CN110221173B - Power distribution network intelligent diagnosis method based on big data drive - Google Patents
Power distribution network intelligent diagnosis method based on big data drive Download PDFInfo
- Publication number
- CN110221173B CN110221173B CN201910535174.0A CN201910535174A CN110221173B CN 110221173 B CN110221173 B CN 110221173B CN 201910535174 A CN201910535174 A CN 201910535174A CN 110221173 B CN110221173 B CN 110221173B
- Authority
- CN
- China
- Prior art keywords
- probability
- section
- distribution network
- power distribution
- cluster
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power distribution network intelligent diagnosis method based on big data drive, which is characterized in that the maximum composite probability of faults of each section is finally obtained through incomplete historical monitoring data of each section of a power distribution network by a K-means hierarchical evaluation algorithm according to the sequence of a basic layer step, an intermediate layer step and an output layer step, so that the fragile section of the power distribution network can be effectively found, and the real-time running state of the power distribution network can be scientifically evaluated.
Description
Technical Field
The invention relates to a power distribution network intelligent diagnosis method based on big data driving, which is used in the field of intelligent power grids.
Background
The distribution network is directly connected with the user, meanwhile, due to the characteristics of wide geographical distribution coverage area, complex and changeable geographical environment, high fault rate and the like, the power distribution network can quickly and accurately sense and diagnose the fault state of the distribution network, and the power distribution network is an indispensable technical measure for improving the power supply safety and reliability of the user.
The accumulation of a large amount of real-time data and fault record historical data from the power distribution network provides a good data base for intelligent evaluation of the power distribution network. However, the amount of such data is too large, and there are errors and inconsistencies, and the number of data monitoring points of the power distribution network is limited, so that massive data cannot be effectively applied. Analyzing the internal structure of the data, the content of data transmission and the incidence relation among the data, combing the data, performing system analysis and diagnosis on various attributes of the data, ensuring the quality of the provided data, improving the effectiveness of the data in application, and ensuring the practicability, effectiveness and rationality of the data in the application process are the main targets of technicians.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a power distribution network intelligent diagnosis method based on big data drive, which can realize intelligent diagnosis of a power distribution network.
One technical method for achieving the above purpose is as follows: a power distribution network intelligent diagnosis method based on big data drive, based on the sensing and diagnosis of the abnormal and fault of the key composition unit of the power distribution network of incomplete information, adopts K-means hierarchical evaluation strategy to carry out unsupervised classification on the incomplete historical monitoring information of the local section of the power distribution network, and evaluates the fault probability of each evaluation section in each cluster according to the historical fault record information, and comprises the following steps:
step 1, a basic layer step, wherein the basic layer adopts a K-means clustering algorithm to perform unsupervised classification on incomplete historical monitoring information of local sections, calculates the fault probability of each evaluation section in each cluster according to historical fault recording information, and divides m pieces of historical data information into K different classes by using the K-means algorithm, wherein the fault probability in the first class can be obtained
The probability of failure of the jth evaluation section in the class;
step 2, the intermediate layer provides a section composite fault probability solving algorithm, the probability that the real-time monitoring data belong to each cluster is calculated according to the distance from the real-time sampling data matrix of the monitoring section to each cluster, and the composite probability of the fault of each section is obtained by combining the probability of the fault of each section in each cluster;
and 3, outputting a layer, wherein the output layer provides a maximum composite probability evaluation algorithm, and the maximum composite probability of faults of each section is used as an overall operation state evaluation coefficient to evaluate the operation state grade of the power distribution network.
Further, the intermediate layer step, the section composite fault probability solving algorithm is based on the real-time data of the monitoring section, and the real-time data and the first fault probability are calculated
Distance of cluster centers. Then, the probability coefficients of the current real-time monitoring data belonging to different clusters can be obtained, and the calculation process is as follows:
defining an inverse distance coefficient:
in the formula (I), the compound is shown in the specification,
is a cluster number, and is a cluster number,
for monitoring data in real time to
The distance between the centers of the clusters is,
is an inverse distance coefficient;
calculating the real-time monitoring data
Probability coefficient of cluster:
in the formula, k represents the maximum cluster number,
indicating that the real-time monitoring data belongs to
Probability coefficients of clusters;
according to the first
The probability of the fault of the jth section in the cluster and the monitoring data belong to the
The probability coefficient of the cluster can calculate the composite fault probability of the real-time monitoring data in each evaluation section:
further, a point with the maximum composite fault probability is taken to represent the overall operation state of the power distribution network:
according to the intelligent diagnosis method for the power distribution network based on big data drive, the maximum composite probability of faults of each section is finally obtained through incomplete historical monitoring data of each section of the power distribution network according to the sequence of the steps of the basic layer, the intermediate layer and the output layer through a K-means hierarchical evaluation algorithm, so that the fragile section of the power distribution network can be effectively found, and the real-time running state of the power distribution network can be scientifically evaluated.
Detailed Description
In order to better understand the technical process of the invention, the following is described in detail by means of specific examples:
the invention discloses a power distribution network intelligent diagnosis method based on big data drive, which is based on the sensing and diagnosis of the abnormity and the fault of a key component unit of a power distribution network of incomplete information, adopts a K-means hierarchical evaluation strategy to carry out unsupervised classification on incomplete historical monitoring information of local sections of the power distribution network, and evaluates the fault probability of each evaluation section in each cluster according to historical fault record information, and comprises the following steps:
step 1, base layer step, base layerUnsupervised classification is carried out on incomplete historical monitoring information of local sections by adopting a K-means clustering algorithm, the fault probability of each evaluation section in each cluster is calculated according to historical fault record information, m pieces of historical data information are divided into K different classes by utilizing the K-means algorithm, and the fault probability in the first class can be obtained
The probability of failure of the jth evaluation section in the class;
step 2, the intermediate layer provides a section composite fault probability solving algorithm, the probability that the real-time monitoring data belong to each cluster is calculated according to the distance from the real-time sampling data matrix of the monitoring section to each cluster, and the composite probability of the fault of each section is obtained by combining the probability of the fault of each section in each cluster;
the section composite fault probability solving algorithm is based on real-time data of the monitored sections, and calculates the real-time data and the first data
Distance of cluster centers. Then, the probability coefficients of the current real-time monitoring data belonging to different clusters can be obtained, and the calculation process is as follows:
defining an inverse distance coefficient:
in the formula (I), the compound is shown in the specification,
is a cluster number, and is a cluster number,
for monitoring data in real time to
The distance between the centers of the clusters is,
is an inverse distance coefficient;
calculating the real-time monitoring data
Probability coefficient of cluster:
in the formula, k represents the maximum cluster number,
indicating that the real-time monitoring data belongs to
Probability coefficients of clusters;
according to the first
The probability of the fault of the jth section in the cluster and the monitoring data belong to the
The probability coefficient of the cluster can calculate the composite fault probability of the real-time monitoring data in each evaluation section:
and 3, outputting a layer, wherein the output layer provides a maximum composite probability evaluation algorithm, the maximum composite probability of faults in each section is used as an evaluation coefficient of the overall operation state, the operation state grade of the power distribution network is evaluated, and the point with the maximum composite fault probability is taken to represent the overall operation state of the power distribution network:
the method is based on the voltage information of the limited monitoring points, and utilizes a K-means hierarchical evaluation algorithm to evaluate the state of all evaluation sections of the power distribution network under study. And sensing the time of the power distribution network fault by utilizing the ring theorem and the average spectrum radius characteristic based on the voltage and current redundant information of the limited monitoring point or the full monitoring point. According to an automatic system from a local dispatching, characteristic analysis, data cleaning and extraction are carried out on data, then classification and combination are carried out on multi-source heterogeneous data by comprehensively considering data pre-set rules based on different dimensions such as data sources, purposes, data attributes and the like, and a high-reliability state perception and diagnosis method for the new energy-containing power distribution network is established. The output of the method is the sensing and diagnosis result of the fault state of the power distribution network.
It should be understood by those skilled in the art that the above embodiments are only for illustrating the present invention and are not to be used as a limitation of the present invention, and that changes and modifications to the above described embodiments are within the scope of the claims of the present invention as long as they are within the spirit and scope of the present invention.
Claims (3)
1. A power distribution network intelligent diagnosis method based on big data drive is characterized by comprising the following steps of based on sensing and diagnosis of abnormity and faults of key component units of a power distribution network of incomplete information, adopting a K-means hierarchical evaluation strategy to carry out unsupervised classification on incomplete historical monitoring information of local sections of the power distribution network, and evaluating fault probability of each evaluation section in each cluster according to historical fault record information:
step 1, a basic layer step, wherein the basic layer adopts a K-means clustering algorithm to perform unsupervised classification on incomplete historical monitoring information of local sections, calculates the fault probability of each evaluation section in each cluster according to historical fault recording information, and divides m pieces of historical data information into K different classes by using the K-means algorithm, wherein the fault probability in the first class can be obtained
Probability of failure of jth evaluation section in class
Step 2, the intermediate layer provides a section composite fault probability solving algorithm, the probability that the real-time monitoring data belong to each cluster is calculated according to the distance from the real-time sampling data matrix of the monitoring section to each cluster, and the composite probability of the fault of each section is obtained by combining the probability of the fault of each section in each cluster;
and 3, outputting a layer, wherein the output layer provides a maximum composite probability evaluation algorithm, and the maximum composite probability of faults of each section is used as an overall operation state evaluation coefficient to evaluate the operation state grade of the power distribution network.
2. The intelligent diagnosis method for the power distribution network based on big data driving as claimed in claim 1, wherein the intermediate layer step, section composite fault probability solving algorithm, is based on real-time data of the monitored section, and calculates the real-time data and the first real-time data
Distance of cluster centers; then, the probability coefficients of the current real-time monitoring data belonging to different clusters can be obtained, and the calculation process is as follows:
defining an inverse distance coefficient:
in the formula (I), the compound is shown in the specification,
is a cluster number, and is a cluster number,
for monitoring data in real time to
The distance between the centers of the clusters is,
is an inverse distance coefficient;
calculating the real-time monitoring data
Probability coefficient of cluster:
in the formula, k represents the maximum cluster number,
indicating that the real-time monitoring data belongs to
Probability coefficients of clusters;
according to the first
The probability of the fault of the jth section in the cluster and the monitoring data belong to the
The probability coefficient of the cluster can calculate the composite fault probability of the real-time monitoring data in each evaluation section:
3. the intelligent diagnosis method for the power distribution network based on big data driving according to claim 1, characterized by representing the overall operation state of the power distribution network by taking the point with the maximum composite fault probability:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910535174.0A CN110221173B (en) | 2019-06-20 | 2019-06-20 | Power distribution network intelligent diagnosis method based on big data drive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910535174.0A CN110221173B (en) | 2019-06-20 | 2019-06-20 | Power distribution network intelligent diagnosis method based on big data drive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110221173A CN110221173A (en) | 2019-09-10 |
| CN110221173B true CN110221173B (en) | 2021-06-04 |
Family
ID=67814293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910535174.0A Active CN110221173B (en) | 2019-06-20 | 2019-06-20 | Power distribution network intelligent diagnosis method based on big data drive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110221173B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112180215A (en) * | 2020-09-29 | 2021-01-05 | 国网上海市电力公司 | Intelligent power distribution network fault searching and positioning method based on multi-source data fusion |
| CN112180216A (en) * | 2020-09-29 | 2021-01-05 | 国网上海市电力公司 | Power distribution network intelligent sensing and diagnosis method based on big data drive |
| CN113673904A (en) * | 2021-08-31 | 2021-11-19 | 江苏省电力试验研究院有限公司 | Data-driven power distribution network user-changing relation diagnosis method and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105891629A (en) * | 2016-03-31 | 2016-08-24 | 广西电网有限责任公司电力科学研究院 | Transformer equipment fault identification method |
| CN107122879A (en) * | 2017-03-03 | 2017-09-01 | 广东南方电力通信有限公司 | A kind of State-Oriented Maintenance in Power Grid method based on big data and equipment state tracking extremely |
| CN108258802A (en) * | 2016-12-29 | 2018-07-06 | 国网江苏省电力公司镇江供电公司 | The monitoring method and device of the operation conditions of controller switching equipment in a kind of power distribution network |
| CN108805427A (en) * | 2018-05-29 | 2018-11-13 | 深圳众厉电力科技有限公司 | A kind of distribution Running State Warning System based on big data |
| CN109459669A (en) * | 2019-01-09 | 2019-03-12 | 国网上海市电力公司 | 10kV one-phase earthing failure in electric distribution network Section Location |
| CN109491339A (en) * | 2018-11-16 | 2019-03-19 | 国网江苏省电力有限公司盐城供电分公司 | A kind of operating condition of transformer station equipment early warning system based on big data |
| CN109711664A (en) * | 2018-11-16 | 2019-05-03 | 国网江苏省电力有限公司盐城供电分公司 | A kind of power transmission and transforming equipment health evaluation system based on big data |
| CN109754116A (en) * | 2018-12-20 | 2019-05-14 | 国网北京市电力公司 | The analysis method and device of transmission line of electricity |
-
2019
- 2019-06-20 CN CN201910535174.0A patent/CN110221173B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105891629A (en) * | 2016-03-31 | 2016-08-24 | 广西电网有限责任公司电力科学研究院 | Transformer equipment fault identification method |
| CN108258802A (en) * | 2016-12-29 | 2018-07-06 | 国网江苏省电力公司镇江供电公司 | The monitoring method and device of the operation conditions of controller switching equipment in a kind of power distribution network |
| CN107122879A (en) * | 2017-03-03 | 2017-09-01 | 广东南方电力通信有限公司 | A kind of State-Oriented Maintenance in Power Grid method based on big data and equipment state tracking extremely |
| CN108805427A (en) * | 2018-05-29 | 2018-11-13 | 深圳众厉电力科技有限公司 | A kind of distribution Running State Warning System based on big data |
| CN109491339A (en) * | 2018-11-16 | 2019-03-19 | 国网江苏省电力有限公司盐城供电分公司 | A kind of operating condition of transformer station equipment early warning system based on big data |
| CN109711664A (en) * | 2018-11-16 | 2019-05-03 | 国网江苏省电力有限公司盐城供电分公司 | A kind of power transmission and transforming equipment health evaluation system based on big data |
| CN109754116A (en) * | 2018-12-20 | 2019-05-14 | 国网北京市电力公司 | The analysis method and device of transmission line of electricity |
| CN109459669A (en) * | 2019-01-09 | 2019-03-12 | 国网上海市电力公司 | 10kV one-phase earthing failure in electric distribution network Section Location |
Non-Patent Citations (2)
| Title |
|---|
| 一种面向风险评估的输电线路故障概率模型;何迪 等;《电力***保护与控制》;20170401;第45卷(第7期);第69-76页 * |
| 基于改进K-Means聚类和BP神经网络的台区线损率计算方法;李亚 等;《中国电机工程学报》;20160905;第36卷(第17期);第4543-4551页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110221173A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221173B (en) | Power distribution network intelligent diagnosis method based on big data drive | |
| CN108320043B (en) | Power distribution network equipment state diagnosis and prediction method based on electric power big data | |
| CN110322048B (en) | Fault early warning method for production logistics conveying equipment | |
| CN108375476B (en) | Hydroelectric generating set health assessment method | |
| CN110222991B (en) | Metering device fault diagnosis method based on RF-GBDT | |
| CN113156917A (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| CN110414154B (en) | Fan component temperature abnormity detection and alarm method with double measuring points | |
| CN106199276A (en) | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system | |
| CN108398934B (en) | equipment fault monitoring system for rail transit | |
| CN109858140B (en) | Fault diagnosis method for water chilling unit based on information entropy discrete Bayesian network | |
| CN110927654B (en) | Batch running state evaluation method for intelligent electric energy meters | |
| CN107844067B (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
| CN110321912A (en) | More metering anomalous event correlation analysis methods | |
| CN111126489A (en) | Power transmission equipment state evaluation method based on ensemble learning | |
| CN111666978B (en) | Intelligent fault early warning system for IT system operation and maintenance big data | |
| Wang et al. | Prognostics and health management system for electric vehicles with a hierarchy fusion framework: concepts, architectures, and methods | |
| CN108108839B (en) | Power grid information system equipment state early warning method based on reverse fuzzy hierarchical analysis | |
| CN109711664A (en) | A kind of power transmission and transforming equipment health evaluation system based on big data | |
| CN113689072A (en) | Offshore wind turbine generator running state evaluation method based on Markov chain | |
| CN116861503A (en) | Method for constructing digital twin model of power transformer based on big data | |
| CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal system | |
| CN113128482B (en) | Multi-factor-influenced power transmission line abnormal discharge risk grade evaluation method | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN110441725A (en) | Intelligent electric meter method for diagnosing faults and device based on Adaptive Neural-fuzzy Inference | |
| CN112507290B (en) | Power distribution equipment fault probability pre-judging method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |