CN107608971A - A kind of relay protection warning information semantic identification method - Google Patents
A kind of relay protection warning information semantic identification method Download PDFInfo
- Publication number
- CN107608971A CN107608971A CN201710970891.7A CN201710970891A CN107608971A CN 107608971 A CN107608971 A CN 107608971A CN 201710970891 A CN201710970891 A CN 201710970891A CN 107608971 A CN107608971 A CN 107608971A
- Authority
- CN
- China
- Prior art keywords
- warning information
- decision tree
- relay protection
- attribute
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Monitoring And Testing Of Exchanges (AREA)
Abstract
The invention discloses a kind of relay protection warning information semantic identification method.Pass through the analysis to relay protection history alarm information processing situation; characteristic during relay protection fault is set to the attribute information of warning information; and decision tree classification training is carried out as sample data, form the types such as alarm property, abort situation, failure cause.In relay protected operation, warning information is gathered in real time and is sent to protection fault message main station system, and combine the relay protected operation parameter information that alarm produces the moment, realized using decision tree inference method to the semantic identification of warning information.
Description
Technical field
The invention belongs to dispatching automation of electric power systems technical field, is related to substation relay protection direction.
Background technology
Relay protection is the first line of defence of electric power netting safe running, and its stable operation ensures the stable operation of power network, when
, it is necessary to which unit exception can in time be found and notify equipment operation maintenance personnel when relay protection is broken down.Therefore in relay
Just possess fairly perfect self-checking function in protection equipment design, the abnormal of equipment itself can be carried out certainly in the process of running
Diagnosis, discovering device failure provide alarm, and its self-checking function has accomplished that " as long as warning information is not sent out in protection, device is exactly substantially
Intact ".Therefore warning information can be as the important criterion of relay protection examination.But the description of specific warning information is because respectively setting
The logic theory and the difference of algorithm that standby manufacturing enterprise uses are each different, have used more technical term and the language of non-specification
Speech, causes these signal readability poor, only relay protection professional could effectively identify alarm description implication, Supervision
Control personnel can not such as identify the implication of warning information after finding alarm, then can cause equipment deficiency can not be by timely processing, to electricity
Net safe operation brings hidden danger.In ideal conditions, the classification for tackling the self-checking alarming information of relay protection makes specification
Property definition, power grid operation management personnel is identified its implication according to the description of self-checking alarming.But in power network, relay protection
Be used widely, such as press such scheme, then need to every operation relay protection upgrade, its workload with cause
Equipment stoppage in transit risk be that grid company is difficult to receive.Therefore by data research, existing relay protection device self-test is accused
Alert information MAP is specific nature of trouble, coverage and alarm cause, makes grid equipment monitoring personnel, operation maintenance personnel
The implication of self-checking alarming information description can be easily identified, there is important application value.
The content of the invention
A kind of relay protection warning information semantic identification method proposed by the present invention, the purpose is to alerted based on relay protection
Description and operation information, multi dimensional analysis is carried out to relay protection warning information by data digging method, finds relay protection
Fault signature corresponding to warning information, so as to effectively carry out semantics recognition to the warning information of relay protection device, support after
Electric protection maintenance work.
The present invention takes following scheme.
A kind of relay protection warning information semantic identification method, the semanteme of relay protection warning information is entered based on decision tree
Row identification, realizes the automatic identification to relay protection warning information；It is characterized in that the relay protection warning information semanteme is distinguished
Knowledge method comprises the steps：
Step (1) analyzes the processing procedure of relay protection history alarm information, using the build-in attribute of warning information, and ties
Close the electric current of required reference when failure is positioned manually, voltage, open into, the fault eigenvalue such as output, form the warning information
Attribute information, and semanteme and real processing results with reference to described by each history alarm information, form sample data, Ran Houjin
Enter step (2)；
Step (2) carries out decision tree training study using multinomial sample data, carries out branch and the beta pruning of decision tree, produces
Relay protection warning information decision tree；
Step (3) gathers the signal, while call relay protection to work as after operating relay protection produces alarm signal
Preceding operation analog quantity and switching value, and be inputted decision-making root vertex and make inferences；
Step (4) decision tree reasoning fails, and decision tree is carried out as sample data using after this warning information manual analysis
Training, generates new decision tree；
Step (5) decision tree reasoning success, decision tree the reasoning results are exported, including alarm property, abort situation, failure
Reason.
The present invention further comprises following preferred scheme：
In the step (2), relay protection warning information decision tree production method is：
1) possible decision tree space is traveled through using top-down greedy search, the best attribute of selection sort ability is made
For the root node of tree；
2) according to the difference of current node attribute value, training sample data collection is divided into some subsets, each subset is
One branch of the node, the nodal community are no longer participate in follow-up branch；
3) repeat 1), 2) process, untill not remaining attribute can be used for further division sample.
Whether the attribute information of warning information fails including function, whether correct, intake is correct for sampled value, outputs
Whether amount is correct；Wherein, the best attribute of classification capacity is whether function fails.In the step (3), relay protection alarm
The inference method of information decision tree includes：
1) since the root node of decision tree, the comparison of attribute and its value is carried out on the node of decision tree；Alarm letter
Number some attribute and its value and the node on attribute and its some property value when matching, just along point of the property value
Branch extends downwardly search, reaches next node；
2) if it is known that having attribute and the attributes match on root node in the fact, but their property value Incomplete matching,
Then according to closest to principle, the branch for selecting matching degree maximum is searched for downwards, reaches new node；
3) if it is known that true all properties all mismatch with the attribute on node, then reasoning fails；
If 4) present node is the leaf node of decision tree, the conclusion included in leaf node, decision tree are provided
Reasoning process terminates.
For prior art, the present invention has technique effect beneficial below：
The present invention solves the problems, such as that relay protection warning information is strongly professional for a long time and is difficult to, and avoids because of nothing
Method effectively identify relay protection warning information semanteme, caused by equipment fault can not promptly and accurately be identified caused by power network pacify
The problems such as full hidden danger, new technical support is provided for relay protection device Stateful Inspection.
Brief description of the drawings
Fig. 1 is the relay protection warning information semantic identification flow chart of the present invention；
Fig. 2 is decision tree generation figure；
Fig. 3 is decision tree inference graph.
Embodiment
Below with reference to accompanying drawing, the present invention is described in further detail.With reference to accompanying drawing 1, the present invention provides a kind of relay
Protection alarm information semantic discrimination method.Relay protection information state evaluating method disclosed in the present application comprises the following steps：
Step 1：The processing procedure of relay protection history alarm information is analyzed, using the attribute of warning information, and combines people
The electric current of required reference, voltage when work positions failure, open into, the fault eigenvalue such as output, form the attribute of the warning information
Information, and semanteme and real processing results with reference to described by each history alarm information, sample data is formed, subsequently into step
Rapid 2；
Whether the build-in attribute of warning information only fails comprising function, identifies whether relay protection function fails, and can make
One of attribute for warning information, the nature of trouble of alarm can be divided into plant failure and abnormal two classes of device accordingly.Simultaneously will
Current conditions, voltage condition when alarm occurs, open into situation, output the attribute that situation etc. also serves as warning information, electric current and
Whether voltage condition identifies sampled value normal, opens into and outputs situation and identify intake respectively whether the normal and amount of outputing is
It is no normal.In addition, the real processing results information of alarm will also be included by participating in the sample data of training generation decision tree.
Step 2：Decision tree training study is carried out using multinomial sample data, branch and the beta pruning of decision tree is carried out, produces
Relay protection warning information decision tree.
Decision tree training method is as described below：
2-1：Possible decision tree space, the best attribute of selection sort ability are traveled through using top-down greedy search
Root node as tree；
Using top-down greedy search algorithm, the sample data of the warning information of relay protection is traveled through, after
Whether the attribute of electric protection fails including function, and correctly whether sampled value, whether intake is correct, whether the amount of outputing is correct etc..
Choose the root node whether best attribute relay protection function of classification capacity fails as tree.
2-2：According to the difference of current node attribute value, training sample data collection is divided into some subsets, each subset
For a branch of the node, the nodal community is no longer participate in follow-up branch；
The attribute of root node is alarm property, sample space can be divided into plant failure and dress according to the difference of its property value
Abnormal two major classes are put, per a kind of child node as root node, in the child node, contain the subset in original sample space, can
A new sample space is seen as, and in the sample space all samples are got rid of with alarm property qualitative attribution.
2-3：2-1,2-2 process of repetition, untill not remaining attribute can be used for further division sample.
For each new child node, the sample space that top-down greedy search travels through child node is reused,
The best attribute of classification capacity is found, in the present invention, according to fault signature data during alarm, abort situation is by traveling through quilt
The categorical attribute chosen, therefore abort situation is chosen as the node for continuing classification, it can be divided into：CPU card is abnormal, it is different to output
Often, open into several classes such as abnormal, exchange exception, channel abnormal, communication abnormality, system exception, other exceptions.Equally, carry out again
The branch of decision tree and produce sample space new in each child node.The like, carried out until can not find new attribute
Untill sample space divides.Ultimately form the decision tree shown in accompanying drawing 2.
Step 3：After operating relay protection produces warning information, the signal is gathered, while call relay protection to work as
Preceding operation analog quantity and switching value, and be inputted decision-making root vertex and make inferences；
After receiving relay protection warning information, whether just relay protection function is obtained according to the description of the warning information first
Normal information, such as：Plant failure or device are abnormal.Then service data calling is carried out to relay protection, when obtaining its alarm
Service data, including：The analog quantitys such as electric current, voltage, open into, the switching value such as output.Judge whether these data are normal, also make
For the attribute of warning information.Above- mentioned information is imported into decision-making root vertex, carries out the reasoning of decision tree.The specific following institute of method
State：
3-1：Since the root node of decision tree, the comparison of attribute and its value is carried out on the node of decision tree；Alarm
When some attribute and its value of information match with the attribute on the node and its some property value, just along the property value
Branch extends downwardly search, reaches next node；
Warning information is made inferences using the decision tree above built, by warning information and its attribute first with root section
Attribute on point is compared, such as find warning information some attribute it is consistent with the attribute on root node, and its value and
Some fork attribute value of root node is consistent, then child node can be branched to along this, and continues to be belonged to the child node
Property compares.
3-2：If it is known that have attribute and the attributes match on root node in the fact, but incomplete of their property value
Match somebody with somebody, then according to closest to principle, the branch for selecting matching degree maximum is searched for downwards, reaches new node；
If some attribute of warning information is consistent with the attribute on root node, and some of its value and root node point
Branch property value is all not quite identical, then can be along the child node that branches to of matching degree maximum, and continues to enter with the child node
Row attribute compares.
3-3：If it is known that true all properties all mismatch with the attribute on node, then reasoning fails；
If it find that all properties of warning information can not all match unanimously with the attribute in current comparison node, then reasoning
Failure, reasoning process terminate.Into step 4；
3-4：If present node is the leaf node of decision tree, the conclusion included in leaf node, decision-making are provided
Tree reasoning process terminates.
Leaf node is such as reached, then provides the conclusion included in leaf node.Into step 5.As shown in Figure 3, accuse
Alert information " opening into communicating interrupt " produces, and its attribute belongs to device exception class, calls analog quantity and switching value, switching value, finds
A part is opened into exception, and a part is opened into normally, and the attribute information can exclude the abnormal possibility of power insert.It is conducted into decision-making
Root vertex, analyzed according to attribute, the nature of trouble for drawing this warning information is " device is abnormal ", and abort situation is " to open
Enter exception ", failure cause is the conclusion of " opening bad into plug-in unit ".
Step 4：Decision tree reasoning fails, and decision tree is instructed as sample data using after this warning information manual analysis
Practice, generate new decision tree；
By the warning information by decision tree reasoning that fails, by manual analysis, the related attribute of its failure is drawn,
And after the method for its processing, as sample data, the decision tree training described in step 2 is re-started, is generated new
Decision tree.
Step 5：Decision tree reasoning success, decision tree the reasoning results are exported, including alarm property, abort situation, failure
Reason.
The leaf node of decision tree is such as successfully arrived at by decision tree reasoning, then reasoning is completed, and the reasoning results are exported, and is wrapped
Alarm property, abort situation and failure cause are included.
Applicant is described in detail and described to embodiments of the invention with reference to Figure of description, but this area skill
Art personnel are it should be understood that above example is only the preferred embodiments of the invention, and explanation is intended merely to help reader in detail
More fully understand that the present invention is spiritual, and not limiting the scope of the invention, on the contrary, any invention essence based on the present invention
Any improvement or modification that god is made should all be fallen within the scope and spirit of the invention.
Claims (4)
1. a kind of relay protection warning information semantic identification method, the semanteme of relay protection warning information is carried out based on decision tree
Identification, realizes the automatic identification to relay protection warning information；It is characterized in that the relay protection warning information semantic identification
Method comprises the steps：
Step (1) analyzes the processing procedure of relay protection history alarm information, using the build-in attribute of warning information, and combines people
The electric current of required reference, voltage when work positions failure, open into, the fault eigenvalue such as output, form the attribute of the warning information
Information, and semanteme and real processing results with reference to described by each history alarm information, sample data is formed, subsequently into step
Suddenly (2)；
Step (2) carries out decision tree training study using multinomial sample data, carries out branch and the beta pruning of decision tree, produces relay
Protection alarm information decision tree；
Step (3) gathers the warning information, while call relay protection to work as after operating relay protection produces warning information
Preceding operation analog quantity and switching value, and be inputted decision-making root vertex and make inferences；
Step (4) decision tree reasoning fails, and decision tree is trained as sample data using after this warning information manual analysis,
Generate new decision tree；
Step (5) decision tree reasoning success, decision tree the reasoning results are exported, including alarm property, abort situation, failure are former
Cause.
2. relay protection warning information semantic identification method according to claim 1, it is characterised in that：
In the step (2), relay protection warning information decision tree production method is：
1) possible decision tree space is traveled through using top-down greedy search, the best attribute of selection sort ability is as tree
Root node；
2) according to the difference of current node attribute value, training sample data collection is divided into some subsets, each subset is the knot
One branch of point, the nodal community are no longer participate in follow-up branch；
3) repeat 1), 2) process, untill not remaining attribute can be used for further division sample.
3. relay protection warning information semantic identification method according to claim 2, it is characterised in that：
Whether the attribute information of warning information fails including function, whether sampled value is correct, whether the correct, amount of outputing is intake
It is no correct etc.；Wherein, the best attribute of classification capacity is whether function fails.
4. relay protection warning information semantic identification method according to claim 1 or 2, it is characterised in that：
In the step (3), the inference method of relay protection warning information decision tree includes：
1) since the root node of decision tree, the comparison of warning information attribute and its value is carried out on the node of decision tree；Accuse
When some attribute and its value of alert information match with the attribute on the node and its some property value, just along the property value
Branch extend downwardly search, reach next node；
2) if it is known that having warning information attribute and the attributes match on root node in the fact, but incomplete of their property value
Match somebody with somebody, then according to closest to principle, the branch for selecting matching degree maximum is searched for downwards, reaches new node；
3) if it is known that all warning information attributes in the fact all mismatch with the attribute on node, then reasoning fails；
If 4) present node is the leaf node of decision tree, the conclusion included in leaf node, decision tree reasoning are provided
Process terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710970891.7A CN107608971A (en) | 2017-10-18 | 2017-10-18 | A kind of relay protection warning information semantic identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710970891.7A CN107608971A (en) | 2017-10-18 | 2017-10-18 | A kind of relay protection warning information semantic identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107608971A true CN107608971A (en) | 2018-01-19 |
Family
ID=61077085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710970891.7A Pending CN107608971A (en) | 2017-10-18 | 2017-10-18 | A kind of relay protection warning information semantic identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107608971A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765447A (en) * | 2019-01-29 | 2019-05-17 | 国网冀北电力有限公司唐山供电公司 | A kind of intelligent substation relay protection automatic test approach |
| CN110517469A (en) * | 2019-08-08 | 2019-11-29 | 武汉兴图新科电子股份有限公司 | A kind of intelligent alarm convergence method suitable for audio-video convergence platform |
| CN111106953A (en) * | 2019-12-16 | 2020-05-05 | 深圳前海微众银行股份有限公司 | Abnormal root cause analysis method and device |
| CN111898776A (en) * | 2020-08-03 | 2020-11-06 | 贵州电网有限责任公司 | Transformer substation equipment abnormity and accident handling method |
| CN112506738A (en) * | 2020-12-03 | 2021-03-16 | 上海哔哩哔哩科技有限公司 | Data visualization processing method and device |
| CN112580712A (en) * | 2020-12-15 | 2021-03-30 | 山东山大电力技术股份有限公司 | Fault processing aid decision method and system for relay protection device |
| CN113589191A (en) * | 2021-07-07 | 2021-11-02 | 江苏毅星新能源科技有限公司 | Power failure diagnosis system and method |
| CN115883330A (en) * | 2023-02-08 | 2023-03-31 | 阿里云计算有限公司 | Alarm event processing method, system, device, storage medium and program product |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101609987A (en) * | 2008-06-20 | 2009-12-23 | 上海申瑞电力科技股份有限公司 | The joint coordination method of main website automatism voltage control and factory's station voltage power-less control |
| CN103714348A (en) * | 2014-01-09 | 2014-04-09 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on decision-making tree |
| CN104463709A (en) * | 2014-12-12 | 2015-03-25 | 国家电网公司 | Substation alarm information processing method based on decision trees |
| CN104506338A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Fault diagnosis expert system based on decision tree for industrial Ethernet network |
| CN104749493A (en) * | 2015-05-04 | 2015-07-01 | 江苏省电力公司苏州供电公司 | Grid fault equipment analyzing and reasoning method based on rule tree |
| CN105553990A (en) * | 2015-12-18 | 2016-05-04 | 国网天津市电力公司 | Network security triple anomaly detection method based on decision tree algorithm |
| US20170061331A1 (en) * | 2007-01-04 | 2017-03-02 | Health Care Productivity, Inc | Methods and systems for automatic selection of classification and regression trees having preferred consistency and accuracy |
| CN107016507A (en) * | 2017-04-07 | 2017-08-04 | 国网技术学院 | Electric network fault method for tracing based on data mining technology |
-
2017
- 2017-10-18 CN CN201710970891.7A patent/CN107608971A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170061331A1 (en) * | 2007-01-04 | 2017-03-02 | Health Care Productivity, Inc | Methods and systems for automatic selection of classification and regression trees having preferred consistency and accuracy |
| CN101609987A (en) * | 2008-06-20 | 2009-12-23 | 上海申瑞电力科技股份有限公司 | The joint coordination method of main website automatism voltage control and factory's station voltage power-less control |
| CN103714348A (en) * | 2014-01-09 | 2014-04-09 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on decision-making tree |
| CN104506338A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Fault diagnosis expert system based on decision tree for industrial Ethernet network |
| CN104463709A (en) * | 2014-12-12 | 2015-03-25 | 国家电网公司 | Substation alarm information processing method based on decision trees |
| CN104749493A (en) * | 2015-05-04 | 2015-07-01 | 江苏省电力公司苏州供电公司 | Grid fault equipment analyzing and reasoning method based on rule tree |
| CN105553990A (en) * | 2015-12-18 | 2016-05-04 | 国网天津市电力公司 | Network security triple anomaly detection method based on decision tree algorithm |
| CN107016507A (en) * | 2017-04-07 | 2017-08-04 | 国网技术学院 | Electric network fault method for tracing based on data mining technology |
Non-Patent Citations (2)
| Title |
|---|
| 姚浩 等: "《基于大数据的告警信息处理和故障设备定位技术研究》", 《电网与清洁能源》 * |
| 姜鹏 等: "《基于典型继电保护语义的安全措施自动生成方法研究》", 《黑龙江电力》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765447A (en) * | 2019-01-29 | 2019-05-17 | 国网冀北电力有限公司唐山供电公司 | A kind of intelligent substation relay protection automatic test approach |
| CN109765447B (en) * | 2019-01-29 | 2021-12-21 | 国网冀北电力有限公司唐山供电公司 | Automatic testing method for relay protection of intelligent substation |
| CN110517469A (en) * | 2019-08-08 | 2019-11-29 | 武汉兴图新科电子股份有限公司 | A kind of intelligent alarm convergence method suitable for audio-video convergence platform |
| CN111106953A (en) * | 2019-12-16 | 2020-05-05 | 深圳前海微众银行股份有限公司 | Abnormal root cause analysis method and device |
| CN111106953B (en) * | 2019-12-16 | 2024-04-16 | 深圳前海微众银行股份有限公司 | Method and device for analyzing abnormal root cause |
| CN111898776A (en) * | 2020-08-03 | 2020-11-06 | 贵州电网有限责任公司 | Transformer substation equipment abnormity and accident handling method |
| CN112506738A (en) * | 2020-12-03 | 2021-03-16 | 上海哔哩哔哩科技有限公司 | Data visualization processing method and device |
| CN112580712A (en) * | 2020-12-15 | 2021-03-30 | 山东山大电力技术股份有限公司 | Fault processing aid decision method and system for relay protection device |
| CN113589191A (en) * | 2021-07-07 | 2021-11-02 | 江苏毅星新能源科技有限公司 | Power failure diagnosis system and method |
| CN113589191B (en) * | 2021-07-07 | 2024-03-01 | 郴州雅晶源电子有限公司 | Power failure diagnosis system and method |
| CN115883330A (en) * | 2023-02-08 | 2023-03-31 | 阿里云计算有限公司 | Alarm event processing method, system, device, storage medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107608971A (en) | A kind of relay protection warning information semantic identification method | |
| CN110717665B (en) | System and method for fault identification and trend analysis based on scheduling control system | |
| CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
| Xu et al. | Power distribution fault cause identification with imbalanced data using the data mining-based fuzzy classification $ e $-algorithm | |
| CN104463709B (en) | A kind of substation's alarm information processing method based on decision tree | |
| CN104363106B (en) | A kind of communicating for power information fault pre-alarming analysis method based on big data technology | |
| CN109840157A (en) | Method, apparatus, electronic equipment and the storage medium of fault diagnosis | |
| CN112448836A (en) | Fault root cause determination method, device, server and computer readable medium | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN109101906A (en) | A kind of converting station electric power equipment infrared image exception real-time detection method and device | |
| CN105376193B (en) | The intelligent association analysis method and device of security incident | |
| CN107770797A (en) | A kind of association analysis method and system of wireless network alarm management | |
| CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
| CN107016507A (en) | Electric network fault method for tracing based on data mining technology | |
| CN111474444B (en) | Line fault power restoration decision method based on knowledge graph | |
| CN105867347B (en) | Cross-space cascading fault detection method based on machine learning technology | |
| CN112464995A (en) | Power grid distribution transformer fault diagnosis method and system based on decision tree algorithm | |
| Kaouk et al. | A review of intrusion detection systems for industrial control systems | |
| CN108288875A (en) | A kind of relay protection intelligent alarm method and system opened based on multi-source data with check analysis | |
| CN116304928A (en) | Power supply equipment fault prediction method, device, equipment and storage medium | |
| CN106130986A (en) | A kind of wind energy turbine set active safety defence method based on automated decision-making | |
| CN117411703A (en) | Modbus protocol-oriented industrial control network abnormal flow detection method | |
| CN116094174A (en) | Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium | |
| CN104978837B (en) | A kind of warning system and its implementation of user oriented end electric substation | |
| CN111044845A (en) | Power distribution network accident identification method and system based on Apriori algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180119 |
|
| RJ01 | Rejection of invention patent application after publication |