CN104679828A - Rules-based intelligent system for grid fault diagnosis - Google Patents
Rules-based intelligent system for grid fault diagnosis Download PDFInfo
- Publication number
- CN104679828A CN104679828A CN201510022964.0A CN201510022964A CN104679828A CN 104679828 A CN104679828 A CN 104679828A CN 201510022964 A CN201510022964 A CN 201510022964A CN 104679828 A CN104679828 A CN 104679828A
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge
- knowledge base
- base
- rule
- 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
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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a rules-based intelligent system for grid fault diagnosis, comprising a real-time data acquisition module, a data receiver, a preprocessing module, a working database, a knowledge base, an inference engine and a command generator. The real-time data acquisition module acquires real-time data information of a grid and sends it to the data receiver; the data receiver performs reasonableness testing and encoding; the preprocessing module performs formatting and information fusing and sorting and stores the information in the working database; the working database sends a command to the inference engine; the inference engine sends an inference verification request to the knowledge base; the knowledge base acquires data from the working database and performs data matching on the basis of a grid CIM (common information model) according to knowledge rules in the knowledge base built; the inference engine performs inference analysis according to the data in the working database, system state and knowledge in the knowledge base. The system has the advantages that a self-learning function is achieved, checking and error correcting is facilitated and grid fault diagnosis is more efficient.
Description
Technical field
The present invention relates to a kind of safe operation of electric network technical field, particularly a kind of rule-based electric network failure diagnosis intelligent system.
Background technology
The development of electrical network and the progress of society are all had higher requirement to the security of operation of electrical network, strengthen seeming particularly important to the diagnostic process of electric network fault.Along with the development of computer technology, the communication technology, network technology etc., adopt more advanced intellectual technology to improve the performance of electric network failure diagnosis system, there is important researching value and practical significance.The Intelligent Diagnosis Technology of fault is also referred to as Intelligent Fault Diagnosis Technique, intelligent trouble diagnosis is the new method having merged artificial intelligence technology, have preliminary automatic analysis and learning ability to failure message, the artificial intelligence technology that electric network failure diagnosis field is commonly used comprises expert system, artificial neural network, decision tree theory etc.Wherein, expert system is most important in artificial intelligence is also a most active application technology, it achieves artificial intelligence and moves towards practical application from theoretical research, inquire into the important breakthrough turning to and use special knowledge from general inference strategy.
The research direction of current expert system has RBES and object-oriented expert system etc., RBES is the experience according to expert diagnosis in the past, be generalized into rule, carry out fault diagnosis by Heuristic Experience knowledge, be suitable for the fault diagnosis of the professional domain with rich experiences.Rule-based diagnosis has that exploitation is simple, knowledge expression directly perceived, unity of form, easily understand, explain convenient, adaptability and the pioneering advantage such as good, and diagnostic knowledge can be obtained by domain expert and inherit, therefore is widely applied.But RBES is in the past all the decision-making sustentions by experts carried out based on inference machine, lacks effectively study property, and feeds back knowledge content and lack validity, can not accomplish in pre-property, therefore accuracy is not good.
Summary of the invention
The present invention is directed to existing RBES and lack the problem such as study property and feedback knowledge content shortage validity, a kind of rule-based electric network failure diagnosis intelligent system is provided, adopt unique knowledge base and inference machine structure, realize self-learning function, complete electric network fault intelligent diagnostics and analysis, and be easy to check and error correction, improve the efficiency of electric network failure diagnosis.
Technical scheme of the present invention is as follows:
A kind of rule-based electric network failure diagnosis intelligent system, it is characterized in that, comprise the real-time data acquisition module, data sink, pretreatment module and the working data base that connect successively, also comprise knowledge base, inference machine and instruction generator, described working data base, knowledge base are connected between two with inference machine, data sink is sent to after the real time data information of described real-time data acquisition module acquires electrical network, described data sink carries out format by pretreatment module again after carrying out rationality checking and decoding process and information fusion classification processes and is stored to working data base, reasoning checking request is sent by inference machine to knowledge base after described working data base sends instruction to inference machine, described knowledge base obtains the data in working data base and carries out Data Matching based on electrical network CIM according to the knowledge rule in the knowledge base set up, rational analysis is carried out according to data in working data base and system state and knowledge in knowledge base according to reasoning algorithm by inference machine, the order of the rational analysis result generating standard of inference machine exports by described instruction generator.
Described knowledge base comprises knowledge base formula area and knowledge base model district, described inference machine comprises interconnective knowledge editor and rational analysis device, described knowledge base formula area is all connected with working data base with knowledge editor, described knowledge base formula area is connected with rational analysis device with knowledge editor respectively with knowledge base model district, and described rational analysis device and instruction maker is connected; Described working data base sends instruction to knowledge editor, send reasoning by knowledge editor to knowledge base formula area and verify request, electrical network CIM according to the knowledge rule in the knowledge base set up and in conjunction with knowledge base model district after described knowledge base formula area obtains the data in working data base carries out Data Matching, and described rational analysis device carries out rational analysis according to reasoning algorithm.
Described knowledge base also comprises knowledge base prototype district and knowledge base experience district, described inference machine comprises the experience accumulation device be connected with rational analysis device with knowledge editor respectively, described knowledge base prototype district is connected with rational analysis device with knowledge editor respectively, and described knowledge base experience district is connected with experience accumulation device; Decision-making prototype is provided with in described knowledge base prototype district, described decision-making prototype comprises load prediction prototype, fault diagnosis prototype and system state and analyzes prototype, described experience accumulation device by the data of rational analysis device in rational analysis process according to knowledge rule stored in knowledge base experience district, described knowledge base experience district utilizes fuzzy clustering algorithm to carry out the extraction of cluster analysis and forecasting type knowledge to historical data for the feature of electrical network historical data.
Also comprise visual LCD MODULE, transmitter and communication interface, described working data base and instruction generator are all connected with visual LCD MODULE, described instruction generator is also connected with transmitter, and the standardization order of instruction generator is connected with extraneous execution module by communication interface by described transmitter.
Described real-time data acquisition module utilizes the real time data information of extraneous sensor or the electrical network needed for the reasoning of monitoring device real-time acquisition system, described real-time data acquisition module adopts polling method to gather by the cycle to slow varying signal, adopts the collection of interruption method to fast changed signal.
Carry out rationality checking after the information of described data sink receiving real-time data acquisition module collection, and decoding process is carried out to digital quantity signal in data stream, data are delivered in pretreatment module by electrical network isolation gap; Described rationality checking comprises the integrality detecting data.
Described pretreatment module formats the information received and information fusion sorts out process, described information fusion is sorted out process and is comprised information fusion, reports to the police to merge and sort out and priority allocation, described pretreatment module according to priority adds buffer queue again after information fusion sorts out process, enters working data base.
Described rational analysis device is supported data-oriented and goal-oriented inference mode and is adopted Forecast reasoning algorithm and related reasoning algorithm to carry out rational analysis.
Described knowledge base experience district first adopts the Frequent Itemsets Mining Algorithm based on class set to carry out the data mining of frequent item set correlation rule for the feature of electrical network historical data, reject and the incoherent attribute of decision information, then utilize fuzzy clustering algorithm to carry out the extraction of cluster analysis and forecasting type knowledge to historical data.
Technique effect of the present invention is as follows:
Rule-based electric network failure diagnosis intelligent system provided by the invention, real-time data acquisition module is set, data sink, pretreatment module, working data base, knowledge base, inference machine and instruction generator, data sink is sent to after the real time data information of real-time data acquisition module acquires electrical network, data sink carries out format by pretreatment module again after carrying out rationality checking and decoding process and information fusion classification processes and is stored to working data base, reasoning checking request is sent by inference machine to knowledge base after working data base sends instruction to inference machine, knowledge base obtains the data in working data base and carries out Data Matching based on electrical network CIM according to the knowledge rule in the knowledge base set up, rational analysis is carried out according to data in working data base and system state and knowledge in knowledge base according to reasoning algorithm by inference machine, the order of the rational analysis result generating standard of inference machine exports by instruction generator.Present system sets independently knowledge base, setting knowledge rule in this knowledge base, knowledge base obtains the data in working data base and carries out Data Matching based on electrical network CIM according to the knowledge rule in the knowledge base set up, namely knowledge base it be the relevant fact extracting problem from the true logic set up, so be easy to check and error correction.Inference machine carries out rational analysis according to data in working data base and system state and knowledge in knowledge base according to reasoning algorithm, and can upgrade knowledge in knowledge base, expand and adjust in time, realize the function of self study, avoid the problem that existing RBES lacks study property, working data base of the present invention coordinates knowledge base and the inference machine structure of ad hoc structure, each assembly cooperating, the information accurate and effective of final output, accurately complete electric network fault intelligent diagnostics and analysis, improve the efficiency of electric network failure diagnosis.
Knowledge base preferably arranges knowledge base formula area and knowledge base model district, knowledge base formula area to obtain after the data in working data base according to the knowledge rule in the knowledge base set up and the electrical network CIM in combination model district carries out Data Matching, inference machine preferably arranges knowledge editor and rational analysis device, knowledge editor can be modified to the knowledge in knowledge base and supplement, add the dirigibility of present system, rational analysis is carried out according to the knowledge of knowledge base different aspect and operational data database data and state vector according to reasoning algorithm by rational analysis device, the knowledge base of ad hoc structure and other component working of inference machine coupled system, improve the accurate performance of electric network fault intelligent diagnostics, make present system can not only use logic knowledge, also heuristic knowledge can be used, there is feature that the is enlightening and transparency.
Knowledge base also preferably includes knowledge base prototype district and knowledge base experience district, inference machine preferably includes experience accumulation device, disposal route to problem, decision data and treatment effect etc. are sent to knowledge base experience district by experience accumulation device, think the basis of the renewal of knowledge of each assembly in next decision-making and knowledge base.Knowledge base experience district stores the data that experience accumulation device inputs, and can improve speed and the validity of decision-making.Knowledge base prototype district can provide prototype to mate foundation when knowledge base formula area and knowledge base model district can not be mated, improve the efficiency of electric network fault intelligent diagnostics further.
Accompanying drawing explanation
Fig. 1 is the structural representation of the electric network failure diagnosis intelligent system that the present invention is based on rule.
Fig. 2 is the local preferred structure schematic diagram of the electric network failure diagnosis intelligent system that the present invention is based on rule.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be described.
The present invention relates to a kind of rule-based electric network failure diagnosis intelligent system, its structure as shown in Figure 1, comprise the real-time data acquisition module, data sink, pretreatment module and the working data base that connect successively, also comprise knowledge base, inference machine and instruction generator, working data base, knowledge base are connected between two with inference machine.Data sink is sent to after the real time data information of real-time data acquisition module acquires electrical network, data sink carries out format by pretreatment module again after carrying out rationality checking and decoding process and information fusion classification processes and is stored to working data base, reasoning checking request is sent by inference machine to knowledge base after working data base sends instruction to inference machine, knowledge base obtains the data in working data base and carries out Data Matching based on electrical network CIM according to the knowledge rule in the knowledge base set up, by inference machine according to data in working data base and system state and know and carry out rational analysis with knowledge in storehouse according to reasoning algorithm, the order of the rational analysis result generating standard of inference machine exports by instruction generator.The scheme that inference machine infers is supplied to dispatcher with proposed way by man-machine interface (visual LCD MODULE as shown in Figure 1) or is directly sent to extraneous execution module with robotization command mode by transmitter.In whole implementation, dispatcher can interfere execution and the decision-making of expert system, to supervise the correctness of decision-making.
Below each assembly of the electric network failure diagnosis intelligent system that the present invention is based on rule is described in detail.
Real-time data acquisition module: the real time data information gathering electrical network, namely the collection external information shown in Fig. 1, external information is interpreted as it is input signal of the present invention, can comprise electrical network CIM, tomorrow various places load prediction data, generating plant generation schedulecurve data, prediction and the real time data information such as grid equipment inspecting state.External information source is aggregated in electrical network scheduling professional system at different levels by the collection of electrical network one or two electrical network professional equipments.Real-time data acquisition module utilizes the real time data information of extraneous sensor or the electrical network needed for the reasoning of monitoring device real-time acquisition system, accessing database interface modes can be adopted and resolve broadcast mode two kinds of forms of expression and carry out data acquisition, adopt polling method by cycle T collection to slow varying signal, the collection of interruption method is adopted to fast changed signal, and then by interface, communication port pattern, the data message of collection is sent in data sink.In addition, as shown in Figure 1, real-time data acquisition module also receives the order manually assigned by visual man-machine interface by dispatcher.
Data sink: receive the information from accepting from real-time data capture module acquires, carry out preliminary rationality checking, whether rationality checking major function data are complete, whether there is situations such as lacking data, and decoding process is carried out to digital quantity signal in data stream (need to pass more electrical network isolation gap in transmission data, coding&decoding means are adopted to carry out data transmission), data stream is directly translated into the variate-value that System program can call, and be stored in the field of the working data base pre-defined according to a definite sequence, this step decreases data processing time, real time data is processed in real time as far as possible, improve the efficiency of expert system.Data are delivered in pretreatment module by electrical network isolation gap (electricity grid network is mainly divided into safety 2nd district can not go up internet, internet can be gone up by safety 3rd district by electrical network isolation gap).Data sink ensures that in transmittance process real time data processes in real time as possible, the efficiency of expert system of trying hard to keep.
Pretreatment module: the information from data sink is converted to subsequent rationale machine and the discernible problem description of knowledge base, or perhaps is converted to the discernible problem description of expert.After the information received by data sink imports pretreatment module into, format, determine its character and carry out certain information fusion classification process (to comprise information fusion, report to the police to merge and sort out, priority allocation etc.), according to priority add buffer queue again, prepare to enter working data base.
Working data base: different according to subregion according to database structure, stores different information.Information comprises the discernible problem descriptor that pretreatment module sends, and the content such as knowledge base-feedback information.Working data base is exactly the place storing relevant information.Working data base sends instruction to inference machine, and can upgrade the algorithm in inference machine, also discernible problem description data information is stored in knowledge base.
As shown in Figure 2, knowledge base comprises knowledge base formula area, knowledge base model district, knowledge base prototype district and knowledge base experience district to the priority structure of knowledge base and inference machine, and inference machine comprises interconnective knowledge editor, rational analysis device, experience accumulation device; Knowledge base formula area is all connected with working data base with knowledge editor, knowledge base formula area, knowledge base model district are connected with rational analysis device with knowledge editor respectively with knowledge base prototype district, knowledge base experience district is connected with experience accumulation device, and rational analysis device and instruction maker is connected.Working data base sends instruction to knowledge editor, send reasoning by knowledge editor to knowledge base formula area and verify request, electrical network CIM according to the knowledge rule in the knowledge base set up and in conjunction with knowledge base model district after knowledge base formula area obtains the data in working data base carries out Data Matching, and rational analysis device carries out rational analysis according to reasoning algorithm.Knowledge base prototype is provided with decision-making prototype in district, described decision-making prototype comprises load prediction prototype, fault diagnosis prototype and system state and analyzes prototype, described experience accumulation device by the data of rational analysis device in rational analysis process according to knowledge rule stored in knowledge base experience district, described knowledge base experience district utilizes fuzzy clustering algorithm to carry out the extraction of cluster analysis and forecasting type knowledge to historical data for the feature of electrical network historical data.
Knowledge base is in every way one or more information association message structure together.Knowledge base formula area stores dependency rule according to electric network data characteristic, adopts production rule as basic representation.For example, it is as follows that knowledge base rule schemata can be set: [knowledge ID] [affiliated Knowledge category] [keyword] [Knowledge Element title] [knowledge description] [associated entry] [device name] [condition 1 ..., condition n], wherein
(1) knowledge ID: the unique identification of knowledge in knowledge base unit.
(2) Knowledge category belonging to: the particular type of Knowledge Element in knowledge base, is mainly divided into forecasting type knowledge or association type knowledge.
(3) keyword: for realizing the fast search with knowledge connection content.
(4) Knowledge Element title: title is the direct mark of Knowledge Element, with corresponding knowledget opic word name, is the search channel directly retrieving this Knowledge Element.
(5) Knowledge Element describes: carry out complete text description and the auxiliary description of image to the content of Knowledge Element.This description generally includes: the content such as axiom, formula, definition, inference, the fact, event, example, number table, and can constantly update and adjust.
(6) associated entry: the content links entry inventory be associated with this Knowledge Element.Its content comprises: relevant device state, other Knowledge Elements mark (title or ID).
(7) device name: the relevant carriers depended on when this Knowledge Element outwardly represents.
(8) condition n: the correlated condition obtaining this Knowledge Element describes.
Knowledge base model district: store electrical network CIM, or perhaps deposit the canonical algorithm for decision-making, this has the situation of clear and definite processing scheme to design for some.
Knowledge base prototype district: for not by the situation of knowledge base model decision-making, if starting situation, then add prototype district, and the decision process of recording dispatching personnel.If not being starting situation, then recording dispatching personnel decision-making, and add prototype district by calculating similarity mode formula.Knowledge base prototype mainly comprises following decision-making prototype: (1) load prediction prototype; (2) fault diagnosis prototype; (3) system state analyzes prototype.The method for expressing of decision-making prototype is: [Knowledge category] [decision-making prototype ID] [algorithm title] [arthmetic statement] [executive condition] [physical pathway].Wherein, [Knowledge category]: as value 004, expression is decision rule.[decision-making prototype ID]: one 32 of system stochastic generation is character string, as the unique identification of decision rule.[algorithm title]: electric network data load prediction is analyzed.[arthmetic statement]: key step indicates.[executive condition]: the parameter that must need when algorithm performs is a variable data array.[physical pathway]: the path that algorithmic code physics is deposited.
Knowledge base experience district: store the data that experience accumulation device inputs, can improve speed and the validity of decision-making, and is used to knowledge in knowledge base renewal.Knowledge base experience district is for the feature of electric power historical data, proposition utilizes rough set to objective factors and carries out yojan, process is: reject and the incoherent attribute of decision information, then fuzzy clustering algorithm is utilized to carry out cluster analysis to historical data, finally according to the result of cluster analysis, carry out the extraction of forecasting type knowledge.
First knowledge base experience district according to the minimum support min_c set, finds out the frequent item set that all supports are greater than min_c; Then in all frequent item sets, find degree of confidence to be greater than the correlation rule of min_c.The core of Apriori algorithm is the excavation of frequent item set.Above two benches, in the process realized, asks the method for correlation rule also fairly simple after finding frequent item set.But there are following two aspects and there is performance bottleneck problem in Apriori algorithm: on the one hand, Multiple-Scan transaction database, needs very large I/O load.Such as: a frequent item set includes 10 item collection, so scan transaction database to need at least 10 times; On the other hand, the generation of huge candidate collection, huge candidate set pair time and the primary memory space are all a kind of challenges.The present invention, by improving the Apriori algorithm of classics, simultaneously in conjunction with the feature of electric network data, proposes a kind of Frequent Itemsets Mining Algorithm based on class set, to realize the efficient excavation for electric network data frequent item set.Should be based on the basic thought of the Frequent Itemsets Mining Algorithm of class set:
1. adopting the method for class wrapper frequent episode, include in such: key name, degree of confidence, support, store in the form of classes after the frequent item set generated, when calculating the support of marquis's set of choices, directly can obtain from category.
2. after Multiple-Scan transaction database, I/O load needs very large performance bottleneck, data in transaction database are first stored into the method in two-dimensional array by employing, carry out carrying out dredge operation to frequent item set for two-dimensional array, can avoid so frequently carrying out transaction database scanning, thus improve digging efficiency.Algorithmic procedure is as follows: first, scan for electrical network transaction database, and the data excavated are stored in N---dimension group, then association mining is carried out for the data in two-dimensional array, finally with Format Object, the frequent item set obtained is stored in class set Vector, the calculating of support and degree of confidence can be realized by class set.
Inference machine: first working data base enters the knowledge editor of inference machine after receiving the data of pretreatment module, knowledge editor extracts knowledge base rule and knowledge base model, the content such as knowledge rule, model required according to knowledge base carries out compiling after matching disposal data information, and whether algorithm upgrades in judging and deducing analyzer, and upgrade its algorithm, for rational analysis device uses, simultaneously for follow-up work lays the foundation.In addition knowledge editor is the vitals embodying expert system intelligence, it achieve the self-learning function of system, by the analysis of solution inputted knowledge base experience accumulation district and external operation person, can knowledge base knowledge be upgraded, expands and be adjusted.
Rational analysis device is the main technical elements of inference machine, can carry out analyzing and reasoning according to reasoning algorithm according to the knowledge of different aspect in data in working data base and system state vector and knowledge base, the rationality of the reasoning results is directly reflected in the correctness of the result of decision and the real-time of decision process.The inference mode of forward direction (data-oriented) and backward (object-oriented) supported by rational analysis device, and known by verifying, forward inference is most suitable in " hypothesis " stage of monitoring equipment Study on Trend and inference machine; Backward reasoning is in tracking highest ranking fault and guide operator to carry out in the maintenance process of being correlated with being the most useful.Rational analysis device adopts Forecast reasoning algorithm and these two kinds of reasoning algorithms of related reasoning algorithm to carry out dependency inference analysis.Rational analysis device carries out the rational analysis of problem description, will predict the outcome and be deposited in working data base, for the visual LCD MODULE in foreground is as support.Carrying out in rational analysis process, system can provide the capable suggestion order of aid decision making.Rational analysis device job step is as follows:
1) knowledge editor editor knowledge content is extracted;
2) knowledge optimum data information is selected.
(such as predict network load data, in Xu Zhao prototype district and experience district, the data message of similarity is as support.Similarity comprises: the content such as topological structure of electric, weather condition, generating prediction curve data message, load prediction data information, overhaul of the equipments situation) simultaneously, system originally of also extracting provides advice content.
3), after the data message selecting the current pretreatment module of knowledge optimum data information comparison to generate, whether best knowledge data message meets, as provided data message according to original experience suggestion, output buffer queue.
Experience accumulation device: in rational analysis process, best knowledge data can not meet, and the disposal route to problem, decision data and treatment effect are deposited into knowledge base experience district, using the basis as next rational analysis and knowledge base update according to knowledge rule.
Instruction generator: the order of the reasoning results generating standard of rational analysis device or suggestion, is fed back to commander by man-machine interface (visual LCD MODULE) or is sent to extraneous execution module by transmitter and automatically perform.
Present system as shown in Figure 1 also comprises visual LCD MODULE, transmitter and communication interface, and working data base and instruction generator are all connected with visual LCD MODULE, and instruction generator is also connected with transmitter.Related data in working data base can show as man-machine interface by visual LCD MODULE, and can provide inquiry and print application.The data message (or perhaps policy information) of the standardization order of instruction generator is connected with extraneous execution module by communication interface by transmitter, as passed to subordinate generating plant professional system.Issuing in data command process, dispatcher sends instructions under can interfering (simultaneously according to dispatcher's experience, real-time change weather, local activity schedule situation, adjustment issues director data information).Data pass in generating plant professional system by communication interface.Whether dispatcher, by communication interface mode, checks generating plant and accepts and adopt to issue data message, feed back.
The present invention is based on the electric network failure diagnosis intelligent system of rule, also can be regarded as is RBES, by a large amount of IT field, the relevant special knowledge of energy field and experience make a policy the working model of brand-new expert system of suggestion and structure, adopt the knowledge base of absolute construction, the inference machine of ad hoc structure, work with working data base and other part fits, the information accurate and effective of final output, realize self-learning function, accurately complete electric network fault intelligent diagnostics and analysis, improve the efficiency of electric network failure diagnosis, and there is enlightenment, the advantages such as the transparency and dirigibility.
It should be pointed out that the above embodiment can make the invention of those skilled in the art's comprehend, but do not limit the present invention in any way creation.Therefore; although this instructions has been described in detail the invention with reference to drawings and Examples; but; those skilled in the art are to be understood that; still can modify to the invention or equivalent replacement; in a word, all do not depart from technical scheme and the improvement thereof of the spirit and scope of the invention, and it all should be encompassed in the middle of the protection domain of the invention patent.
Claims (9)
1. a rule-based electric network failure diagnosis intelligent system, it is characterized in that, comprise the real-time data acquisition module, data sink, pretreatment module and the working data base that connect successively, also comprise knowledge base, inference machine and instruction generator, described working data base, knowledge base are connected between two with inference machine, data sink is sent to after the real time data information of described real-time data acquisition module acquires electrical network, described data sink carries out format by pretreatment module again after carrying out rationality checking and decoding process and information fusion classification processes and is stored to working data base, reasoning checking request is sent by inference machine to knowledge base after described working data base sends instruction to inference machine, described knowledge base obtains the data in working data base and carries out Data Matching based on electrical network CIM according to the knowledge rule in the knowledge base set up, rational analysis is carried out according to data in working data base and system state and knowledge in knowledge base according to reasoning algorithm by inference machine, the order of the rational analysis result generating standard of inference machine exports by described instruction generator.
2. rule-based electric network failure diagnosis intelligent system according to claim 1, it is characterized in that, described knowledge base comprises knowledge base formula area and knowledge base model district, described inference machine comprises interconnective knowledge editor and rational analysis device, described knowledge base formula area is all connected with working data base with knowledge editor, described knowledge base formula area is connected with rational analysis device with knowledge editor respectively with knowledge base model district, and described rational analysis device and instruction maker is connected; Described working data base sends instruction to knowledge editor, send reasoning by knowledge editor to knowledge base formula area and verify request, electrical network CIM according to the knowledge rule in the knowledge base set up and in conjunction with knowledge base model district after described knowledge base formula area obtains the data in working data base carries out Data Matching, and described rational analysis device carries out rational analysis according to reasoning algorithm.
3. rule-based electric network failure diagnosis intelligent system according to claim 2, it is characterized in that, described knowledge base also comprises knowledge base prototype district and knowledge base experience district, described inference machine comprises the experience accumulation device be connected with rational analysis device with knowledge editor respectively, described knowledge base prototype district is connected with rational analysis device with knowledge editor respectively, and described knowledge base experience district is connected with experience accumulation device; Decision-making prototype is provided with in described knowledge base prototype district, described decision-making prototype comprises load prediction prototype, fault diagnosis prototype and system state and analyzes prototype, described experience accumulation device by the data of rational analysis device in rational analysis process according to knowledge rule stored in knowledge base experience district, described knowledge base experience district utilizes fuzzy clustering algorithm to carry out the extraction of cluster analysis and forecasting type knowledge to historical data for the feature of electrical network historical data.
4. according to the rule-based electric network failure diagnosis intelligent system one of claims 1 to 3 Suo Shu, it is characterized in that, also comprise visual LCD MODULE, transmitter and communication interface, described operational data certificate is all connected with visual LCD MODULE with instruction generator, described instruction generator is also connected with transmitter, and the standardization order of instruction generator is connected with extraneous execution module by communication interface by described transmitter.
5. according to the rule-based electric network failure diagnosis intelligent system one of claims 1 to 3 Suo Shu, it is characterized in that, described real-time data acquisition module utilizes the real time data information of extraneous sensor or the electrical network needed for the reasoning of monitoring device real-time acquisition system, described real-time data acquisition module adopts polling method to gather by the cycle to slow varying signal, adopts the collection of interruption method to fast changed signal.
6. according to the rule-based electric network failure diagnosis intelligent system one of claims 1 to 3 Suo Shu, it is characterized in that, rationality checking is carried out after the information of described data sink receiving real-time data acquisition module collection, and decoding process is carried out to digital quantity signal in data stream, data are delivered in pretreatment module by electrical network isolation gap; Described rationality checking comprises the integrality detecting data.
7. according to the rule-based electric network failure diagnosis intelligent system one of claims 1 to 3 Suo Shu, it is characterized in that, described pretreatment module formats the information received and information fusion sorts out process, described information fusion is sorted out process and is comprised information fusion, reports to the police to merge and sort out and priority allocation, described pretreatment module according to priority adds buffer queue again after information fusion sorts out process, enters working data base.
8. the rule-based electric network failure diagnosis intelligent system according to Claims 2 or 3, is characterized in that, described rational analysis device is supported data-oriented and goal-oriented inference mode and adopted Forecast reasoning algorithm and related reasoning algorithm to carry out rational analysis.
9. rule-based electric network failure diagnosis intelligent system according to claim 3, it is characterized in that, described knowledge base experience district first adopts the Frequent Itemsets Mining Algorithm based on class set to carry out the data mining of frequent item set correlation rule for the feature of electrical network historical data, reject and the incoherent attribute of decision information, then utilize fuzzy clustering algorithm to carry out the extraction of cluster analysis and forecasting type knowledge to historical data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510022964.0A CN104679828A (en) | 2015-01-19 | 2015-01-19 | Rules-based intelligent system for grid fault diagnosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510022964.0A CN104679828A (en) | 2015-01-19 | 2015-01-19 | Rules-based intelligent system for grid fault diagnosis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104679828A true CN104679828A (en) | 2015-06-03 |
Family
ID=53314870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510022964.0A Pending CN104679828A (en) | 2015-01-19 | 2015-01-19 | Rules-based intelligent system for grid fault diagnosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104679828A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117662A (en) * | 2015-09-17 | 2015-12-02 | 国网北京市电力公司 | Power distribution network data exception processing method and device |
| CN105372557A (en) * | 2015-12-03 | 2016-03-02 | 国家电网公司 | Power grid resource fault diagnosis method based on association rules |
| CN105389460A (en) * | 2015-10-19 | 2016-03-09 | 苏华巍 | Traditional Chinese medicine habitus screening expert system and control method thereof |
| CN105528671A (en) * | 2015-11-30 | 2016-04-27 | 武汉大学 | Power grid multidimensional sensing and safety assessment system and method on the basis of big data |
| CN105527597A (en) * | 2015-11-28 | 2016-04-27 | 广西电网有限责任公司电力科学研究院 | Fault diagnosis processing system of distribution transform monitoring terminal and diagnosis method of system |
| CN105703258A (en) * | 2016-03-21 | 2016-06-22 | 广东电网有限责任公司东莞供电局 | Action state monitoring system of gas insulated switchgear (GIS) and application method of action state monitoring system |
| CN106199494A (en) * | 2016-07-25 | 2016-12-07 | 国网上海市电力公司 | A kind of intelligent diagnosis system based on metering device fault |
| CN106253272A (en) * | 2016-08-24 | 2016-12-21 | 国网山东省电力公司滨州供电公司 | A kind of power dispatch data network fault quick examination device |
| CN107169618A (en) * | 2017-03-23 | 2017-09-15 | 北京国电通网络技术有限公司 | A kind of power communication security risk assessment system |
| CN107862459A (en) * | 2017-11-10 | 2018-03-30 | 国网浙江省电力公司电力科学研究院 | Metering equipment state evaluation method and system based on big data |
| CN107966942A (en) * | 2017-06-18 | 2018-04-27 | 广东金宝力化工科技装备股份有限公司 | A kind of equipment fault forecasting system in knowledge based storehouse |
| CN108319240A (en) * | 2018-01-24 | 2018-07-24 | 中国电力科学研究院有限公司 | A kind of method and system of the application of job-oriented terminal at the scene acquisition O＆M knowledge base |
| CN108763377A (en) * | 2018-05-18 | 2018-11-06 | 郑州轻工业学院 | Multi-source telemetering big data feature extraction preprocess method is diagnosed based on satellite failure |
| CN109558418A (en) * | 2018-12-03 | 2019-04-02 | 上海熙菱信息技术有限公司 | A kind of method of automatic identification information |
| CN109636139A (en) * | 2018-11-26 | 2019-04-16 | 华南理工大学 | A kind of smart machine method for diagnosing faults based on semantic reasoning |
| CN109633370A (en) * | 2018-12-08 | 2019-04-16 | 国网山东省电力公司德州供电公司 | A kind of electric network failure diagnosis method based on fault message coding and fusion method |
| CN109697210A (en) * | 2018-12-26 | 2019-04-30 | 天津瑞源电气有限公司 | A kind of Wind turbines relevant fault inline diagnosis method |
| CN109710239A (en) * | 2018-12-29 | 2019-05-03 | 北京航天数据股份有限公司 | Industry pattern generation method and device, digital asset processing method and electronic equipment |
| CN109977689A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团广东有限公司 | A kind of Method of Database Secure Audit method, apparatus and electronic equipment |
| CN110119446A (en) * | 2018-02-05 | 2019-08-13 | 埃森哲环球解决方案有限公司 | Interpretable artificial intelligence |
| CN110297207A (en) * | 2019-07-08 | 2019-10-01 | 国网上海市电力公司 | Method for diagnosing faults, system and the electronic device of intelligent electric meter |
| CN110489620A (en) * | 2019-06-24 | 2019-11-22 | 厦门美域中央信息科技有限公司 | A kind of information technology expert's system based on artificial intelligence |
| CN111283474A (en) * | 2020-03-06 | 2020-06-16 | 河北凯通信息技术服务有限公司 | Numerical control automation equipment fault detection system based on big data |
| CN111404770A (en) * | 2020-02-29 | 2020-07-10 | 华为技术有限公司 | Network device, data processing method, device, system and readable storage medium |
| CN111639921A (en) * | 2020-06-11 | 2020-09-08 | 广东电网有限责任公司 | Intelligent equipment fault judgment and auxiliary disposal method based on expert system |
| CN111784537A (en) * | 2020-06-30 | 2020-10-16 | 国网信息通信产业集团有限公司 | Power distribution network state parameter monitoring method and device and electronic equipment |
| CN112132355A (en) * | 2020-09-28 | 2020-12-25 | 苏州优炫智能科技有限公司 | Thermal industry management system and method, electronic device and readable storage medium |
| CN112399466A (en) * | 2020-11-12 | 2021-02-23 | 国网江苏省电力有限公司信息通信分公司 | Method for analyzing communication rule defects based on domain rule base |
| CN112861421A (en) * | 2021-01-08 | 2021-05-28 | 陕西比瑞控制技术设备有限公司 | Intelligent analysis early warning system and method for power equipment |
| CN113064934A (en) * | 2021-03-26 | 2021-07-02 | 安徽继远软件有限公司 | Fault association rule mining method and system for sensing layer of power sensor network |
| CN113312271A (en) * | 2021-06-28 | 2021-08-27 | 四创电子股份有限公司 | Radio frequency assembly automatic test and diagnosis platform based on big data |
| CN113341874A (en) * | 2021-06-07 | 2021-09-03 | 大连理工大学 | Turning parameter automatic loading method based on hybrid reasoning |
| WO2021232567A1 (en) * | 2020-05-20 | 2021-11-25 | 江苏南工科技集团有限公司 | Ai technology-based smart operation and maintenance knowledge analysis method |
| CN113765100A (en) * | 2021-09-10 | 2021-12-07 | 国网上海市电力公司 | Power grid fault processing system and method |
| CN115329774A (en) * | 2022-10-14 | 2022-11-11 | 中国建筑科学研究院有限公司 | Intelligent building fault diagnosis rule generation method and device based on semantic matching |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05150988A (en) * | 1991-11-26 | 1993-06-18 | Kawasaki Steel Corp | Inference device |
| CN101576869A (en) * | 2009-05-31 | 2009-11-11 | 北京富邦科讯信息咨询有限公司 | Intelligent expert consulting system based on backboard model and method |
| CN102184209A (en) * | 2011-04-29 | 2011-09-14 | 中国电力科学研究院 | Simulation data accessing method based on power grid CIM (Common Information Model) interface |
| CN103106565A (en) * | 2012-10-22 | 2013-05-15 | 山东电力集团公司青岛供电公司 | Power grid information real-time display method and device which are based on geographic information system (GIS) and supervisory control and data acquisition (SCADA) |
| CN103440552A (en) * | 2013-08-27 | 2013-12-11 | 广东电网公司 | Grid safety production method based on safety production professional knowledge base |
| CN103633739A (en) * | 2013-11-28 | 2014-03-12 | 中国科学院广州能源研究所 | Microgrid energy management system and method |
-
2015
- 2015-01-19 CN CN201510022964.0A patent/CN104679828A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05150988A (en) * | 1991-11-26 | 1993-06-18 | Kawasaki Steel Corp | Inference device |
| CN101576869A (en) * | 2009-05-31 | 2009-11-11 | 北京富邦科讯信息咨询有限公司 | Intelligent expert consulting system based on backboard model and method |
| CN102184209A (en) * | 2011-04-29 | 2011-09-14 | 中国电力科学研究院 | Simulation data accessing method based on power grid CIM (Common Information Model) interface |
| CN103106565A (en) * | 2012-10-22 | 2013-05-15 | 山东电力集团公司青岛供电公司 | Power grid information real-time display method and device which are based on geographic information system (GIS) and supervisory control and data acquisition (SCADA) |
| CN103440552A (en) * | 2013-08-27 | 2013-12-11 | 广东电网公司 | Grid safety production method based on safety production professional knowledge base |
| CN103633739A (en) * | 2013-11-28 | 2014-03-12 | 中国科学院广州能源研究所 | Microgrid energy management system and method |
Non-Patent Citations (2)
| Title |
|---|
| 刘守明等: "基于知识库的电力变压器故障诊断专家系统", 《计算机测量与控制》 * |
| 季永程: "基于模糊识别的电网故障诊断专家系统的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117662A (en) * | 2015-09-17 | 2015-12-02 | 国网北京市电力公司 | Power distribution network data exception processing method and device |
| CN105389460B (en) * | 2015-10-19 | 2018-09-11 | 苏华巍 | Tcm constitution screens expert system and its control method |
| CN105389460A (en) * | 2015-10-19 | 2016-03-09 | 苏华巍 | Traditional Chinese medicine habitus screening expert system and control method thereof |
| CN105527597A (en) * | 2015-11-28 | 2016-04-27 | 广西电网有限责任公司电力科学研究院 | Fault diagnosis processing system of distribution transform monitoring terminal and diagnosis method of system |
| CN105528671A (en) * | 2015-11-30 | 2016-04-27 | 武汉大学 | Power grid multidimensional sensing and safety assessment system and method on the basis of big data |
| CN105528671B (en) * | 2015-11-30 | 2019-10-11 | 武汉大学 | A kind of power grid Multidimensional Awareness based on big data and safety estimation system and method |
| CN105372557A (en) * | 2015-12-03 | 2016-03-02 | 国家电网公司 | Power grid resource fault diagnosis method based on association rules |
| CN105703258A (en) * | 2016-03-21 | 2016-06-22 | 广东电网有限责任公司东莞供电局 | Action state monitoring system of gas insulated switchgear (GIS) and application method of action state monitoring system |
| CN106199494A (en) * | 2016-07-25 | 2016-12-07 | 国网上海市电力公司 | A kind of intelligent diagnosis system based on metering device fault |
| CN106253272A (en) * | 2016-08-24 | 2016-12-21 | 国网山东省电力公司滨州供电公司 | A kind of power dispatch data network fault quick examination device |
| CN107169618A (en) * | 2017-03-23 | 2017-09-15 | 北京国电通网络技术有限公司 | A kind of power communication security risk assessment system |
| CN107966942A (en) * | 2017-06-18 | 2018-04-27 | 广东金宝力化工科技装备股份有限公司 | A kind of equipment fault forecasting system in knowledge based storehouse |
| CN107862459A (en) * | 2017-11-10 | 2018-03-30 | 国网浙江省电力公司电力科学研究院 | Metering equipment state evaluation method and system based on big data |
| CN107862459B (en) * | 2017-11-10 | 2020-12-18 | 国网浙江省电力公司电力科学研究院 | Metering equipment state evaluation method and system based on big data |
| CN109977689A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团广东有限公司 | A kind of Method of Database Secure Audit method, apparatus and electronic equipment |
| CN109977689B (en) * | 2017-12-28 | 2020-12-04 | 中国移动通信集团广东有限公司 | Database security audit method and device and electronic equipment |
| CN108319240A (en) * | 2018-01-24 | 2018-07-24 | 中国电力科学研究院有限公司 | A kind of method and system of the application of job-oriented terminal at the scene acquisition O＆M knowledge base |
| CN110119446A (en) * | 2018-02-05 | 2019-08-13 | 埃森哲环球解决方案有限公司 | Interpretable artificial intelligence |
| CN108763377B (en) * | 2018-05-18 | 2021-08-13 | 郑州轻工业学院 | Multi-source telemetering big data feature extraction preprocessing method based on satellite fault diagnosis |
| CN108763377A (en) * | 2018-05-18 | 2018-11-06 | 郑州轻工业学院 | Multi-source telemetering big data feature extraction preprocess method is diagnosed based on satellite failure |
| CN109636139A (en) * | 2018-11-26 | 2019-04-16 | 华南理工大学 | A kind of smart machine method for diagnosing faults based on semantic reasoning |
| CN109558418A (en) * | 2018-12-03 | 2019-04-02 | 上海熙菱信息技术有限公司 | A kind of method of automatic identification information |
| CN109558418B (en) * | 2018-12-03 | 2023-04-07 | 上海熙菱信息技术有限公司 | Method for automatically identifying information |
| CN109633370A (en) * | 2018-12-08 | 2019-04-16 | 国网山东省电力公司德州供电公司 | A kind of electric network failure diagnosis method based on fault message coding and fusion method |
| CN109697210B (en) * | 2018-12-26 | 2023-09-05 | 天津瑞源电气有限公司 | Online diagnosis method for wind turbine generator set associated faults |
| CN109697210A (en) * | 2018-12-26 | 2019-04-30 | 天津瑞源电气有限公司 | A kind of Wind turbines relevant fault inline diagnosis method |
| CN109710239A (en) * | 2018-12-29 | 2019-05-03 | 北京航天数据股份有限公司 | Industry pattern generation method and device, digital asset processing method and electronic equipment |
| CN110489620A (en) * | 2019-06-24 | 2019-11-22 | 厦门美域中央信息科技有限公司 | A kind of information technology expert's system based on artificial intelligence |
| CN110297207A (en) * | 2019-07-08 | 2019-10-01 | 国网上海市电力公司 | Method for diagnosing faults, system and the electronic device of intelligent electric meter |
| CN111404770A (en) * | 2020-02-29 | 2020-07-10 | 华为技术有限公司 | Network device, data processing method, device, system and readable storage medium |
| EP4096166A4 (en) * | 2020-02-29 | 2023-07-26 | Huawei Technologies Co., Ltd. | Network device, data processing method, apparatus and system, and readable storage medium |
| CN111283474A (en) * | 2020-03-06 | 2020-06-16 | 河北凯通信息技术服务有限公司 | Numerical control automation equipment fault detection system based on big data |
| WO2021232567A1 (en) * | 2020-05-20 | 2021-11-25 | 江苏南工科技集团有限公司 | Ai technology-based smart operation and maintenance knowledge analysis method |
| CN111639921A (en) * | 2020-06-11 | 2020-09-08 | 广东电网有限责任公司 | Intelligent equipment fault judgment and auxiliary disposal method based on expert system |
| CN111639921B (en) * | 2020-06-11 | 2023-02-17 | 广东电网有限责任公司 | Intelligent equipment fault judgment and auxiliary disposal method based on expert system |
| CN111784537A (en) * | 2020-06-30 | 2020-10-16 | 国网信息通信产业集团有限公司 | Power distribution network state parameter monitoring method and device and electronic equipment |
| CN112132355A (en) * | 2020-09-28 | 2020-12-25 | 苏州优炫智能科技有限公司 | Thermal industry management system and method, electronic device and readable storage medium |
| CN112399466A (en) * | 2020-11-12 | 2021-02-23 | 国网江苏省电力有限公司信息通信分公司 | Method for analyzing communication rule defects based on domain rule base |
| CN112399466B (en) * | 2020-11-12 | 2024-02-09 | 国网江苏省电力有限公司信息通信分公司 | Communication rule defect analysis method based on domain rule base |
| CN112861421A (en) * | 2021-01-08 | 2021-05-28 | 陕西比瑞控制技术设备有限公司 | Intelligent analysis early warning system and method for power equipment |
| CN113064934A (en) * | 2021-03-26 | 2021-07-02 | 安徽继远软件有限公司 | Fault association rule mining method and system for sensing layer of power sensor network |
| CN113064934B (en) * | 2021-03-26 | 2023-12-08 | 安徽继远软件有限公司 | Power sensing network perception layer fault association rule mining method and system |
| CN113341874A (en) * | 2021-06-07 | 2021-09-03 | 大连理工大学 | Turning parameter automatic loading method based on hybrid reasoning |
| CN113312271A (en) * | 2021-06-28 | 2021-08-27 | 四创电子股份有限公司 | Radio frequency assembly automatic test and diagnosis platform based on big data |
| CN113765100A (en) * | 2021-09-10 | 2021-12-07 | 国网上海市电力公司 | Power grid fault processing system and method |
| CN115329774A (en) * | 2022-10-14 | 2022-11-11 | 中国建筑科学研究院有限公司 | Intelligent building fault diagnosis rule generation method and device based on semantic matching |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104679828A (en) | Rules-based intelligent system for grid fault diagnosis | |
| CN204883710U (en) | Power system fault diagnoses intelligent system based on rule | |
| CN102130783B (en) | Intelligent alarm monitoring method of neural network | |
| Liu et al. | A knowledge graph-based data representation approach for IIoT-enabled cognitive manufacturing | |
| CN102765643B (en) | Elevator fault diagnosis and early-warning method based on data drive | |
| CN103902816A (en) | Electrification detection data processing method based on data mining technology | |
| CN102439584A (en) | Method of establishing a process decision support system | |
| CN109255523A (en) | Analysis indexes computing platform based on KKS coding rule and big data framework | |
| CN104616092A (en) | Distributed log analysis based distributed mode handling method | |
| CN116485576A (en) | Intelligent manufacturing management platform for brain data with known source in aviation manufacturing industry | |
| CN103985022A (en) | Intelligent substation secondary equipment operation and maintenance decision support system and data analysis method | |
| CN115293507A (en) | Situation knowledge graph construction method and system for power grid dispatching operation management | |
| CN106776903A (en) | A kind of big data shared system and method that auxiliary tone is sought suitable for intelligent grid | |
| US20230229124A1 (en) | Operation control system and a control method for a gas-steam combined cycle generator unit | |
| CN115170344A (en) | Intelligent processing method and device, medium and equipment for operation events of regulation and control system | |
| CN111090643A (en) | Mass electricity consumption data mining method based on data analysis system | |
| CN116882978A (en) | Deep sea submersible operation and maintenance support platform based on product information frame | |
| US20220277119A1 (en) | A System and Method for Generating a Holistic Digital Twin | |
| CN116771576A (en) | Comprehensive fault diagnosis method for hydroelectric generating set | |
| Zhang et al. | Distributed Architecture of Power Grid Asset Management and Future Research Directions | |
| CN115222058A (en) | Method and device for establishing operating state analysis model of regulation and control system, medium and equipment | |
| CN114819925A (en) | Industrial Internet of things based on event sequence analysis and prediction and control method thereof | |
| CN113469343A (en) | Industrial time sequence data processing method and system | |
| CN114139781A (en) | Method and system for predicting operation trend of power system | |
| Kundacina et al. | Supporting future electrical utilities: Using deep learning methods in ems and dms algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150603 |
|
| WD01 | Invention patent application deemed withdrawn after publication |