CN107992959A - A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology - Google Patents
A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology Download PDFInfo
- Publication number
- CN107992959A CN107992959A CN201710283241.5A CN201710283241A CN107992959A CN 107992959 A CN107992959 A CN 107992959A CN 201710283241 A CN201710283241 A CN 201710283241A CN 107992959 A CN107992959 A CN 107992959A
- Authority
- CN
- China
- Prior art keywords
- data
- electric power
- neural network
- visualization
- parameter
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000005516 engineering process Methods 0.000 title claims abstract description 17
- 238000013079 data visualisation Methods 0.000 title claims abstract description 11
- 238000007418 data mining Methods 0.000 claims abstract description 17
- 238000012800 visualization Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000007935 neutral effect Effects 0.000 claims description 11
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 claims description 2
- 239000007795 chemical reaction product Substances 0.000 claims description 2
- 230000007423 decrease Effects 0.000 claims description 2
- 238000007667 floating Methods 0.000 claims description 2
- 210000002364 input neuron Anatomy 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 claims description 2
- 238000007639 printing Methods 0.000 claims description 2
- 238000007794 visualization technique Methods 0.000 claims description 2
- 238000009412 basement excavation Methods 0.000 claims 1
- 230000005611 electricity Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000007257 malfunction Effects 0.000 description 2
- 238000012106 screening analysis Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology, including an electric power large database concept, a data mining pretreatment and visualization processing module, a visualization BP neural network data-mining module, result output module composition, it is this that failure predication is realized with graphical Neural Network Data digging technology, reduce electric power big data and use difficulty, improve service efficiency.
Description
Technical field
It is especially a kind of to be based on the big number of electric power the present invention relates to a kind of power failure Forecasting Methodology based on electric power big data
According to the power failure Forecasting Methodology of visualization BP neural network data mining technology.
Background technology
During power generation, power transmission and distribution, mass data can be produced, becomes electric power big data, these data packets contain
The various information of electric system, it is all particularly significant to Operation of Electric Systems, scheduling, maintenance, fault diagnosis, prediction.At present, electric power
Collection, analysis and the use of big data are extremely limited, the stage analyzed and processed greatly all in artificial treatment or with simple software, consumption
Take a large amount of manpower and materials, use is cumbersome, and efficiency is very low, effect unobvious.Meanwhile the harm that power failure is brought is very huge
Greatly, power failure Predicting Technique very imperfection.Electric power big data be conveniently used for power failure prediction to theory analysis with
Practical application is all of great significance.
The content of the invention
The present invention seeks to build a kind of electric power based on electric power big data visualization BP neural network data mining technology
Failure prediction method, solves the problems, such as that electric power big data utilization ratio is low, power failure prediction is difficult.
Technical solution is used by the present invention solves the technical problem：
A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology, including one
Electric power large database concept, a data mining pretreatment and visualization processing module, a visualization BP neural network data-mining module,
One result output module forms.
It is preferred that an electric power large database concept, is used for：Electric power data is provided, is the basis for carrying out data mining analysis.Specific bag
Two aspect data are included, are on the one hand electrical nature parameters, including project, equipment, assets, goods and materials, personnel, customer information；It is another
Aspect is operation power data, including operating parameter over the years, including power, voltage, electric current, power angle etc. change over time number
According to, and break down in operational process and fault type data.
It is preferred that a data mining pretreatment and visualization processing module, are used for：
Data type conversion is carried out, electrical nature parameter is into line label, operation power data conversion into floating number；
Carry out data cleansing, default value processing and data integration, hence it is evident that mistakes and omissions data are weighted average completion；
Carry out correlation significance parameter setting；
The correlation analysis of historical data and different types of n kinds failure is carried out, calculates correlation significance；
According to down time distance, filter out the electrical nature parameter more than significance (implying for 0.05)
And operating parameter m, obtain the parameter that n kinds fault type exceedes correlation significance, composition of vector X:(x1,x2…,
xm).The nearlyer data dependence of distance is stronger, and the correlation time maximum for taking this group of parameter is boundary, takes out P groups (X1,T1,S1；X2,
T2,S2；…；Xp,Tp,Sp) it is used as sample data, Xi, i=1,2 ... p are the parameter group filtered out, Ti, i=1,2 ... p, for correspondence
Rate of breakdown, take the value between 0 to 1, Si, i=1,2 ... p are fault type, take 1 to the value between n；
The data of electrical nature parameter and operating parameter report based on 3D visualization techniques are carried out to show；
It is preferred that a visualization BP neural network data-mining module, is used for：Neural Network Data is provided with form of icons to dig
Module is dug, including input parameter number, that is, first layer neuron number is set, the neutral net number of plies (implying for 2 layers) is set, in
Interbed neuron number (implicit with input neuron number equal), output layer are two outputs, respectively fault rate,
Failure occurrence type；
The characteristic function of each layer neuron is set；
It is X the strong parameter composition input of failure dependency, selects the P groups of its different time to input and exported with corresponding failure
(X1,T1,S1；X2,T2,S2；…；Xp,Tp,Sp) it is used as sample, desired output T1,S1；T2,S2；…；Tp,Sp, to neutral net
Decline learning algorithm according to BP gradients to be trained.
It is preferred that a result output module, is used for：Neural Network Data excavate intermediate result and end product report form or
Person's graphic form exports；With storage, setting of printing and export；When difference is small between neutral net reality output and desired output
(implied in step-up error for 0.1%), neural metwork training terminates, the strong parameter X of input fault correlation:(x1,x2... x)
Current live value inputs neutral net, obtains probability and the type that may be broken down.
The present invention beneficial outcomes be：
A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology is provided, is adopted
With can correlation screening technique, realize with the strong parameter of failure dependency, by easily building visualization Neural Network Data
Digging system, passes through the strong P group supplemental characteristics (X of conventional historical failure correlation1,T1,S1；X2,T2,S2；…；Xp,Tp,Sp) make
For sample input and desired output, study is trained to neutral net.After the completion of study, event is realized by input of current data
Hinder the prediction of type and incidence.
It is an advantage of the invention that：Failure predication is realized with graphical Neural Network Data digging technology, reduces the big number of electric power
According to using difficulty, service efficiency is improved.
Brief description of the drawings
Fig. 1 is data screening and correlation analysis schematic diagram
Fig. 2 is that visualization Neural Network Data excavates training process schematic diagram
Fig. 3 is prediction process schematic
Embodiment
Referring to the drawings 1, Fig. 2, Fig. 3：
It is clearer to discuss the present invention, with reference to the data screening and correlation analysis schematic diagram 1 and tool of the present invention
Body embodiment Fig. 2, Fig. 3 is further described, it is necessary to illustrate, instantiation described herein is only used for explaining this hair
It is bright, do not limit the present invention.
In Fig. 1, using the data mining pretreatment and visualization processing module 3 to the electric power big data 1 with it is described
Conventional down time, type 2, such as it is 1,2,3 that line fault, circuit breaker failure, transformer fault are numbered respectively, is consulted
Such fault time occurred in the past, carries out a period of time progress data dependence inspection from the near to the remote in time of failure,
It is 0.05 to set correlation significance, wherein being there is failure numbering 1 of the time point more than 0.05 to have a related ginseng
Number, failure numbering 2 have b relevant parameter, and failure numbering 3 has c relevant parameter, and all a+b+c=m parameters are denoted as Xm,；This
Parameter carries out visualization output by the correlation significance output module 4, and output can be form or figure shape
Formula；
In Fig. 2, in Xm, taking the relevant maximum duration parameter of all parameters to be limited for the time, take and temporally take P groups, with institute
Corresponding fault type 1,2,3 and corresponding probability of malfunction, corresponding probability of malfunction are 1, other fault types are zero, form institute
Desired output 6 is stated, as the sample input data 5, inputs the graphical function module 7 of the BP neural network data mining,
The input number is carried out to the graphical function module 7 of the BP neural network data mining sets the 8, number of plies to set 9, BP nerves
E-learning rule setting 10, inputs the sample input data 5, obtains output and is compared with the desired output 6, is pressed
The connection weight between neutral net is changed according to BP neural network learning rules；By repetition learning, until reality output and institute
The difference of desired output 6 is stated less than untill step-up error such as 0.1%；
In Fig. 3, using the real time data of selected parameter as the real time input data 12, input the training and complete god
Through network 11, the prediction output result 13 is obtained, by obtaining the prediction output analysis of result 13 by the class that breaks down
Type and probability of happening.
It can be seen from the above that the present invention can efficiently use electric power big data, and pass through Neural Network Data by visual pattern
Digging technology is predicted typical fault.
Content described in this specification embodiment is only enumerating to the way of realization of inventive concept, protection of the invention
The concrete form for being not construed as being only limitted to embodiment and being stated of scope, protection scope of the present invention is also and in this area skill
Art personnel conceive according to the present invention it is conceivable that equivalent technologies mean.
Claims (5)
1. a kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology, including an electricity
Power large database concept, a data mining pretreatment and visualization processing module, a visualization BP neural network data-mining module, one
As a result output module forms.
A kind of 2. electric power event based on electric power big data visualization Neural Network Data digging technology according to claim 1
Hinder Forecasting Methodology, it is characterised in that the electric power large database concept, is used for：Electric power data is provided, is to carry out data mining analysis
Basis.Two aspect data are specifically included, are on the one hand electrical nature parameters, including project, equipment, assets, goods and materials, personnel, visitor
Family information；On the other hand be operation power data, including operating parameter over the years, including power, voltage, electric current, power angle etc. with
Break down in time-variable data, and operational process and fault type data.
A kind of 3. electric power event based on electric power big data visualization Neural Network Data digging technology according to claim 1
Hinder Forecasting Methodology, it is characterised in that the data mining pretreatment and visualization processing module, are used for：
Data type conversion is carried out, electrical nature parameter is into line label, operation power data conversion into floating number；
Carry out data cleansing, default value processing and data integration, hence it is evident that mistakes and omissions data are weighted average completion；
Carry out correlation significance parameter setting；
The correlation analysis of historical data and different types of n kinds failure is carried out, calculates correlation significance；
According to down time distance, filter out electrical nature parameter and fortune more than significance (implying for 0.05)
Row parameter m, obtains the parameter that n kinds fault type exceedes correlation significance, composition of vector X:(x1,x2…,xm).Away from
Stronger from nearlyer data dependence, the correlation time maximum for taking this group of parameter is boundary, takes out P groups (X1,T1,S1；X2,T2,
S2；…；Xp,Tp,Sp) it is used as sample data, Xi, i=1,2 ... p are the parameter group filtered out, Ti, i=1,2 ... p, are corresponding
Rate of breakdown, takes the value between 0 to 1, Si, i=1,2 ... p are fault type, take 1 to the value between n；
The data of electrical nature parameter and operating parameter report based on 3D visualization techniques are carried out to show.
A kind of 4. electric power event based on electric power big data visualization Neural Network Data digging technology according to claim 1
Hinder Forecasting Methodology, it is characterised in that the visualization BP neural network data-mining module, is used for：Nerve is provided with form of icons
Network data excavation module, including input parameter number, that is, first layer neuron number is set, set the neutral net number of plies (implicit
For 2 layers), intermediate layer neuron number (implicit equal with input neuron number), output layer is two outputs, is respectively failure
Probability of happening, failure occurrence type；
The characteristic function of each layer neuron is set；
It is X the strong parameter composition input of failure dependency, selects the P groups of its different time to input and export (X with corresponding failure1,
T1,S1；X2,T2,S2；…；Xp,Tp,Sp) it is used as sample, desired output T1,S1；T2,S2；…；Tp,Sp, to neutral net according to
BP gradients decline learning algorithm and are trained.
A kind of 5. electric power event based on electric power big data visualization Neural Network Data digging technology according to claim 1
Hinder Forecasting Methodology, it is characterised in that the result output module, is used for：
Neural Network Data excavates intermediate result and end product report form or graphic form output；
With storage, setting of printing and export；
When difference is less than step-up error (implying for 0.1%), neutral net instruction between neutral net reality output and desired output
White silk terminates, the strong parameter X of input fault correlation:(x1,x2... current live value input neutral net x), obtains possibility
The probability and type of failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710283241.5A CN107992959A (en) | 2017-04-26 | 2017-04-26 | A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710283241.5A CN107992959A (en) | 2017-04-26 | 2017-04-26 | A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107992959A true CN107992959A (en) | 2018-05-04 |
Family
ID=62029583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710283241.5A Pending CN107992959A (en) | 2017-04-26 | 2017-04-26 | A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107992959A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898249A (en) * | 2018-06-28 | 2018-11-27 | 鹿寨知航科技信息服务有限公司 | A kind of electric network fault prediction technique |
| CN109768625A (en) * | 2019-03-29 | 2019-05-17 | 国网山东省电力公司费县供电公司 | A kind of electric system overhaul management terminal and method |
| CN110222452A (en) * | 2019-06-14 | 2019-09-10 | 国网上海市电力公司 | Oil-immersed transformer failure based on big data association mining deduces visualization system |
| CN110955746A (en) * | 2019-10-22 | 2020-04-03 | 中国科学院信息工程研究所 | Electromagnetic data collecting and processing device and method |
| CN112863007A (en) * | 2021-03-01 | 2021-05-28 | 中车株洲电力机车有限公司 | Fault early warning model of traction converter, modeling method, early warning method and early warning system |
| CN113159517A (en) * | 2021-03-24 | 2021-07-23 | 国网浙江省电力有限公司宁波供电公司 | Three-dimensional visual power grid operation data analysis system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462846A (en) * | 2014-12-22 | 2015-03-25 | 山东鲁能软件技术有限公司 | Intelligent device failure diagnosis method based on support vector machine |
| CN104732276A (en) * | 2015-03-18 | 2015-06-24 | 国家电网公司 | On-line diagnosing method for faults of metering production facility |
| CN105550700A (en) * | 2015-12-08 | 2016-05-04 | 国网山东省电力公司电力科学研究院 | Time series data cleaning method based on correlation analysis and principal component analysis |
| CN105548744A (en) * | 2015-12-04 | 2016-05-04 | 国网技术学院 | Substation equipment fault identification method based on operation-detection large data and system thereof |
| CN106123970A (en) * | 2016-09-07 | 2016-11-16 | 浙江群力电气有限公司 | A kind of underground substation status monitoring and analysis method for reliability and system |
| CN106483947A (en) * | 2016-09-21 | 2017-03-08 | 国网江苏省电力公司南通供电公司 | Distribution Running State assessment based on big data and method for early warning |
-
2017
- 2017-04-26 CN CN201710283241.5A patent/CN107992959A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462846A (en) * | 2014-12-22 | 2015-03-25 | 山东鲁能软件技术有限公司 | Intelligent device failure diagnosis method based on support vector machine |
| CN104732276A (en) * | 2015-03-18 | 2015-06-24 | 国家电网公司 | On-line diagnosing method for faults of metering production facility |
| CN105548744A (en) * | 2015-12-04 | 2016-05-04 | 国网技术学院 | Substation equipment fault identification method based on operation-detection large data and system thereof |
| CN105550700A (en) * | 2015-12-08 | 2016-05-04 | 国网山东省电力公司电力科学研究院 | Time series data cleaning method based on correlation analysis and principal component analysis |
| CN106123970A (en) * | 2016-09-07 | 2016-11-16 | 浙江群力电气有限公司 | A kind of underground substation status monitoring and analysis method for reliability and system |
| CN106483947A (en) * | 2016-09-21 | 2017-03-08 | 国网江苏省电力公司南通供电公司 | Distribution Running State assessment based on big data and method for early warning |
Non-Patent Citations (3)
| Title |
|---|
| 夏春艳: "《数据挖掘技术与应用》", 31 August 2014, 北京：冶金工业出版社 * |
| 孟海东 等: "《大数据挖掘技术与应用》", 31 December 2014, 北京：冶金工业出版社 * |
| 李志鹏: "基于大数据分析的输电线路管理系统及故障诊断研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898249A (en) * | 2018-06-28 | 2018-11-27 | 鹿寨知航科技信息服务有限公司 | A kind of electric network fault prediction technique |
| CN109768625A (en) * | 2019-03-29 | 2019-05-17 | 国网山东省电力公司费县供电公司 | A kind of electric system overhaul management terminal and method |
| CN110222452A (en) * | 2019-06-14 | 2019-09-10 | 国网上海市电力公司 | Oil-immersed transformer failure based on big data association mining deduces visualization system |
| CN110955746A (en) * | 2019-10-22 | 2020-04-03 | 中国科学院信息工程研究所 | Electromagnetic data collecting and processing device and method |
| CN110955746B (en) * | 2019-10-22 | 2022-03-22 | 中国科学院信息工程研究所 | Electromagnetic data collecting and processing device and method |
| CN112863007A (en) * | 2021-03-01 | 2021-05-28 | 中车株洲电力机车有限公司 | Fault early warning model of traction converter, modeling method, early warning method and early warning system |
| CN113159517A (en) * | 2021-03-24 | 2021-07-23 | 国网浙江省电力有限公司宁波供电公司 | Three-dimensional visual power grid operation data analysis system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107992959A (en) | A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology | |
| Mandal et al. | In search of suitable fuzzy membership function in prediction of time series data | |
| CN105095967B (en) | A kind of multi-modal neuromorphic network core | |
| CN106909933B (en) | A kind of stealing classification Forecasting Methodology of three stages various visual angles Fusion Features | |
| CN101729315B (en) | Network flow-predicting method and device based on wavelet package decomposition and fuzzy neural network | |
| CN105095965B (en) | The mixed communication method of artificial neural network and impulsive neural networks nerve | |
| CN105974265A (en) | SVM (support vector machine) classification technology-based power grid fault cause diagnosis method | |
| CN109444667A (en) | Power distribution network initial failure classification method and device based on convolutional neural networks | |
| CN107909206A (en) | A kind of PM2.5 Forecasting Methodologies based on deep structure Recognition with Recurrent Neural Network | |
| CN108320043A (en) | A kind of distribution network equipment state diagnosis prediction method based on electric power big data | |
| CN107391385B (en) | A kind of construction method of Generation of software test case technology | |
| CN107832219A (en) | The construction method of software fault prediction technology based on static analysis and neutral net | |
| CN104899664B (en) | A kind of drilling risk prediction technique based on Markov Chain and Bayesian network | |
| CN109061391B (en) | Power grid fault diagnosis method and system based on computer vision tidal current diagram | |
| CN101957889A (en) | Selective wear-based equipment optimal maintenance time prediction method | |
| CN108090606A (en) | Equipment fault finds method and system | |
| CN104732087A (en) | GIS-based neural-network cellular automaton infectious-disease transmission simulation analysis method | |
| CN109507527B (en) | Fault positioning method for power distribution network containing distributed power supply of SNP system based on synaptic plasticity | |
| CN110928187A (en) | Sewage treatment process fault monitoring method based on fuzzy width self-adaptive learning model | |
| CN111999591A (en) | Method for identifying abnormal state of primary equipment of power distribution network | |
| CN106526465A (en) | High-voltage circuit breaker fault intelligent diagnosis method based on improved fuzzy Petri network | |
| CN115965150A (en) | Power load prediction method based on weight distribution | |
| CN113887626A (en) | Method and device for generating portrait of power equipment | |
| CN105956252A (en) | Generative deep belief network-based multi-scale forecast modeling method for ultra-short-term wind speed | |
| Ni et al. | An improved attention-based bidirectional LSTM model for cyanobacterial bloom prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180504 |
|
| RJ01 | Rejection of invention patent application after publication |