly, at least one first state parameter corresponding to power distribution network monitoring data is obtained from a plurality of state parameters in the power distribution network monitoring data; the first state parameter refers to a state parameter with a flag in the power grid monitoring data, for example, in the state parameters such as low-voltage side three-phase voltage, current, active power, load factor, reactive power, frequency and the like in the power grid monitoring data, the voltage, current, frequency and load factor are the identification variables therein, and at this time, the first state parameters corresponding to the identification variables are obtained, that is, the voltage, current, frequency and load factor are the first state parameters.
Then, a target parameter set can be obtained from a set including a plurality of preset parameter sets according to the first state parameter.
The target parameter set includes at least one second state parameter, where the second state parameter refers to a state parameter having a flag in the parameter set, and the second state parameter matches the first state parameter. That is, a parameter set of the selected target parameter set having a second state parameter consistent with the first state parameter in the power distribution network monitoring data. It should be noted that, the matching of the first state parameter and the second state parameter is that the types of the state parameters corresponding to the first state parameter and the second state parameter are the same, but the parameter values of the state parameters are not the same. It should be noted that, the first state parameter and the second state parameter are not sequentially divided, but represent two state parameters.
In a specific implementation, in this embodiment, at least two state parameters in the power distribution network monitoring data are obtained as first state parameters of the power distribution network monitoring data, then, in a set including a plurality of preset parameter sets, a target parameter set is obtained, at least two state parameters in the target parameter set are taken as second state data of the target parameter set, and the first state parameters are matched with the second state parameters, for example, the state parameters in the power distribution network monitoring data include three-phase voltage, current, active power, reactive power and frequency at the low voltage side, the state parameters in the power distribution network monitoring data include three-phase voltage, current, active power and frequency at the low voltage side, the state parameters in the power distribution network monitoring data, such as three-phase voltage, current and active power at the low voltage side are obtained as first state parameters of the power distribution network monitoring data, and in a set including a plurality of preset parameter sets, each preset parameter set includes three-phase voltage, current, active power, frequency deviation and a load rate of a station area and other state parameters (the state parameters in each preset parameter set may have the same state parameters) at the low voltage side, and the current side, i.e., the second state parameters are different from the preset parameter sets, i.e., the state parameters are the second state parameters and the current and the state parameters are the second state parameters.
In one implementation, step 104 may determine whether the parameter similarity value meets a preset alarm condition by comparing the parameter similarity value with a similarity threshold, for example, if the parameter similarity value is less than or equal to the similarity threshold, it may be determined that the alarm condition is met, and if the alarm condition is met, a corresponding alarm result is output.
Wherein the similarity threshold may be obtained as shown in fig. 4 by:
step 401: second historical state data is obtained.
The second historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a power distribution network fault-free moment section.
In a specific implementation, in this embodiment, a plurality of history times may be selected in a non-fault period of the power distribution network, a front history time in the non-fault period may be selected, a rear history time in the non-fault period may also be selected, a history time in a middle part in the non-fault period may be selected optimally, and then a plurality of state parameters corresponding to the history times may be obtained as second history state data, where the second history state data includes a plurality of power distribution network history state parameters corresponding to the plurality of history times respectively. For example, in 2019, the power distribution network has no faults, 6 months and 7 months in 2019 are selected as the second historical time period, the state parameters of the voltage and current unbalance degree and the frequency deviation at a plurality of moments in 2019, 6 months in 2019 are obtained, the obtained state parameters form a set of power distribution network historical data, the state parameters of the current and the active power at a plurality of moments in 2019, 7 months in 2019 are obtained, and the obtained state parameters form a set of power distribution network historical data. The plurality of sets of power distribution network historical data form second historical state data.
Step 402: and carrying out blurring processing on the power distribution network historical data corresponding to each historical moment in the second historical state data so as to obtain fuzzy data corresponding to each historical moment.
The fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the historical data of the power distribution network and a membership value corresponding to the fuzzy set;
specifically, the fuzzy processing of the grading fuzzy aggregation method can be performed on the power distribution network historical data corresponding to each historical moment in the second historical state data, so as to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set.
The implementation of step 402 in implementing the blurring process may refer to the implementation of step 202, which is not described in detail herein.
Step 403: and generating an initial fuzzy rule statement corresponding to each historical moment according to the fuzzy set and the membership value in the fuzzy data corresponding to each historical moment.
Specifically, according to the fuzzy set and membership value in the fuzzy data corresponding to each historical moment, mining and reasoning to obtain initial fuzzy rule sentences corresponding to each distribution and transformation state parameter in each historical moment.
The implementation of step 403 in generating the initial ambiguous sentence may refer to the implementation of step 203, which is not described in detail herein.
Step 404: and screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value.
Specifically, at least screening the initial fuzzy rule statement according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement, and screening out a target fuzzy rule statement with the minimum confidence coefficient value being greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value being greater than or equal to a support coefficient threshold value.
The implementation of step 404 in filtering the minimum confidence value and the minimum support value may refer to the implementation of step 204, which is not described in detail herein.
Step 405 performs anti-blurring processing on the target fuzzy rule sentences to obtain a preset parameter set corresponding to each target fuzzy rule sentence.
The implementation of step 405 in implementing the defuzzification process may refer to the implementation of step 205, which is not described in detail herein.
Step 406: and obtaining a minimum similarity value between the preset parameter set and the power distribution network historical data in the second historical state data.
Where similarity refers to a measure of similarity between two sets of state parameters. In this embodiment, a euclidean distance calculation method in a vector space distance calculation algorithm may be used to obtain a similarity value between each preset parameter set and the corresponding power distribution network history data, and based on this, obtain a minimum similarity value. Wherein, euclidean distance formula is as formula (5):
in the above formula, d ij Representing a real-time monitoring state parameter set x i (i.e. distribution network history data) and corresponding set of normal state parameters x in xml file (collection) j The Euclidean distance between (i.e. the preset parameter sets), n represents the dimension of the state parameter set, k represents the parameter number in the state parameter set, x ik And x jk Respectively represent normal state parameter groups x i And monitoring a state parameter set x j A corresponding kth parameter element. In engineering applications, S ij ＝1/(1+d ij ) Is commonly used for standardizing Euclidean distance range to [0,1 ]]. Thus, for evaluating the normal state parameter set x i And monitoring a state parameter set x j The similarity function between the two is set as in formula (6):
in a specific implementation, the preset parameter set obtained in step 305 is used as a minimum similarity value calculation basis to obtain the preset parameter set and the historical number of the power distribution network in the second historical state data The minimum similarity value between the data is S m . Alternatively, in this embodiment, the preset parameter set (i.e. the normal state parameter data) of the distribution network in the xml file obtained in step 205 may be used as a minimum similarity value calculation basis, so as to obtain a minimum similarity value S between the preset parameter set and the distribution network history data in the first history state data m 。
For example, in this embodiment, a value (380 v) of a three-phase voltage on a low-voltage side and a value (50 hz) of a frequency of a distribution transformer of a normal state parameter set of a preset parameter set of a distribution network in an xml configuration file are obtained as determination criteria, and state parameters in historical data of the distribution network are obtained: after the three-phase voltage of the distribution transformer is 450v and the frequency is 45hz, the state parameters in the historical data of the distribution network are as follows: and performing similarity calculation on the three-phase voltage 450v and the frequency 45hz of the distribution transformer low-voltage side and the three-phase voltage 380v and the frequency 50hz of the distribution transformer low-voltage side in the preset parameter set obtained by fuzzy reasoning to obtain a minimum similarity value of 0.8 between the preset parameter set and the historical data of the power distribution network in the second historical state data.
Step 407: and obtaining a similarity threshold according to the minimum similarity value.
In particular implementation, the minimum similarity S in this embodiment m And threshold coefficient k t Is set as the similarity threshold S t (which may also be referred to as a similarity warning threshold), as in equation (7):
S t ＝k t ·S m formula (7)
In the above formula, the threshold coefficient k t Can be set to a proper value according to the monitoring sensitivity requirement in practical application, for example, the minimum similarity S m Is 0.4, threshold coefficient k t kt is 2, then a similarity threshold of 0.8 is obtained, based on which, in this embodiment, the parameter similarity value is found to be less than or equal to the similarity threshold S t And outputting an alarm result.
In one implementation, step 104 may be implemented when outputting an alarm result corresponding to the monitoring data of the power distribution network by:
outputting a first alarm result, wherein the first alarm result is used for prompting the abnormal state parameters of the power distribution network; and/or outputting a second alarm result, wherein the second alarm result is used for prompting the abnormality of the target state parameter in the power distribution network.
When the first alarm result and the second alarm result are output at the same time, the output of the first alarm result and the second alarm result may not be divided into a sequential order, or the first alarm result is output first and then the second alarm result is output.
In a specific implementation, in this embodiment, there are three situations of outputting an alarm result, and only the first alarm result may be output to prompt that the state parameter of the power distribution network is abnormal, for example, the power distribution network is abnormal; only the second alarm result can be output to prompt that the target parameter in the power distribution network is abnormal, for example, the voltage state parameter is abnormal; the method can also output a first alarm result and a second alarm result, wherein the first alarm result is used for prompting the abnormal occurrence of the state parameter of the power distribution network, and the second alarm result is used for prompting the abnormal occurrence of the target parameter in the power distribution network, such as the abnormal occurrence of the power distribution network and the abnormal occurrence of the power distribution network on the voltage state parameter.
Example one: and outputting the first alarm result to the power distribution and transformation equipment platform and the database, wherein the first alarm result output to the power distribution and transformation equipment platform and the database prompts that the power distribution network has abnormal state parameters at the target moment.
Example two: and outputting the second alarm result to the power distribution and transformation equipment platform and the database, wherein the second alarm result output to the power distribution and transformation equipment platform and the database prompts that the voltage state parameter and the current state parameter in the state parameters of the power distribution network are abnormal.
Example three: and outputting the first alarm result and the second alarm result to the power distribution and transformation equipment platform and the database, wherein the first alarm result in the power distribution and transformation equipment platform and the database prompts that the state parameters of the power distribution network are abnormal at the target moment, and the second alarm result prompts that the voltage state parameters and the current state parameters of the power distribution network are abnormal.
Wherein the target state parameter is determined by:
and obtaining parameter error data between each state parameter in the power distribution network monitoring data and the corresponding state parameter in the target parameter set, and determining the state parameter corresponding to the parameter error data meeting the error abnormal condition as the target state parameter.
Wherein the error exception condition includes:
the relative error value in the parameter error data is the largest in the parameter error data corresponding to each state parameter, wherein the relative error value is: the ratio between the parameter difference and the parameter value of the corresponding state parameter in the target parameter set is: differences in parameter values between the state parameters in the power distribution network monitoring data and their corresponding state parameters in the target parameter set.
In particular implementation, in this embodiment, each state parameter in the monitoring data of the power distribution network is compared with a corresponding normal state parameter in a target parameter set where the state parameter is located, a difference value between the state parameters is obtained first and then divided by the corresponding normal state parameter in the target parameter set where the state parameter is located to obtain relative errors, after the relative errors are obtained, a plurality of relative errors in the state parameter set at the same time are compared, the state parameter corresponding to the maximum relative error is determined as the target state parameter, for example, the obtained current value in the monitoring data of the power distribution network is 500A, the voltage value is 360V, the current value of the corresponding normal state parameter in the target parameter set where the state parameter is 600A, the voltage value is 380V, the current value 600A of the normal state parameter is subtracted by the current value 500A of the monitoring data of the power distribution network, the difference value 100A between the two is divided by the current value 600A of the normal state parameter to obtain the relative error which is 0.167, the voltage value 380V of the normal state parameter is subtracted by the voltage value 360V of the monitoring data of the power distribution network, the difference value 20V between the two is divided by the voltage value 380V of the normal state parameter to obtain the relative error which is finally obtained as the maximum state parameter, and the maximum relative error is determined.
Referring to fig. 5, for a schematic structural diagram of a power distribution network state parameter monitoring device provided in a second embodiment of the present application, the device may be configured in an electronic device capable of performing data processing, and the technical scheme in the present application is mainly used for monitoring faults and early warning of power distribution, creating an intelligent device with an edge computing function and a general software platform, and deploying a power distribution network fault monitoring system in the form of software APP in the power distribution network device software platform, so as to achieve power distribution network running state monitoring and fault real-time early warning functions, thereby improving monitoring efficiency, and enabling fault judgment standards to be more accurate.
In particular, the device may comprise the following units:
a first obtaining unit 501, configured to obtain power distribution network monitoring data of a power distribution network at a target time, where the power distribution network monitoring data includes a plurality of state parameters;
the second obtaining unit 502 is configured to obtain, in a set including a plurality of preset parameter sets, a target parameter set corresponding to monitoring data of the power distribution network, where the target parameter set includes a plurality of state parameters, the preset parameter sets in the set are generated based on power distribution network historical data corresponding to a plurality of historical moments of the power distribution network respectively, each of the historical moments corresponds to power distribution network historical data including a plurality of state parameters, and the historical moments are moments selected in a fault-free time period of the power distribution network;
The second obtaining unit 402 is specifically configured to: at least one first state parameter corresponding to the power distribution network monitoring data is obtained from a plurality of state parameters in the power distribution network monitoring data; according to the first state parameter, a target parameter set is obtained from a set containing a plurality of preset parameter sets, wherein the target parameter set contains at least one second state parameter, and the second state parameter is matched with the first state parameter.
A third obtaining unit 503, configured to obtain a parameter similarity value between the state parameter in the target parameter set and the state parameter in the monitoring data of the power distribution network;
and the output unit 504 is configured to output an alarm result corresponding to the monitoring data of the power distribution network when the parameter similarity value meets a preset alarm condition.
The case where the parameter similarity value in the output unit 504 meets the preset alarm condition is specifically used for: the parameter similarity value is less than or equal to a similarity threshold; wherein the similarity threshold is obtained by: obtaining second historical state data, wherein the second historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a power distribution network fault-free moment section; carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the second historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set; generating an initial fuzzy rule statement corresponding to each historical moment according to the fuzzy set and the membership value in the fuzzy data corresponding to each historical moment; screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement with the minimum confidence coefficient value being greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value being greater than or equal to a support coefficient threshold value; respectively performing anti-blurring processing on the target fuzzy rule sentences to obtain preset parameter groups corresponding to each target fuzzy rule sentence; obtaining a minimum similarity value between the preset parameter set and the power distribution network historical data in the second historical state data; and obtaining a similarity threshold according to the minimum similarity value.
When the output unit 504 outputs the alarm result corresponding to the monitoring data of the power distribution network, the following implementation manners may be provided:
outputting a first alarm result, wherein the first alarm result is used for prompting the abnormal state parameters of the power distribution network; and/or outputting a second alarm result, wherein the second alarm result is used for prompting the abnormality of the target state parameter in the power distribution network; wherein the target state parameter is determined by: acquiring parameter error data between each state parameter in the power distribution network monitoring data and the corresponding state parameter in the target parameter set; determining a state parameter corresponding to parameter error data meeting error exception conditions as a target state parameter, wherein the error exception conditions comprise: the relative error value in the parameter error data is the largest in the parameter error data corresponding to all the state parameters; wherein the relative error value is: the ratio between the parameter difference and the parameter value of the corresponding state parameter in the target parameter set is: differences in parameter values between the state parameters in the power distribution network monitoring data and their corresponding state parameters in the target parameter set.
As can be seen from the foregoing, in the power distribution network state parameter monitoring device provided in the second embodiment of the present application, after obtaining power distribution network monitoring data including a plurality of state parameters of a power distribution network at a target time, a target parameter set including a plurality of state parameters corresponding to the power distribution network monitoring data is obtained through a set including a plurality of preset parameter sets, where the preset parameter sets in the set are generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical times respectively, and the historical times are times selected in a power distribution network fault-free time period. Therefore, the power distribution network monitoring method and device can monitor whether the power distribution network is abnormal according to the parameter similarity by acquiring the parameter similarity between the state parameters in the power distribution network monitoring data and the historical state parameters of the power distribution network in the fault-free period, and avoid the inaccurate condition when a single and fixed threshold is monitored.
Referring to fig. 6, the apparatus in the second embodiment of the present application further includes a fourth obtaining unit 505, configured to obtain, in advance, a set corresponding to the power distribution network, where the fourth obtaining unit 505 specifically includes the following structure, as shown in fig. 7:
the historical data obtaining module 701 is configured to obtain first historical state data, where the first historical state data includes a set of historical data of the power distribution network corresponding to a plurality of historical moments, each of the historical data of the power distribution network corresponding to a plurality of historical moments includes a plurality of state parameters, and the historical moments are moments selected in a fault-free time period of the power distribution network.
The fuzzy data obtaining module 702 is configured to perform a fuzzification process on the power distribution network historical data corresponding to each historical time in the first historical state data, so as to obtain fuzzy data corresponding to each historical time, where the fuzzy data corresponding to each historical time includes a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set.
The sentence acquisition module 703 is configured to generate an initial fuzzy rule sentence corresponding to each historical moment according to the fuzzy set and the membership value in the fuzzy data corresponding to each historical moment.
The initial filtering module 704 is configured to filter at least the initial fuzzy rule sentence according to the minimum confidence value and the minimum support value of the fuzzy rule sentence, so as to obtain a target fuzzy rule sentence with the minimum confidence value being greater than or equal to the confidence threshold and the minimum support value being greater than or equal to the support threshold.
The merging module 705 is configured to merge identical fuzzy rule sentences in the initial fuzzy rule sentences before the initial filtering module 704 filters the initial fuzzy rule sentences, where the identical fuzzy rule sentences are: the fuzzy set corresponding to each state parameter and the membership value corresponding to the fuzzy set are the same among the fuzzy rule sentences.
The defuzzification module 706 is configured to perform defuzzification processing on the target fuzzy rule sentences to obtain preset parameter sets corresponding to each target fuzzy rule sentence, where the preset parameter sets corresponding to each history moment form a set corresponding to the power distribution network.
The interestingness screening module 707 is configured to screen at least two fuzzy rule sentences satisfying the logic contradiction condition in the target fuzzy rule sentences according to the interestingness value of the fuzzy rule sentences before the anti-fuzzy module 706 performs anti-fuzzy processing, so as to delete fuzzy rule sentences whose interestingness value is less than or equal to the interestingness threshold value in the fuzzy rule sentences satisfying the logic contradiction condition; wherein the logical contradiction conditions include: at least one fuzzy set corresponding to the state parameter is different among the fuzzy rule sentences.
It should be noted that, the specific implementation of each unit in this embodiment may refer to the corresponding content in the foregoing, which is not described in detail herein.
Referring to fig. 8, a schematic structural diagram of an electronic device according to a third embodiment of the present application may be an electronic device capable of performing data processing, such as a computer or a server. The electronic device in this embodiment mainly builds a model of prosody recognition.
Specifically, the electronic device in this embodiment may include the following structure:
a memory 801 for storing an application program and data generated by the running of the application program;
a processor 802 for executing an application program to implement: acquiring power distribution network monitoring data of a power distribution network at a target time, wherein the power distribution network monitoring data comprise a plurality of state parameters; obtaining a target parameter set corresponding to the monitoring data of the power distribution network from a set containing a plurality of preset parameter sets, wherein the target parameter set contains a plurality of state parameters; the method comprises the steps that a preset parameter set in a set is generated based on power distribution network historical data corresponding to a plurality of historical moments of a power distribution network respectively, the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data; and under the condition that the parameter similarity value meets the preset alarm condition, outputting an alarm result corresponding to the monitoring data of the power distribution network.
As can be seen from the foregoing, in the electronic device according to the third embodiment of the present application, after obtaining the power distribution network monitoring data including a plurality of state parameters of the power distribution network at the target time, the target parameter set including a plurality of state parameters corresponding to the power distribution network monitoring data is obtained through a set including a plurality of preset parameter sets, where the preset parameter sets in the set are generated based on the power distribution network historical data corresponding to the power distribution network at a plurality of historical times respectively, and the historical times are selected in a fault-free time period of the power distribution network. Therefore, the power distribution network monitoring method and device can monitor whether the power distribution network is abnormal according to the parameter similarity by acquiring the parameter similarity between the state parameters in the power distribution network monitoring data and the historical state parameters of the power distribution network in the fault-free period, and avoid the inaccurate condition when a single and fixed threshold is monitored.
It should be noted that, the specific implementation of the processor in this embodiment may refer to the corresponding content in the foregoing, which is not described in detail herein.
Taking monitoring of a power distribution network in a certain country or region as an example, fig. 9 is a schematic diagram of a power distribution network state parameter monitoring scheme according to an embodiment of the present application, where the following modules are used for collecting early-stage state parameter data and monitoring and early warning faults of the power distribution network, and the schematic diagram includes the following modules: module 1: a power distribution and transformation equipment platform and a database; module 2: the data sampling, selecting and preprocessing module; module 3: the fuzzy association rule mining and expert knowledge base module; module 4: and the state parameter similarity judging module.
As shown in fig. 9, the power distribution and transformation equipment platform and database module are connected with the data selection and preprocessing module and the state parameter similarity judging module, the data selection and preprocessing module is connected with the fuzzy association rule mining and expert knowledge base module and the state parameter similarity judging module, and the fuzzy association rule mining and expert knowledge base module is connected with the state parameter similarity judging module.
Firstly, the distribution and transformation equipment platform and the database module transmit data in a distribution and transformation area to the data sampling, selecting and preprocessing module, and meanwhile, the fault early warning signals for judging the final state parameter similarity sent by the state parameter similarity judging module are received, so that the platform function of data information interaction is achieved;
The data sampling, selecting and preprocessing module comprises two parts: one part is parameter sampling, selecting and preprocessing in an offline state, and the other part is a modeling foundation of a fuzzy association rule mining inference engine; the other part is sampling, selecting and preprocessing of the real-time monitoring state parameters in the on-line state, and the part is a working basis for judging the similarity of the state parameters;
the fuzzy association rule mining and expert knowledge base module is used for mining fuzzy rule sentences among variables from the state parameters after the sampling processing in the offline state, describing the relativity among the state parameters by rule language, and the fuzzy rule sentences obtained by reasoning are the expert knowledge base. The rule data in the expert knowledge base is required to be converted into the power distribution network normal state parameter numerical data, and the power distribution network normal state parameter numerical data is required to be constructed into a configuration file form which can be called by power distribution network equipment so as to be used for judging subsequent state parameters;
the state parameter similarity judging module is used for comparing the similarity difference between the real-time monitoring state parameter and the deduced standard normal state parameter, and sending out early warning when the similarity difference exceeds a similarity threshold value. The state parameter similarity judging module mainly aims at developing and compiling a function APP, and the APP not only needs to read the normal state parameter value of the power distribution network in the configuration file as a judging standard, but also needs to receive real-time monitoring state parameter data, and outputs a state judging result in real time after the state judgment.
Specifically, in combination with the above modules, the technical scheme of the application realizes the monitoring of the state parameters of the power distribution network through the following processes:
step one: and searching normal historical data from a power distribution and transformation equipment platform and a database of the module 1, and sampling, selecting and preprocessing the historical data related to power distribution network monitoring in an off-line state. According to the sampling time of 50 mu s and taking the local time of equipment as a reference, sampling a power distribution network fault related data set at the same moment to serve as a group of power distribution network state parameters, wherein the specific power distribution network state parameters comprise: and the distribution transformer has three-phase voltage, current, active power, reactive power, frequency, voltage-current imbalance degree, frequency deviation, transformer area load rate and other state parameters. In order to ensure the accuracy and representativeness of the data, cleaning and preprocessing are required to be carried out on the data samples, and outliers caused by metering errors, sensor faults and environmental changes are removed;
step two: and (3) inputting the processed normal power distribution network state parameters in the offline state of the module 2 into a fuzzy association rule mining inference engine model. The core work of the step is to utilize the historical data of the actual power distribution network state parameters to mine and infer the association relation among the power distribution network state parameters, namely fuzzy rule sentences. The fuzzy rule statement is a fuzzy item set implication type among all monitoring state parameters, no intersection exists among the two fuzzy item sets, fuzzy association rules obtained by the inference engine are stored in an expert knowledge base in the form of rule groups, and each rule qualitatively represents the range grade of the parameters in the domain by fuzzy data. The association rule adopts If-Then sentences, which are described as follows:
Wherein: x is X 1 To X n Representing different distribution and transformation state parameters X at the same time 2～n Represents dividing X 1 The state parameters of the external power distribution network, wherein n represents the number of the state parameters of different power distribution networks at the same time; i represents the sequence numbers of the rules at different moments in the expert knowledge base.
For fuzzy association rule mining, it is most critical how to select the most valuable association rule from association rules corresponding to a large amount of data. For the traditional fuzzy association mining method, the association rule takes the minimum support degree s and the minimum confidence degree c as selection criteria, and the expressions are shown in a formula (1) and a formula (2) respectively.
Wherein: mu (X) represents X (X) 1 To X n ) D represents the total number of transactions in the X dataset. The data mining aims at finding out credible and representative rules, firstly obtaining the minimum support degree and the minimum confidence degree of each initial fuzzy rule statement, then screening the initial fuzzy rule statement according to a preset confidence degree threshold value and a preset support degree threshold value, and finally obtaining the minimum support degree s min And minimum confidence level c min Thresholds for the support and confidence are specified, which respectively specify the minimum support and confidence that must be achieved by the establishment of the association rule, and the minimum support and confidence that must be achieved by the filtered initial fuzzy rule statement is shown as formula (3).
However, if only the minimum support and confidence conditions are used as rule selection criteria, many inference rules can be found to meet the minimum support and confidence conditions, and the inference rules contradict each other, which can cause inference decision failure. Thus, minimum support and minimum confidence often do not ensure that association rules are both valuable, even if rule bias or misleading occurs at times.
When the fuzzy association rule mining is carried out, the interest concept is introduced to screen the most valuable rule based on the traditional minimum support and confidence. The interestingness I is a measure for representing the interesting degree of the rule, and the higher the interestingness value is, the better the parameter relevance is under the guidance of the rule, and the expression is shown in a formula (4).
According to the fuzzy association rule, selecting a standard selected bedding to be used as finally obtaining the fuzzy data of the normal state parameters of the power distribution network, and carrying out the detailed modeling step of modeling the fuzzy association rule mining inference engine model in the module 3, wherein the detailed modeling step is expressed as follows:
(1) Determining that X1 to Xn represent the state parameters of n distribution transformers at the same time, and carrying out fuzzification processing of a grading fuzzy set method on the power distribution network state parameter historical data after the sampling pretreatment: dividing the precise quantity on the state parameter domain into a plurality of files, determining a fuzzy aggregation for each file, and presetting the fuzzy domain as [ -6,6 [ ]Fuzzy aggregationThe number is 7, and the corresponding linguistic variables sequentially represent NB (negative big), NM (negative medium), NS (negative small), Z (zero), PS (positive small), PM (median) and PB (positive big), and are represented by triangle membership functions, as shown in FIG. 3. Wherein c 1 To c 7 And the central points of the fuzzy sets of the data in the EKB are represented, and the central points are cluster centers obtained by carrying out cluster analysis on the state parameters through a K-means clustering algorithm.
(2) Establishing a power distribution network state parameter X from fuzzy data obtained by performing fuzzy processing on a large amount of historical data in Step1 1 To X n Rule1 of the initial fuzzy Rule base.
(3) Merging X in Rule1 1 To X n The same fuzzy Rule sentences are obtained to obtain a fuzzy Rule base Rule2, and the minimum support degree s corresponding to each fuzzy Rule in the fuzzy Rule base Rule2 is calculated according to the formulas (1) and (2) min And minimum confidence level c min 。
(4) Selecting standard according to traditional rule, and minimum support degree s min And confidence level c min Is respectively set to 0.3 and 0.6, and the fuzzy Rule base Rule2 is deleted according to the formula (3) that the support degree s is lower than the minimum support degree s min And confidence level c min And (3) sorting to obtain a fuzzy Rule library Rule3.
(5) Checking whether contradictory redundant rules exist in the fuzzy Rule base Rule3, if so, calculating the interestingness of different fuzzy Rule sentences by using the formula (4), and selecting the fuzzy Rule sentences with the maximum interestingness calculation result in Rule3 to form the fuzzy Rule base Rule4 according to the principle of maximum interestingness, wherein the fuzzy Rule base Rule4 is the expert knowledge base in the module 3.
(6) And (3) taking fuzzy association rules in an expert knowledge base as guidance, and obtaining output of different state parameter normalization values under a normal state parameter domain by using a fuzzy controller in MATLAB software, namely synthesizing an input vector and a fuzzy relation.
(7) And finally, obtaining numerical data of different state parameters under a normal state by utilizing anti-fuzzy processing of fuzzy value output, and storing the numerical data into an xml configuration file.
Step three: the module 4 parameter similarity judging module is used for comparing the similarity difference between the real-time monitoring state parameter and the deduced normal state parameter, so that a similarity function needs to be constructed. The similarity function reads the normal state parameter value of the distribution network in the xml configuration file in the module 3 as a judgment standard, and simultaneously receives the real-time monitoring state parameter value in the module 2 as input, and the state judgment result is required to be output to the distribution and transformation equipment platform and the database of the module 1 in real time after the state judgment. The similarity function is a measure describing the similarity between two sets of state parameter samples, and is therefore constructed based on the most common euclidean distance in the vector space distance, and the euclidean distance formula is shown in formula (5).
Wherein d ij Representing a real-time monitoring state parameter set x i Normal state parameter set x corresponding to xml file j The Euclidean distance between the two, n represents the dimension of the state parameter group, k represents the parameter serial number in the state parameter group, and x ik And x jk Respectively represent normal state parameter groups x i And monitoring a state parameter set x j A corresponding kth parameter element.
In engineering applications, S ij ＝1/(1+d ij ) Is commonly used for standardizing Euclidean distance range to [0,1 ]]. Thus, for evaluating the normal state target parameter group x i And monitoring a state parameter set x j The similarity function setting between them is shown in formula (6).
Collecting historical data of power distribution network state parameters in a normal state from power distribution network equipment again, and defining the minimum similarity between all the power distribution network normal operation state parameter sets obtained through fuzzy reasoning and the actual normal state parameter sets as S m Will minimize the similarity S m And threshold coefficient k t Is set as a similarity early warning threshold S t As shown in equation (7).
When the similarity of the monitoring states is lower than the similarity early warning threshold S t The system sounds an alarm where the threshold coefficient k t Suitable values may be set according to the monitoring sensitivity requirements. In addition, after fault early warning, the parameter number k with the largest relative error in each state parameter group is marked abnormally so as to determine the fault state The parameter, monitoring maintenance personnel can analyze the fault state parameter characteristic and cooperate with equipment inspection, and finally the fault type is determined.
According to the algorithm logic, the C++ language is utilized for embedded programming development, a similarity function is constructed to capture the difference between the state parameters, and the comparison function between the real-time monitoring state parameters and the reasoning normal state parameters is realized. After the linux platform is compiled, the obtained function APP is matched with the xml configuration file in the step 2 to be transmitted to power distribution network equipment through an equipment debugging tool, so that the on-line monitoring of the state parameters of the power distribution network is finally realized, and early warning signals are reported to the equipment platform through an interactive interface when fault early warning occurs.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. 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 application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. A method for monitoring a state parameter of a power distribution network, the method comprising:
acquiring power distribution network monitoring data of a power distribution network at a target time, wherein the power distribution network monitoring data comprises a plurality of state parameters;
Obtaining a target parameter set corresponding to the power distribution network monitoring data from a set containing a plurality of preset parameter sets, wherein the target parameter set contains a plurality of state parameters;
the method comprises the steps that a preset parameter set in a set is generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical moments, wherein the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data;
outputting an alarm result corresponding to the monitoring data of the power distribution network under the condition that the parameter similarity value meets a preset alarm condition;
the parameter similarity value meets a preset alarm condition and comprises the following steps: the parameter similarity value is smaller than or equal to a similarity threshold value;
wherein the similarity threshold is obtained by:
obtaining second historical state data, wherein the second historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the second historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set; generating an initial fuzzy rule statement corresponding to each historical moment according to a fuzzy set and a membership value in fuzzy data corresponding to each historical moment; screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value; performing anti-blurring processing on the target fuzzy rule sentences respectively to obtain preset parameter groups corresponding to each target fuzzy rule sentence; obtaining a minimum similarity value between the preset parameter set and the power distribution network historical data in the second historical state data; and obtaining a similarity threshold according to the minimum similarity value.
2. The method according to claim 1, wherein the method further comprises:
the method for obtaining the set corresponding to the power distribution network in advance specifically comprises the following steps:
obtaining first historical state data, wherein the first historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network;
carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the first historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set;
generating an initial fuzzy rule statement corresponding to each historical moment according to a fuzzy set and a membership value in fuzzy data corresponding to each historical moment;
screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value;
And performing anti-blurring processing on the target fuzzy rule sentences respectively to obtain preset parameter sets corresponding to each target fuzzy rule sentence, wherein the preset parameter sets corresponding to each history moment form a set corresponding to the power distribution network.
3. The method of claim 2, wherein prior to defuzzifying the target fuzzy rule statement, the method further comprises:
screening at least two fuzzy rule sentences meeting the logic contradiction conditions in the target fuzzy rule sentences according to the interestingness values of the fuzzy rule sentences to delete the fuzzy rule sentences with the interestingness values smaller than or equal to the interestingness threshold value in the fuzzy rule sentences meeting the logic contradiction conditions;
wherein the logical contradictory conditions include: at least one fuzzy set corresponding to the state parameter is different among the fuzzy rule sentences.
4. The method of claim 2, wherein prior to filtering the initial fuzzy rule statement based on the minimum confidence value and the minimum support value of the fuzzy rule statement, the method further comprises:
merging the same fuzzy rule sentences in the initial fuzzy rule sentences, wherein the same fuzzy rule sentences are as follows: the fuzzy set corresponding to each state parameter and the membership value corresponding to the fuzzy set are the same among the fuzzy rule sentences.
5. The method according to claim 1, wherein obtaining a set of target parameters corresponding to the distribution network monitoring data from a set of a plurality of preset parameter sets comprises:
at least one first state parameter corresponding to the power distribution network monitoring data is obtained from a plurality of state parameters in the power distribution network monitoring data;
and obtaining a target parameter set in a set containing a plurality of preset parameter sets according to the first state parameter, wherein the target parameter set contains at least one second state parameter which is matched with the first state parameter.
6. The method of claim 1, wherein outputting an alarm result corresponding to the power distribution network monitoring data comprises:
outputting a first alarm result, wherein the first alarm result is used for prompting the abnormal state parameters of the power distribution network;
and/or the number of the groups of groups,
outputting a second alarm result, wherein the second alarm result is used for prompting the abnormality of a target state parameter in the power distribution network; wherein the target state parameter is determined by:
obtaining parameter error data between each state parameter in the power distribution network monitoring data and the corresponding state parameter in the target parameter set;
And determining the state parameter corresponding to the parameter error data meeting the error abnormal condition as a target state parameter.
7. The method of claim 6, wherein the error exception condition comprises: the relative error value in the parameter error data is the largest in the parameter error data corresponding to all the state parameters;
wherein the relative error value is: the ratio between the parameter difference and the parameter value of the corresponding state parameter in the target parameter set is that: and a difference value of a parameter value between the state parameter in the power distribution network monitoring data and a corresponding state parameter in the target parameter set.
8. A power distribution network state parameter monitoring device, the device comprising:
the power distribution network monitoring system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring power distribution network monitoring data of a power distribution network at a target time, and the power distribution network monitoring data comprise a plurality of state parameters;
a second obtaining unit, configured to obtain, in a set including a plurality of preset parameter sets, a target parameter set corresponding to the power distribution network monitoring data, where the target parameter set includes a plurality of state parameters, where the preset parameter set in the set is generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical moments, each of the power distribution network historical data corresponding to a historical moment includes a plurality of state parameters, and the historical moment is a moment selected in a fault-free time period of the power distribution network;
The third acquisition unit is used for acquiring a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data;
the output unit is configured to output an alarm result corresponding to the monitoring data of the power distribution network when the parameter similarity value meets a preset alarm condition, where the parameter similarity value meets the preset alarm condition, and includes: the parameter similarity value is smaller than or equal to a similarity threshold value;
wherein the similarity threshold is obtained by: obtaining second historical state data, wherein the second historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the second historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set; generating an initial fuzzy rule statement corresponding to each historical moment according to a fuzzy set and a membership value in fuzzy data corresponding to each historical moment; screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value; performing anti-blurring processing on the target fuzzy rule sentences respectively to obtain preset parameter groups corresponding to each target fuzzy rule sentence; obtaining a minimum similarity value between the preset parameter set and the power distribution network historical data in the second historical state data; and obtaining a similarity threshold according to the minimum similarity value.
9. An electronic device, comprising:
a memory for storing an application program and data generated by the operation of the application program;
a processor for executing the application program to realize: acquiring power distribution network monitoring data of a power distribution network at a target time, wherein the power distribution network monitoring data comprises a plurality of state parameters; obtaining a target parameter set corresponding to the power distribution network monitoring data from a set containing a plurality of preset parameter sets, wherein the target parameter set contains a plurality of state parameters; the method comprises the steps that a preset parameter set in a set is generated based on power distribution network historical data corresponding to the power distribution network at a plurality of historical moments, wherein the power distribution network historical data corresponding to each historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; obtaining a parameter similarity value between the state parameters in the target parameter set and the state parameters in the power distribution network monitoring data; outputting an alarm result corresponding to the monitoring data of the power distribution network under the condition that the parameter similarity value meets a preset alarm condition;
The parameter similarity value meets a preset alarm condition and comprises the following steps: the parameter similarity value is smaller than or equal to a similarity threshold value; wherein the similarity threshold is obtained by:
obtaining second historical state data, wherein the second historical state data comprises a group of power distribution network historical data corresponding to a plurality of historical moments respectively, each power distribution network historical data corresponding to the historical moment comprises a plurality of state parameters, and the historical moment is a moment selected in a fault-free moment section of the power distribution network; carrying out fuzzification processing on the power distribution network historical data corresponding to each historical moment in the second historical state data to obtain fuzzy data corresponding to each historical moment, wherein the fuzzy data corresponding to each historical moment comprises a fuzzy set corresponding to each state parameter in the power distribution network historical data and a membership value corresponding to the fuzzy set; generating an initial fuzzy rule statement corresponding to each historical moment according to a fuzzy set and a membership value in fuzzy data corresponding to each historical moment; screening the initial fuzzy rule statement at least according to the minimum confidence coefficient value and the minimum support coefficient value of the fuzzy rule statement to obtain a target fuzzy rule statement of which the minimum confidence coefficient value is greater than or equal to a confidence coefficient threshold value and the minimum support coefficient value is greater than or equal to a support coefficient threshold value; performing anti-blurring processing on the target fuzzy rule sentences respectively to obtain preset parameter groups corresponding to each target fuzzy rule sentence; obtaining a minimum similarity value between the preset parameter set and the power distribution network historical data in the second historical state data; and obtaining a similarity threshold according to the minimum similarity value.
CN202010622269.9A 2020-06-30 2020-06-30 Power distribution network state parameter monitoring method and device and electronic equipment Active CN111784537B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010622269.9A CN111784537B (en) 2020-06-30 2020-06-30 Power distribution network state parameter monitoring method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010622269.9A CN111784537B (en) 2020-06-30 2020-06-30 Power distribution network state parameter monitoring method and device and electronic equipment

Publications (2)

Publication Number Publication Date
CN111784537A CN111784537A (en) 2020-10-16
CN111784537B true CN111784537B (en) 2023-08-01

Family

ID=72760579

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010622269.9A Active CN111784537B (en) 2020-06-30 2020-06-30 Power distribution network state parameter monitoring method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN111784537B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112925806B (en) * 2021-04-14 2023-07-25 中国人民解放军海军航空大学岸防兵学院 Method, system, medium and equipment for extracting performance degradation characteristic parameters based on association rule
CN113436030A (en) * 2021-06-25 2021-09-24 南京智盟电力有限公司 Multi-dimensional monitoring method and system for power distribution network
CN114826881A (en) * 2022-04-15 2022-07-29 北京科杰科技有限公司 Intelligent operation and maintenance method based on correlation analysis and computer readable storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010257227A (en) * 2009-04-24 2010-11-11 Toshiba Corp Monitoring device and server
CN109861291A (en) * 2019-03-15 2019-06-07 国网北京市电力公司 The optimal control method and device of power distribution network

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH04127239A (en) * 1990-06-06 1992-04-28 Hitachi Ltd Automatic control method for fuzzy inference parameter and display method for learning state
JP3106031B2 (en) * 1993-04-23 2000-11-06 松下電工株式会社 Fire alarm system
EP2287785A1 (en) * 2009-08-19 2011-02-23 University Of Leicester Fuzzy inference apparatus and methods, systems and apparatuses using such inference apparatus
CN101819411B (en) * 2010-03-17 2011-06-15 燕山大学 GPU-based equipment fault early-warning and diagnosis method for improving weighted association rules
US20110298621A1 (en) * 2010-06-02 2011-12-08 Lokesh Shanbhag System and method for generating alerts
CN103927431A (en) * 2014-02-20 2014-07-16 东南大学 Power station boiler operation state monitoring method based on pyramid time frame
CN104679828A (en) * 2015-01-19 2015-06-03 云南电力调度控制中心 Rules-based intelligent system for grid fault diagnosis
CN204883710U (en) * 2015-01-19 2015-12-16 云南电力调度控制中心 Power system fault diagnoses intelligent system based on rule
CN105045256B (en) * 2015-07-08 2018-11-20 北京泰乐德信息技术有限公司 Rail traffic real-time fault diagnosis method and system based on date comprision
CN107403239B (en) * 2017-07-25 2021-02-12 南京工程学院 Parameter analysis method for control equipment in power system
US10700523B2 (en) * 2017-08-28 2020-06-30 General Electric Company System and method for distribution load forecasting in a power grid
CN109684181B (en) * 2018-11-20 2020-08-07 华为技术有限公司 Alarm root cause analysis method, device, equipment and storage medium
CN109739905A (en) * 2019-01-10 2019-05-10 吉林建筑大学 A kind of pipe gallery fire alarm method and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010257227A (en) * 2009-04-24 2010-11-11 Toshiba Corp Monitoring device and server
CN109861291A (en) * 2019-03-15 2019-06-07 国网北京市电力公司 The optimal control method and device of power distribution network

Also Published As

Publication number Publication date
CN111784537A (en) 2020-10-16

Similar Documents

Publication Publication Date Title
CN111784537B (en) Power distribution network state parameter monitoring method and device and electronic equipment
Don et al. Dynamic process fault detection and diagnosis based on a combined approach of hidden Markov and Bayesian network model
US8868985B2 (en) Supervised fault learning using rule-generated samples for machine condition monitoring
EP2171598B1 (en) Fuzzy classification approach to fault pattern matching
Zaher et al. A multi-agent fault detection system for wind turbine defect recognition and diagnosis
CN105677791B (en) For analyzing the method and system of the operation data of wind power generating set
CN109543210A (en) A kind of Wind turbines failure prediction system based on machine learning algorithm platform
CN106021771A (en) Method and device for diagnosing faults
CN108268905A (en) A kind of Diagnosis Method of Transformer Faults and system based on support vector machines
CN111899905B (en) Fault diagnosis method and system based on nuclear power device
CN111680875B (en) Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model
CN112906764B (en) Communication safety equipment intelligent diagnosis method and system based on improved BP neural network
CN114186900B (en) Fire risk assessment method and device based on cloud model and fuzzy Bayesian network
CN114185760A (en) System risk assessment method and device and charging equipment operation and maintenance detection method
CN115822887A (en) Performance evaluation and energy efficiency diagnosis method and system of wind turbine generator
CN114065605A (en) Intelligent electric energy meter running state detection and evaluation system and method
CN111273125A (en) RST-CNN-based power cable channel fault diagnosis method
CN112415331A (en) Power grid secondary system fault diagnosis method based on multi-source fault information
Tiwary et al. Multi-dimensional ANN application for active power flow state classification on a utility system
Zio et al. A fuzzy decision tree method for fault classification in the steam generator of a pressurized water reactor
WO2023065580A1 (en) Fault diagnosis method and apparatus for gearbox of wind turbine generator set
CN115828173A (en) Fan fault diagnosis method and system based on fault knowledge and causal reasoning
CN116089871A (en) Motor state monitoring method based on semantic reasoning and deep extreme learning machine
CN110441725A (en) Intelligent electric meter method for diagnosing faults and device based on Adaptive Neural-fuzzy Inference
Smirnov Fuzzy model of fault finding in systems of responsible appointment

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