CN109586239B - Real-time diagnosis and fault early warning method for intelligent substation - Google Patents
Real-time diagnosis and fault early warning method for intelligent substation Download PDFInfo
- Publication number
- CN109586239B CN109586239B CN201811505559.4A CN201811505559A CN109586239B CN 109586239 B CN109586239 B CN 109586239B CN 201811505559 A CN201811505559 A CN 201811505559A CN 109586239 B CN109586239 B CN 109586239B
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- early warning
- network
- substation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000003745 diagnosis Methods 0.000 title claims abstract description 17
- 238000010801 machine learning Methods 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 3
- 238000012098 association analyses Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000003012 network analysis Methods 0.000 description 5
- 238000010219 correlation analysis Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H1/00—Details of emergency protective circuit arrangements
- H02H1/0092—Details of emergency protective circuit arrangements concerning the data processing means, e.g. expert systems, neural networks
-
- H02J13/0006—
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a real-time diagnosis and fault early warning method for an intelligent substation, which is characterized by comprising the following steps of: s1: inputting electrical equipment operation data, network flow data and server log data when a transformer substation fault occurs into a database to form fault data, and establishing a large number of data set sample training spaces; s2: capturing a network packet through a network packet analysis tool, uploading data in the network packet to a database for analysis and display, wherein the data in the network packet is network data; s3: performing machine learning on the data in a database, and performing classification comparison on fault data and network data through the machine learning to obtain a fault model; s4: and forming a fault parameter fluctuation threshold value of the operation of the substation equipment based on the fault model, accessing real-time data of the substation, and displaying fault early warning when the fluctuation threshold value of the real-time data exceeds an early warning value of the fault model.
Description
Technical Field
The invention relates to a fault early warning method, in particular to a real-time diagnosis and fault early warning method for an intelligent substation.
Background
The IEC61850 protocol realizes the digitization and the informatization of the transformer substation, realizes the information interaction among the total stations through GOOSE, SV and MMS messages, and completes the functions of controlling, protecting, monitoring and the like of the equipment. In order to help operation and maintenance personnel and technical personnel to locate fault points and find fault reasons in time after a transformer substation event occurs, an intelligent transformer substation is provided with a network analysis system, the existing network analysis system realizes the functions of collecting and storing whole network data, monitoring the state of a communication link and alarming abnormal information, but the existing network analysis system lacks a means for effectively classifying and screening various alarming information, and the operation and maintenance personnel often have no way to handle and find out when facing a large amount of alarming information. In addition, information such as link abnormality, equipment alarm and the like exist independently, and correlation analysis capability is not provided between the information, so that the conventional network analysis system can only show abnormality and does not have intelligent analysis capability, and situation perception and active early warning cannot be realized.
Disclosure of Invention
The invention aims to solve the technical problems that the diagnosis result is fuzzified, only a large amount of abnormal alarm information can be prompted, the alarm information cannot be classified and defect eliminating measures cannot be given out, the running state of the whole transformer substation equipment and network cannot be dynamically displayed, technicians can only disassemble and analyze data packets layer by layer and trace back to the source one by one, the technical threshold is high, the working efficiency is extremely low, and the method aims to provide the real-time diagnosis and fault early warning method for the intelligent transformer substation and solve the problems.
The invention is realized by the following technical scheme:
the intelligent substation real-time diagnosis and fault early warning method is characterized by comprising the following steps: s1: inputting electrical equipment operation data, network flow data and server log data when a transformer substation fault occurs into a database to form fault data, and establishing a large number of data set sample training spaces; s2: capturing a network packet through a network packet analysis tool, uploading data in the network packet to a database for analysis and display, wherein the data in the network packet is network data; s3: performing machine learning on the data in a database, and performing classification comparison on fault data and network data through the machine learning to obtain a fault model; s4: and forming a fault parameter fluctuation threshold value of the operation of the substation equipment based on the fault model, accessing real-time data of the substation, and displaying fault early warning when the fluctuation threshold value of the real-time data exceeds an early warning value of the fault model.
The existing network analysis system technology comprises the following implementation steps: 1) a mirror switch port; 2) collecting data messages of the whole network and storing the data messages in a local hard disk; 3) analyzing the collected data message according to an IEC61850 protocol; 4) and (4) alarming abnormal conditions (communication interruption, no signal received by the measurement and control equipment and the like). Therefore, a plurality of problems can be caused, such as fuzzification of a diagnosis result, only a large amount of abnormal alarm information can be prompted, and the alarm information cannot be classified and defect elimination measures cannot be provided; the running state of the whole substation equipment and the network cannot be dynamically displayed, technicians can only disassemble and analyze the data packets layer by layer and trace the source one by one, so that the technical threshold is high, and the working efficiency is extremely low.
In order to solve the technical problem, the system is composed of a front-end data acquisition system, a network transmission subsystem and a rear-end analysis platform in a mode of acquiring and analyzing network data of the intelligent substation in real time. The network data acquisition, processing, analysis, criterion judgment, prediction and the like of the transformer substation are realized, and the operation state of the whole network is visually displayed.
Further, the machine learning in the step S3 includes supervised machine learning and unsupervised machine learning, where the supervised machine learning is to classify common faults and abnormal phenomena of the substation, and establish a time series algorithm to analyze and predict the current substation operation condition; the unsupervised machine learning adopts an association analysis mode, fault data and network data are classified and compared by finding frequent item sets and mining association rules, and then analysis and prediction are carried out.
Furthermore, the unsupervised machine learning adopts an Apriori algorithm to perform correlation operation, and correlation classification is performed on classified data through iteration of layer-by-layer search.
Further, the electrical device operation data in step S1 includes current, voltage, and active value data, and when the fault warning display is performed, each data in the electrical device is displayed.
Compared with the prior art, the invention has the following advantages and beneficial effects: the intelligent diagnosis and prediction method is mainly used for realizing an intelligent diagnosis and prediction technology aiming at the current situation that the operation and maintenance mode of the intelligent transformer substation is low in efficiency, combines the advantages of technologies such as supervised machine learning and unsupervised machine learning, fundamentally changes the operation and maintenance modes of the existing transformer substation, improves the operation and maintenance work efficiency of the transformer substation, diagnoses the health condition of the transformer substation on line in real time, senses possible problems in advance and gives prevention guidance suggestions, and the terminal of a fault is cut off timely without rain and silk, so that the intelligent diagnosis and prediction method has high social and economic benefits.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a process flow diagram of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
The intelligent substation real-time diagnosis and fault early warning method is characterized by comprising the following steps: s1: inputting electrical equipment operation data, network flow data and server log data when a transformer substation fault occurs into a database to form fault data, and establishing a large number of data set sample training spaces; s2: capturing a network packet through a network packet analysis tool, uploading data in the network packet to a database for analysis and display, wherein the data in the network packet is network data; s3: performing machine learning on the data in a database, and performing classification comparison on fault data and network data through the machine learning to obtain a fault model; s4: and forming a fault parameter fluctuation threshold value of the operation of the substation equipment based on the fault model, accessing real-time data of the substation, and displaying fault early warning when the fluctuation threshold value of the real-time data exceeds an early warning value of the fault model. The system is composed of a front-end data acquisition system, a network transmission subsystem and a rear-end analysis platform in a mode of acquiring and analyzing network data of the intelligent substation in real time. The network data acquisition, processing, analysis, criterion judgment, prediction and the like of the transformer substation are realized, and the operation state of the whole network is visually displayed. .
(1) Establishing a large number of data set sample training spaces
The method comprises the steps of collecting typical fault cases of the transformer substation, recording operation data (current, voltage, active values and the like) of electrical equipment when the faults occur, network flow data, server log data and the like, and meanwhile, obtaining related data by simulating different faults in a laboratory.
(2) Data packet collection
The main roles of Sniffer, Net Flow and Wireshark are common network packet analysis tools are to try to capture network packets and to show as detailed a packet as possible. The main characteristics are as follows: the method supports UNIX and Windows platforms, captures packets in real time at interfaces, can display detailed protocol information of the packets in detail, can open/store the captured packets, can import and export packet data formats supported by other capture programs, can filter the packets in various modes, search the packets in various modes, display the packets in various colors by filtering, create various statistical analyses, capture various network interfaces, support files captured by various other programs, support multi-format output, provide support for decoding various protocols, and open source software.
(3) Supervised machine learning
The machine learning comprises supervised learning and unsupervised learning, common faults and abnormal phenomena of the transformer substation are classified artificially in a supervised learning mode, and a time series algorithm (regression algorithm) is established to analyze and predict the current operation condition of the transformer substation.
(4) Unsupervised machine learning
One of the most important loops of unsupervised region learning is correlation analysis, which can be used to find correlations or correlations between data information in large-scale data sets. The goals of correlation analysis mainly include two: discovering a frequent set of items and mining association rules. The Apriori algorithm is an efficient algorithm for finding a frequent set of terms, using an iterative method called layer-by-layer search, i.e. a set of k terms is used to explore a set of (k +1) terms: first, find the set of the frequent 1 item set, denoted L1, L1 for find the set of the frequent 2 item set, L2, and L2 for find L3, and so on until the k item set cannot be found. One database scan is required for each Lk found. To improve the efficiency of layer-by-layer generation of frequent item sets, an important property called Apriori is used to compress the search space, whose rationale is: 1. if a certain set of items is frequent, then all of its subsets will tend to be frequent as well; 2. if an item set is a non-frequent item set, then the superset to which it corresponds is all a non-frequent item set. Although Apriori's algorithm can avoid exponential growth in the number of sets of terms, and thus compute a frequent set of terms in a reasonable time, its efficiency is still less than ideal. In order to find out the frequent item set more quickly, researchers propose an FP-growth algorithm to make up for the deficiency of the Apriori algorithm. Compared with the Apriori algorithm, the FP-growth algorithm only needs to traverse the database twice, thereby efficiently finding frequent item sets. The FP-growth algorithm is based on the Apriori principle, finds a frequent item set by storing a data set on an FP (FrequntPattern) tree, but cannot find association rules among data. The FP-growth algorithm only needs to scan the database twice, while the Apriori algorithm needs to scan the database once when each potential frequent item set is solved, so the FP-growth algorithm is efficient.
(5) Fault location/prognosis
Based on the steps of data training, unsupervised learning, correlation analysis, SCD comparison of the substation configuration files and the like, a set of fault criterion and prediction system is formed, current substation operation data (current, voltage and active values) and network data (flow, data packet size, time delay and the like) are input, and output indicates whether electrical equipment of the substation is normal or not, and states of faults, hidden dangers and the like exist.
(6) Visual display
A set of visual display system with friendly interface and comprehensive function coverage is formed at the background, so that operation and maintenance personnel can master the real-time and all-around operation conditions of the electrical equipment and the network of the whole transformer substation in a master control room, and the overall flow chart of the real-time diagnosis and fault early warning system of the intelligent transformer substation is shown in figure 1.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (4)
1. The intelligent substation real-time diagnosis and fault early warning method is characterized by comprising the following steps:
s1: inputting electrical equipment operation data, network flow data and server log data when a transformer substation fault occurs into a database to form fault data, and establishing a large number of data set sample training spaces;
s2: capturing a network packet through a network packet analysis tool, uploading data in the network packet to a database for analysis and display, wherein the data in the network packet is network data;
s3: performing machine learning on the data in a database, and performing classification comparison on fault data and network data through the machine learning to obtain a fault model;
s4: and forming a fault parameter fluctuation threshold value of the operation of the substation equipment based on the fault model, accessing real-time data of the substation, and displaying fault early warning when the fluctuation threshold value of the real-time data exceeds an early warning value of the fault model.
2. The intelligent substation real-time diagnosis and fault early warning method according to claim 1, wherein the machine learning in the step S3 includes supervised machine learning and unsupervised machine learning, the supervised machine learning is to classify common faults and abnormal phenomena of the substation, and a time series algorithm is established to analyze and predict the current substation operation condition; the unsupervised machine learning adopts an association analysis mode, fault data and network data are classified and compared by finding frequent item sets and mining association rules, and then analysis and prediction are carried out.
3. The intelligent substation real-time diagnosis and fault early warning method according to claim 2, wherein the unsupervised machine learning adopts Apriori algorithm for correlation operation, and classification data is subjected to correlation classification through iteration of layer-by-layer search.
4. The intelligent substation real-time diagnosis and fault early warning method according to claim 1, wherein the electrical equipment operation data in step S1 includes current, voltage, and active value data, and each data in the electrical equipment is displayed when fault early warning display is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811505559.4A CN109586239B (en) | 2018-12-10 | 2018-12-10 | Real-time diagnosis and fault early warning method for intelligent substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811505559.4A CN109586239B (en) | 2018-12-10 | 2018-12-10 | Real-time diagnosis and fault early warning method for intelligent substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109586239A CN109586239A (en) | 2019-04-05 |
| CN109586239B true CN109586239B (en) | 2020-03-31 |
Family
ID=65928749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811505559.4A Active CN109586239B (en) | 2018-12-10 | 2018-12-10 | Real-time diagnosis and fault early warning method for intelligent substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109586239B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866616A (en) * | 2019-11-01 | 2020-03-06 | 许继集团有限公司 | Fault early warning method and device for secondary equipment of transformer substation |
| CN110703743A (en) * | 2019-11-12 | 2020-01-17 | 深圳市亲邻科技有限公司 | Equipment failure prediction and detection system and method |
| CN110941918B (en) * | 2019-12-30 | 2024-03-19 | 国网安徽省电力有限公司 | Intelligent substation fault analysis system |
| CN111371180B (en) * | 2020-03-23 | 2023-03-17 | 国网黑龙江省电力有限公司鹤岗供电公司 | Substation patrol supervision and data analysis system |
| CN112398218A (en) * | 2020-09-28 | 2021-02-23 | 国网山东省电力公司冠县供电公司 | Power grid safety and stability analysis device and method |
| CN112329914B (en) * | 2020-10-26 | 2024-02-02 | 华翔翔能科技股份有限公司 | Fault diagnosis method and device for buried transformer substation and electronic equipment |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010011918A2 (en) * | 2008-07-24 | 2010-01-28 | University Of Cincinnati | Methods for prognosing mechanical systems |
| CN103136587B (en) * | 2013-03-07 | 2015-12-09 | 武汉大学 | Based on the power distribution network running status classifying identification method of support vector machine |
| CN104102773B (en) * | 2014-07-05 | 2017-06-06 | 山东鲁能软件技术有限公司 | A kind of equipment fault early-warning and state monitoring method |
| CN106779505B (en) * | 2017-02-28 | 2021-04-02 | 中国南方电网有限责任公司 | Power transmission line fault early warning method and system based on big data driving |
-
2018
- 2018-12-10 CN CN201811505559.4A patent/CN109586239B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109586239A (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109586239B (en) | Real-time diagnosis and fault early warning method for intelligent substation | |
| CN108763957B (en) | Database security audit system, method and server | |
| CN111885012B (en) | Network situation perception method and system based on information acquisition of various network devices | |
| CN105867351B (en) | Vehicle trouble code acquires the method and device with historical data analysis diagnosis in real time | |
| CN106371986A (en) | Log treatment operation and maintenance monitoring system | |
| CN109783322A (en) | A kind of monitoring analysis system and its method of enterprise information system operating status | |
| CN110855502A (en) | Fault cause determination method and system based on time-space analysis log | |
| CN114509283A (en) | System fault monitoring method and device, electronic equipment and storage medium | |
| CN103049365B (en) | Information and application resource running state monitoring and evaluation method | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN110808856A (en) | Big data operation and maintenance method and system based on data center | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN105634796A (en) | Network device failure prediction and diagnosis method | |
| CN117235169A (en) | Wisdom fortune dimension data storage platform | |
| CN115372816A (en) | Power distribution switchgear operation fault prediction system and method based on data analysis | |
| CN109660396A (en) | A kind of method for monitoring network and device | |
| CN115208059A (en) | Transformer substation power and environment monitoring alarm processing system and method | |
| CN117596119A (en) | Equipment data acquisition and monitoring method and system based on SNMP (simple network management protocol) | |
| CN115277113A (en) | Power grid network intrusion event detection and identification method based on ensemble learning | |
| CN117194171A (en) | Heterogeneous cloud resource panoramic anomaly detection system | |
| CN112449019A (en) | IMS intelligent Internet of things operation and maintenance management platform | |
| CN105530136A (en) | Electric power scheduling system and business monitoring method for the same | |
| CN114257414A (en) | Intelligent network security duty method and system | |
| CN103268353A (en) | Power grid alarming automatic response system and power grid alarming automatic response method | |
| CN115333915A (en) | Network management and control system for heterogeneous host |
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 |