CN109726200A - Grid information system fault location system and method based on two-way deep neural network - Google Patents
Grid information system fault location system and method based on two-way deep neural network Download PDFInfo
- Publication number
- CN109726200A CN109726200A CN201811487032.3A CN201811487032A CN109726200A CN 109726200 A CN109726200 A CN 109726200A CN 201811487032 A CN201811487032 A CN 201811487032A CN 109726200 A CN109726200 A CN 109726200A
- Authority
- CN
- China
- Prior art keywords
- fault
- failure
- information system
- neural network
- grid information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a kind of grid information system fault location systems and method based on two-way deep neural network, including failure monitoring module, inference machine, database, deep learning module;The forward and reverse training of deep neural network is carried out to failure tree analysis (FTA) result, the corresponding relationship obtained between fault signature and abort situation is stored in expert knowledge library, carry out grid information system failure monitoring, the fault signature write-in characteristic database that will be obtained according to monitoring data, according to expert knowledge library and fault signature, reasoning obtains fault location result.The present invention can effectively solve the problems, such as that grid information system fault location is difficult, positioning is slow, positioning is inaccurate, it enables the system to issue alarm in the first time that failure occurs, and combination failure can be realized the intelligent fault positioning and Intelligent treatment function of information system from processing system, it can be further improved grid information system O&M efficiency, guarantee information system safe and stable operation.
Description
Technical field
The invention belongs to information system fault diagnosis technology fields more particularly to a kind of based on two-way deep neural network
Grid information system fault location system and method.
Background technique
With the development of science and technology, information system is in enterprise using more and more extensive.The coordination office of Mu Guowang company,
The level-ones application deployment system such as unified rights, ERP arrived 76 sets, the core systems quantity such as second level deployment marketing, finance, production
Increase year by year.These information systems provide guarantee for the production, operation and management of power grid, once information system breaks down,
Disastrous effect will be caused to the business of power grid.
Grid information system has the characteristics that complexity height, strong real-time, dynamic are high, safety requirements is high, meanwhile, system
Machine is old, performance is gradually reduced causes information system failure rate to rise year by year, evening fault discovery time, fault recovery period
Long, the integrity problem of system is increasingly prominent.Although current fault diagnosis comes into automatic phase, but still dependent on fortune
The experience of peacekeeping expert, the control of lack of wisdom brain.Therefore, how using new technology grid information system failure intelligence is made
Can diagnose just is particularly important, and fault location is the basis of fault diagnosis.
Fault location technology develops to today, there is many methods for solving orientation problem.There is the software event based on data-link
Hinder localization method, there is the Fault Locating Method of configuration management database combination failure tree, it is fixed that there are also the failures based on immune algorithm
Position technology, the Fault Locating Method based on BP neural network and fault tree.
For the Fault Locating Method based on BP neural network and fault tree that transformer fault proposes, this method is received first
Collection arranges transformer fault information content as training and identification sample, establishes the transformer fault diagnosis mould based on BP neural network
Type recycles Fault Tree Analysis, divides to transformer fault grade, severity etc..But grid information system
Increasingly complex compared to transformer, the possible position to break down is changeable and is difficult to exclude, and therefore, it is necessary to be directed to electric network information system
The fault characteristic of system invents the accurate positionin that new method carries out failure.
Existing technical solution is not designed specifically for grid information system fault location, greatly both for a certain
Specific mechanical or single system.Current grid information system fault location guarantee lacks automation means based on artificial.
Existing Supporting System relies primarily on people and carries out whole control, need to spend big to ensure that system does not go wrong for guiding
Amount manpower goes to follow in discovery failure, then carries out post-processing again, lacks effective hand that information system carries out fault location automatically
Section." nerve " of the grid information system as Guo Wang company, plays the part of more and more important role, the reliability requirement of information system
Also it improves increasingly.Using existing technical solution, it is not able to satisfy demand of the grid information system to reliability, can not solve to believe
Cease the intelligentized demand of system failure localization process.
Meanwhile traditional BP neural network is a kind of optimization method of local search, there are local minimization problems, convergence
Speed is slow, BP neural network structure choice is different, contradictory problems, BP neural network predictive ability of application example and network size
With the contradictory problems and BP neural network sample dependency problem of Training Capability.
Summary of the invention
Goal of the invention: in view of the above problems, the present invention proposes a kind of electric network information system based on two-way deep neural network
System fault location system and method carry out implementing monitoring analysis to grid information system, to realize the full mistake of power information system
The accurate positioning of journey failure.
Technical solution: to achieve the purpose of the present invention, the technical scheme adopted by the invention is that: one kind being based on two-way depth
The grid information system fault location system of neural network, including failure monitoring module, inference machine, database, deep learning mould
Block;The database includes expert knowledge library, property data base and location database, and the expert knowledge library stores fault signature
Corresponding relationship between abort situation, the fault bit that the failure tree analysis (FTA) of the location database storage historical failure obtains
It sets, the fault signature that the failure tree analysis (FTA) of the property data base storage historical failure obtains;The deep learning module is to going through
The abort situation and fault signature that the failure tree analysis (FTA) of history failure obtains carry out the forward and reverse training of deep neural network, obtain failure
Corresponding relationship between feature and abort situation, and it is stored in expert knowledge library;The failure monitoring module is for carrying out power grid
The monitoring of information system real time fail, obtains the fault signature of information system failure;The inference machine is stored according to expert knowledge library
Fault signature and abort situation between corresponding relationship and information system failure fault signature, reasoning obtains fault location knot
Fruit.
Further, the fault location system further includes human-machine interface module, by fault location result timely feedback to
Operation maintenance personnel, and issue failure alarm signal.
A kind of grid information system Fault Locating Method based on two-way deep neural network, comprising steps of
(1) failure tree analysis (FTA) of grid information system history accident is carried out, the abort situation that failure tree analysis (FTA) is obtained is deposited
It is stored in location database, fault signature is stored in property data base;
(2) the forward and reverse training of deep neural network is carried out to failure tree analysis (FTA) result, obtains fault signature and abort situation
Between corresponding relationship, be stored in expert knowledge library;
(3) grid information system failure monitoring is carried out, the fault signature of information system failure is obtained;
(4) according to the corresponding relationship and information system failure between the fault signature and abort situation of expert knowledge library storage
Fault signature, reasoning obtains fault location result.
It further, further include step 5, by the system man-machine interface of the fault location result of building, by fault location
As a result it timely feedbacks to operation maintenance personnel, and issues failure alarm signal.
Further, the step 1 includes:
(1.1) according to the relationship between grid information system composition and each section, system architecture diagram is provided;
(1.2) investigating system historical failure and reason;
(1.3) find out that consequence is serious and more incident accident is as top event from historical failure;
(1.4) from top event, the event of immediate cause is found out step by step, by its logical relation, draws fault tree;
(1.5) according to failure tree analysis (FTA) as a result, database of the building based on historical data, the event that failure tree analysis (FTA) is obtained
Barrier position is stored in location database, and fault signature is stored in property data base.
Further, the step 2 includes:
(2.1) fault signature and location information are extracted according to failure tree analysis (FTA) result;
(2.2) deep neural network forward-propagating training is carried out from fault signature to abort situation;
(2.3) deep neural network backpropagation training is carried out from abort situation to fault signature;
(2.4) by training result, expert database is arrived in corresponding relationship between fault signature and abort situation, storage.
The utility model has the advantages that the present invention can be solved effectively, grid information system fault location is difficult, positioning is slow, positioning is inaccurate asks
Topic enables the system to issue alarm in the first time that failure occurs, and combination failure can be realized letter from processing system
The intelligent fault positioning of breath system and Intelligent treatment function, can be further improved grid information system O&M efficiency, ensure letter
Breath system safe and stable operation.
Detailed description of the invention
Fig. 1 is the grid information system fault location system schematic diagram based on two-way deep neural network.
Specific embodiment
Further description of the technical solution of the present invention with reference to the accompanying drawings and examples.
As shown in Figure 1, the grid information system of the present invention based on two-way deep neural network (DNN) and fault tree
Fault location system, including failure monitoring module, inference machine, database, deep learning module and human-machine interface module.
Failure monitoring module, for monitoring the real-time status of each component of grid information system, by being deployed in hardware layer, soft
The system monitoring software of part layer, network layer and application layer is completed to provide to the layer-span combined perception of information system multi-granule and be
System real-time running data.
Inference machine is repeated reasoning according to the rule of Real-time Monitoring Data combination expert knowledge library and draws a conclusion, and is real
The brain of existing fault location, determines the accuracy and agility of fault location.Reasoning is according to established rule by acquisition data
Analysis obtains the process of result, and database and inference machine are two big cores of fault location, and inference machine of the invention is according to failure
Set the analysis that analysis rule carries out fault signature and abort situation to grid information system.
Database, including expert knowledge library, property data base and location database, expert database are used to store O&M warp
Test the fault location rule with DNN training, the as corresponding relationship between fault signature and abort situation;Property data base is used to
The information system failure that the fault signature and failure monitoring module that storage grid information system is obtained according to failure tree analysis (FTA) obtain
Feature, location database are used to store the abort situation point that grid information system is obtained according to failure tree analysis (FTA).
Deep learning module, including the forward-propagating training and backpropagation to information system fault signature and position data
Training, application failure tree analysis and two-way deep neural network (DNN), to the characteristic that monitoring system provides carry out analysis with
Self-teaching provides abort situation, determines fault rootstock.
Human-machine interface module, including positioning result and fault alarm, for inform operation maintenance personnel fault location result and and
When issue failure alarm signal.The conclusion that the result of inference machine combination DNN positive direction training obtains is fed back by man-machine interface
To operation maintenance personnel, pass through fault location and fault warning clear failure position.
As shown in Figure 1, the grid information system Fault Locating Method based on two-way deep neural network and fault tree, including
Following steps:
Step 1 carries out the failure tree analysis (FTA) of grid information system history accident, the fault bit that failure tree analysis (FTA) is obtained
It sets and is stored in location database, fault signature is stored in property data base;And according to failure tree analysis (FTA) as a result, building is based on history
The expert knowledge library of data;
S11, it is familiar with grid information system, according to the relationship between system composition and each section, provides system architecture diagram;
S12, investigating system historical failure and reason collect accident case, carry out accident statistics, it is contemplated that given system may
The accident of generation investigates all reason events related with accident and various factors;
S13, determine top event: the object to be analyzed is top event, is analyzed comprehensively the accident investigated,
Therefrom find out that consequence is serious and more incident accident is as top event;
S14, it draws fault tree: from top event, finding out the event of immediate cause step by step, until the depth to be analyzed
Degree, by its logical relation, draws fault tree;
S15, according to failure tree analysis (FTA) as a result, building the database based on historical data.
Step 2, grid information system failure monitoring, by monitoring data write-in characteristic database;
S21, monitoring system are responsible for the acquisition of all kinds of probe datas, generate alarm according to monitoring rules;
S22, by monitoring data write-in characteristic database;
S23, warning information is summarized according to rule and is formatted processing.
Step 3 carries out the forward and reverse training of deep neural network of fault signature and location information, training result is exported
To fault request;
S31, feature and location information are extracted from grid information system fault signature database and abort situation database;
S32, deep neural network forward-propagating training is carried out from fault signature to abort situation, utilizes upper one layer of output
Calculate next layer of output, as deep neural network propagated forward algorithm;
S33, deep neural network backpropagation training is carried out from abort situation to fault signature, is carrying out depth nerve net
It before network back-propagation algorithm, needs to select a loss function, to measure the calculated output of training sample and true training
Loss between sample output, present invention selection use sigmoid activation primitive and cross entropy loss function.In DNN, loss
The process that function optimization extreme value solves is most common to be iterated solution generally by gradient descent method, to the loss letter of DNN
Number is back-propagation algorithm with the process that gradient descent method is iterated optimization minimizing.
S34, training result is output to fault request.
Step 4 realizes fault request, and the analysis of fault signature and abort situation is carried out to grid information system;
S41, fault location inference rule is obtained according to grid information system historical data and failure tree analysis (FTA);
S42, in conjunction with expert knowledge library and fault signature, obtain fault location result by reasoning.
Step 5 constructs the system man-machine interface of fault location feature and result.
Man-machine interface is constructed, to assist the visualization of fault location result, directly can show failure in client terminal
Positioning result can also notify responsible person concerned by short message or other modes in time.
The present invention can effectively solve the problems, such as that grid information system fault location is difficult, positioning is slow, positioning is inaccurate, so that being
The first time that system can occur in failure issues alarm, and combination failure can be realized the event of information system from processing system
Hinder intelligent positioning and Intelligent treatment function, can be further improved grid information system O&M efficiency, guarantee information system safety
Stable operation.Can be on the basis of artificial debugging, quality to information system fault diagnosis and improved efficiency one etc.
Grade, it is possible to reduce the workload of operation maintenance personnel realizes that grid information system fault section diagnosis is intelligent.Meanwhile this method
Using the paces for accelerating the scientific and technical innovation of Guo Wang company, the scientific and technological level and management level of the informatization of power grid enterprises are promoted,
The Information Service Level of power grid enterprises is improved, the corporate image of grid company is further promoted.
Claims (7)
1. a kind of grid information system fault location system based on two-way deep neural network, which is characterized in that including failure
Monitoring module, inference machine, database, deep learning module;
The database includes expert knowledge library, property data base and location database, and the expert knowledge library storage failure is special
Corresponding relationship between abort situation of seeking peace, the fault bit that the failure tree analysis (FTA) of the location database storage historical failure obtains
It sets, the fault signature that the failure tree analysis (FTA) of the property data base storage historical failure obtains;
The abort situation and fault signature that the deep learning module obtains the failure tree analysis (FTA) of historical failure carry out depth mind
Through the forward and reverse training of network, the corresponding relationship between fault signature and abort situation is obtained;
For the failure monitoring module for carrying out grid information system real time fail monitoring, the failure for obtaining information system failure is special
Sign;
The inference machine is pushed away according to the fault signature of corresponding relationship and information system failure between fault signature and abort situation
Reason obtains fault location result.
2. the grid information system fault location system according to claim 1 based on two-way deep neural network, special
Sign is that the fault location system further includes human-machine interface module, and fault location result is timely feedbacked to operation maintenance personnel, and
Issue failure alarm signal.
3. a kind of grid information system Fault Locating Method based on two-way deep neural network, which is characterized in that comprising steps of
(1) failure tree analysis (FTA) of grid information system history accident is carried out, the abort situation that failure tree analysis (FTA) is obtained is stored in
Location database, fault signature are stored in property data base;
(2) two-way deep neural network training is carried out to failure tree analysis (FTA) result, obtained between fault signature and abort situation
Corresponding relationship;
(3) grid information system failure monitoring is carried out, the fault signature of information system failure is obtained;
(4) according to the fault signature of corresponding relationship and information system failure between fault signature and abort situation, reasoning is obtained
Fault location result.
4. the grid information system Fault Locating Method according to claim 3 based on two-way deep neural network, special
Sign is, further includes step 5, by the system man-machine interface of the fault location result of building, fault location result is anti-in time
It feeds operation maintenance personnel, and issues failure alarm signal.
5. the grid information system Fault Locating Method according to claim 3 based on two-way deep neural network, special
Sign is that the step 1 includes:
(1.1) according to the relationship between grid information system composition and each section, system architecture diagram is provided;
(1.2) investigating system historical failure and reason;
(1.3) find out that consequence is serious and more incident accident is as top event from historical failure;
(1.4) from top event, the event of immediate cause is found out step by step, by its logical relation, draws fault tree;
(1.5) according to failure tree analysis (FTA) as a result, database of the building based on historical data, the fault bit that failure tree analysis (FTA) is obtained
It sets and is stored in location database, fault signature is stored in property data base.
6. the grid information system Fault Locating Method according to claim 3 based on two-way deep neural network, special
Sign is that the step 2 includes:
(2.1) fault signature and location information are extracted according to failure tree analysis (FTA) result;
(2.2) deep neural network forward-propagating training is carried out from fault signature to abort situation;
(2.3) deep neural network backpropagation training is carried out from abort situation to fault signature;
(2.4) training obtains the corresponding relationship between fault signature and abort situation.
7. the grid information system Fault Locating Method according to claim 6 based on two-way deep neural network, special
Sign is that the corresponding relationship between the fault signature and abort situation is stored in expert knowledge library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811487032.3A CN109726200B (en) | 2018-12-06 | 2018-12-06 | Power grid information system fault positioning system and method based on bidirectional deep neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811487032.3A CN109726200B (en) | 2018-12-06 | 2018-12-06 | Power grid information system fault positioning system and method based on bidirectional deep neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109726200A true CN109726200A (en) | 2019-05-07 |
CN109726200B CN109726200B (en) | 2023-08-04 |
Family
ID=66295223
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811487032.3A Active CN109726200B (en) | 2018-12-06 | 2018-12-06 | Power grid information system fault positioning system and method based on bidirectional deep neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109726200B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110728836A (en) * | 2019-10-22 | 2020-01-24 | 深圳供电局有限公司 | Concentrator meter reading abnormity analysis method and system |
CN110766143A (en) * | 2019-10-31 | 2020-02-07 | 上海埃威航空电子有限公司 | Equipment fault intelligent diagnosis method based on artificial neural network |
CN111060815A (en) * | 2019-12-17 | 2020-04-24 | 西安工程大学 | GA-Bi-RNN-based high-voltage circuit breaker fault diagnosis method |
CN111259947A (en) * | 2020-01-13 | 2020-06-09 | 国网浙江省电力有限公司信息通信分公司 | Power system fault early warning method and system based on multi-mode learning |
CN111291245A (en) * | 2020-02-17 | 2020-06-16 | 广东电网有限责任公司电力科学研究院 | Case online generation system and method applied to PAS and computer equipment |
CN111666978A (en) * | 2020-05-11 | 2020-09-15 | 深圳供电局有限公司 | Intelligent fault early warning system for IT system operation and maintenance big data |
CN112630595A (en) * | 2020-12-09 | 2021-04-09 | 国网冀北电力有限公司 | Power grid fault treatment knowledge base management method |
CN112929977A (en) * | 2021-02-10 | 2021-06-08 | 山西大学 | Deep learning amplification forwarding cooperative network energy efficiency resource allocation method |
CN113222140A (en) * | 2021-05-10 | 2021-08-06 | 重庆邮电大学 | C4.5 algorithm and BP neuron-based power distribution network fault auxiliary decision-making method |
CN113283462A (en) * | 2021-03-24 | 2021-08-20 | 国网四川省电力公司电力科学研究院 | Secondary system fault positioning method based on improved IDNN model |
CN113721579A (en) * | 2021-07-08 | 2021-11-30 | 河北工业大学 | Loom fault diagnosis method based on fusion of expert system and neural network algorithm |
CN116827764A (en) * | 2023-08-23 | 2023-09-29 | 山西绿柳科技有限公司 | Internet of things fault detection control method and system based on neural network |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015180397A1 (en) * | 2014-05-31 | 2015-12-03 | 华为技术有限公司 | Method and device for recognizing data category based on deep neural network |
CN107330519A (en) * | 2017-06-26 | 2017-11-07 | 西北工业大学 | Fault Locating Method based on deep neural network |
CN107346466A (en) * | 2017-05-26 | 2017-11-14 | 国网山东省电力公司淄博供电公司 | A kind of control method and device of electric power dispatching system |
-
2018
- 2018-12-06 CN CN201811487032.3A patent/CN109726200B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015180397A1 (en) * | 2014-05-31 | 2015-12-03 | 华为技术有限公司 | Method and device for recognizing data category based on deep neural network |
CN107346466A (en) * | 2017-05-26 | 2017-11-14 | 国网山东省电力公司淄博供电公司 | A kind of control method and device of electric power dispatching system |
CN107330519A (en) * | 2017-06-26 | 2017-11-07 | 西北工业大学 | Fault Locating Method based on deep neural network |
Non-Patent Citations (1)
Title |
---|
刘洋等: "风力发电机典型智能故障诊断方法综述", 《上海电机学院学报》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110728836A (en) * | 2019-10-22 | 2020-01-24 | 深圳供电局有限公司 | Concentrator meter reading abnormity analysis method and system |
CN110766143A (en) * | 2019-10-31 | 2020-02-07 | 上海埃威航空电子有限公司 | Equipment fault intelligent diagnosis method based on artificial neural network |
CN111060815B (en) * | 2019-12-17 | 2021-09-14 | 西安工程大学 | GA-Bi-RNN-based high-voltage circuit breaker fault diagnosis method |
CN111060815A (en) * | 2019-12-17 | 2020-04-24 | 西安工程大学 | GA-Bi-RNN-based high-voltage circuit breaker fault diagnosis method |
CN111259947A (en) * | 2020-01-13 | 2020-06-09 | 国网浙江省电力有限公司信息通信分公司 | Power system fault early warning method and system based on multi-mode learning |
CN111291245A (en) * | 2020-02-17 | 2020-06-16 | 广东电网有限责任公司电力科学研究院 | Case online generation system and method applied to PAS and computer equipment |
CN111666978A (en) * | 2020-05-11 | 2020-09-15 | 深圳供电局有限公司 | Intelligent fault early warning system for IT system operation and maintenance big data |
CN111666978B (en) * | 2020-05-11 | 2023-12-01 | 深圳供电局有限公司 | Intelligent fault early warning system for IT system operation and maintenance big data |
CN112630595A (en) * | 2020-12-09 | 2021-04-09 | 国网冀北电力有限公司 | Power grid fault treatment knowledge base management method |
CN112929977A (en) * | 2021-02-10 | 2021-06-08 | 山西大学 | Deep learning amplification forwarding cooperative network energy efficiency resource allocation method |
CN113283462B (en) * | 2021-03-24 | 2022-09-20 | 国网四川省电力公司电力科学研究院 | Secondary system fault positioning method based on improved IDNN model |
CN113283462A (en) * | 2021-03-24 | 2021-08-20 | 国网四川省电力公司电力科学研究院 | Secondary system fault positioning method based on improved IDNN model |
CN113222140B (en) * | 2021-05-10 | 2022-09-20 | 重庆邮电大学 | C4.5 algorithm and BP neuron-based power distribution network fault auxiliary decision-making method |
CN113222140A (en) * | 2021-05-10 | 2021-08-06 | 重庆邮电大学 | C4.5 algorithm and BP neuron-based power distribution network fault auxiliary decision-making method |
CN113721579A (en) * | 2021-07-08 | 2021-11-30 | 河北工业大学 | Loom fault diagnosis method based on fusion of expert system and neural network algorithm |
CN116827764A (en) * | 2023-08-23 | 2023-09-29 | 山西绿柳科技有限公司 | Internet of things fault detection control method and system based on neural network |
CN116827764B (en) * | 2023-08-23 | 2023-11-03 | 山西绿柳科技有限公司 | Internet of things fault detection control method and system based on neural network |
Also Published As
Publication number | Publication date |
---|---|
CN109726200B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109726200A (en) | Grid information system fault location system and method based on two-way deep neural network | |
CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
CN104407589B (en) | Workshop manufacturing process-oriented active sensing and anomaly analysis method of real-time production performance | |
CN113450065B (en) | Production operation management system and method for wind power plant | |
CN109785289A (en) | A kind of transmission line of electricity defect inspection method, system and electronic equipment | |
CN110493025A (en) | It is a kind of based on the failure root of multilayer digraph because of the method and device of diagnosis | |
CN109857080B (en) | Intelligent ship lock operation and maintenance system based on BIM | |
CN108923531B (en) | Power grid dispatching alarm monitoring system based on big data | |
DE212016000186U1 (en) | simulation system | |
KR20180108446A (en) | System and method for management of ict infra | |
CN106301522A (en) | The Visual method of fault diagnosis of Remote Sensing Ground Station data receiver task and system | |
CN103888287A (en) | Information system integrated operation and maintenance monitoring service early warning platform and realization method thereof | |
CN106302015A (en) | A kind of service condition monitoring method, device and system | |
CN109471698B (en) | System and method for detecting abnormal behavior of virtual machine in cloud environment | |
CN109204389A (en) | A kind of subway equipment fault diagnosis and self-healing method, system | |
CN110689148A (en) | Metering equipment fault detection method based on AR technology | |
CN108519769A (en) | A kind of rule-based flight control system method for diagnosing faults | |
CN110033102A (en) | A kind of huge hydroelectric power plant has the intelligent diagnosing method and expert system of learning functionality | |
CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
CN113741368A (en) | Power enterprise safety production management method based on management and control of Internet of things | |
Singh et al. | EYE-on-HMI: A Framework for monitoring human machine interfaces in control rooms | |
CN117074822A (en) | Charging pile fault diagnosis method, computer equipment and storage medium | |
CN116796633A (en) | Power grid monitoring model correction method based on digital twin technology | |
CN115731073A (en) | Scheduling operation abnormity monitoring method based on service scene analysis | |
CN116128197A (en) | Intelligent airport management system and method |
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 |