CN110322135A - A kind of method for real-time monitoring and system of grid equipment safe operation state - Google Patents
A kind of method for real-time monitoring and system of grid equipment safe operation state Download PDFInfo
- Publication number
- CN110322135A CN110322135A CN201910563097.XA CN201910563097A CN110322135A CN 110322135 A CN110322135 A CN 110322135A CN 201910563097 A CN201910563097 A CN 201910563097A CN 110322135 A CN110322135 A CN 110322135A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- real
- training
- grid
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 85
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 238000010801 machine learning Methods 0.000 claims description 23
- 230000007547 defect Effects 0.000 claims description 18
- 238000012795 verification Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 9
- 230000005611 electricity Effects 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 7
- 238000012847 principal component analysis method Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 8
- 230000007812 deficiency Effects 0.000 abstract description 4
- 238000013210 evaluation model Methods 0.000 abstract 1
- 230000001737 promoting effect Effects 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 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
- 239000003990 capacitor Substances 0.000 description 1
- 210000001520 comb Anatomy 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000000518 rheometry Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the method for real-time monitoring and system of a kind of grid equipment safe operation state, the described method comprises the following steps: based on historical Device operation data training appraisal of equipment model；The relative evaluation of equipment room is calculated based on equipment operating data and appraisal of equipment model；Pushing equipment relativity is safely operated state evaluation result.The present invention forms the Real-Time Evaluation system of grid equipment by constructing multistage evaluation index, compensates for the low deficiency of fortune inspection state evaluation timeliness；The present invention is based on the historical experience that power system monitor personnel have, using SVM algorithm and construct real-time evaluation model, reduce monitoring personnel and manually determine the amount of labour of risk equipment, and improve the reliability of evaluation result, facilitates the safety operation level for promoting power grid.
Description
Technical field
The invention belongs to the monitoring technology fields of grid equipment safe condition, are related to substation, passway for transmitting electricity and power supply
Various primary equipments, secondary device and ancillary equipment in area equipment carry out Real-Time Evaluation more particularly to a kind of grid equipment
The method for real-time monitoring and system of safe operation state.
Background technique
With the iterative method of smart grid construction and the gradually expansion of power grid scale, monitor needs the power grid monitored to set
It is standby more and more, and it is completely dependent on the artificial monitoring method for determining equipment safety operation level and is increasingly not suitable with current electric grid
Construction, can not ensure electric power netting safe running, need in real time to assess equipment state thus, confirm that operation risk is higher and set
It is standby, convenient for carrying out emphasis monitoring to it, to ensure the safe operation of power grid.
The relatively broad substation equipment of current application is evaluated as fortune inspection equipment state evaluation, and the evaluation is mainly towards setting
Standby level is broadly divided into lean administrative evaluation, annual state evaluation and dynamic evaluation three categories.Wherein, lean management is commented
Valence is to transformer equipment examination, O&M, detection, maintenance, the anti-comprehensive inspection evaluation for arranging execution and fortune inspection to manage；Annual state is commented
Valence is that the transformer equipment state evaluation organized is concentrated to work every year according to grid equipment state evaluation directive/guide；Dynamic evaluation is
The evaluation that equipment important state is carried out after changing.Therefore, the evaluation of fortune inspection equipment state lacks equipment state and pacifies to power grid
The analysis of full operation trend.
Summary of the invention
To solve deficiency in the prior art, the present invention provides a kind of real time monitoring side of grid equipment safe operation state
Method and system are realized the real-time control to substation, passway for transmitting electricity and power supply area equipment safety state, and then are confirmed due to setting
The operation of power networks weak link that standby security risk may cause, it is horizontal to promote electric power netting safe running.
In order to achieve the above objectives, the present invention adopts the following technical scheme:
An aspect of of the present present invention, a kind of method for real-time monitoring of grid equipment safe operation state, comprising the following steps:
S1: based on historical Device operation data training appraisal of equipment model；
S2: the relative evaluation of equipment room is calculated based on equipment operating data and appraisal of equipment model.
The present invention further comprises following preferred embodiment:
Preferably, the method also includes S3: pushing equipment relativity is safely operated state evaluation result.
Preferably, based on historical Device operation data training appraisal of equipment model described in step S1, comprising the following steps:
S101: acquiring and handles historical Device operation data；
S102: the weight that the corresponding equipment scoring score combination expert of historical Device operation data that treated provides, it will
Historical Device operation data be labeled as equipment running status be it is outstanding, well, pass and alarm four class data sets, be denoted as Kn, n
=1,2,3,4；
S103: the data set is split into training dataset and predictive data set in proportion；
S104: off-line training appraisal of equipment model classifiers；
S105: off-line verification equipment current state.
Preferably, historical Device operation data is handled described in step S101, specifically: it will by PCA Principal Component Analysis Method
Various kinds of equipment operation data dimensionality reduction is simultaneously mapped to feature space.
Preferably, off-line training appraisal of equipment model classifiers described in step S104, comprising the following steps:
It is concentrated in training data, by K1As positive collection, K2、K3、K4As negative collection, K1、K2、K3、K4It is input to SVM instruction together
Practice and be trained in machine learning algorithm, obtains Optimal Separating Hyperplane f1(x)；
By K2As positive collection, K1、K3、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f2(x)；
By K3As positive collection, K1、K2、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f3(x)；
By K4As positive collection, K1、K2、K3As negative collection, K1、K2、K3、K4Be input to together SVM training machine learning algorithm into
Row training, obtains Optimal Separating Hyperplane f4(x)；
The Optimal Separating Hyperplane fm(x)=ωTX+b, m=1,2,3,4；Wherein, ωTFor the slope of Optimal Separating Hyperplane, X=
[x1,x2,…,x4], b is constant.
Preferably, off-line verification equipment current state described in step S105, specifically:
Calculate separately and in comparison prediction data set every class data to corresponding Optimal Separating Hyperplane f1(x)、f2(x)、f3
(x)、f4(x) Euclidean distance, the smallest Optimal Separating Hyperplane f of Euclidean distancem(x), the as current state of equipment.
Preferably, the relative evaluation of equipment room is calculated described in step S2 based on equipment operating data and appraisal of equipment model,
The following steps are included:
S201: acquisition needs to compare the equipment operating data of two equipment of relative status in real time；
S202: equipment operating data is inputted into trained appraisal of equipment model, obtains the current state f of equipmentm(x)；
S203: the current state of two equipment of the rate of exchange, if the current state f of two equipmentm(x) different, then rate of exchange fm(x)
State；If the current state f of two equipmentm(x) it is the same classification plane, then compares the current state f of two equipmentm(x)
Corresponding Euclidean distance, the close relativity safe operation state of Euclidean distance are preferable.
Preferably, the equipment includes substation, passway for transmitting electricity and power supply area equipment；
The equipment operating data includes equipment operational defect, equipment operating condition, the abnormal method of operation of equipment and sets
Standby service life redundancy；
The equipment operational defect is divided into critical, serious, general and nothing, for evaluating power equipment running state；
The equipment operating condition includes active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit and normal；
The abnormal method of operation of equipment includes maintenance, interval transformation, grid switching operation and normality；
The equipment life redundancy is the percentage of equipment remaining life, by machinery equipment periodic measurement, in real time
The measured data of analysis determine the state and the development trend in future of equipment.
Another aspect of the present invention, a kind of real-time monitoring system of grid equipment safe operation state, including training unit
And computing unit；
The training unit, for based on historical Device operation data training appraisal of equipment model；
The computing unit, for calculating the relative evaluation of equipment room based on equipment operating data and appraisal of equipment model.
Preferably, the system also includes push units, are safely operated state evaluation result for pushing equipment relativity.
Preferably, the training unit includes acquisition and processing unit, mark unit, split cells, off-line training unit
With off-line verification unit；
The acquisition and processing unit, for acquiring and handling historical Device operation data；
The mark unit, the power for providing the corresponding equipment scoring score combination expert of historical Device operation data
Weight, by historical Device operation data be labeled as equipment running status be it is outstanding, well, pass and alarm four class data sets, note
For Kn, n=1,2,3,4；
The split cells, for the data set to be split into training dataset and predictive data set in proportion；
The off-line training unit is used for off-line training appraisal of equipment model classifiers；
The off-line verification unit is used for off-line verification equipment current state.
Preferably, it in the off-line training unit, is concentrated in training data, by K1As positive collection, K2、K3、K4As negative
Collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm and is trained together, obtain Optimal Separating Hyperplane f1(x)；
By K2As positive collection, K1、K3、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f2(x)；
By K3As positive collection, K1、K2、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f3(x)；
By K4As positive collection, K1、K2、K3As negative collection, K1、K2、K3、K4Be input to together SVM training machine learning algorithm into
Row training, obtains Optimal Separating Hyperplane f4(x)；
The Optimal Separating Hyperplane fm(x)=ωTX+b, m=1,2,3,4；Wherein, ωTFor the slope of Optimal Separating Hyperplane, X=
[x1,x2,…,x4], b is constant.
Preferably, in the acquisition and processing unit, by PCA Principal Component Analysis Method by various kinds of equipment operation data dimensionality reduction
And it is mapped to feature space.
Preferably, in the off-line verification unit, calculate separately and comparison prediction data set in every class data arrive corresponding to
Optimal Separating Hyperplane f1(x)、f2(x)、f3(x)、f4(x) Euclidean distance, the smallest Optimal Separating Hyperplane f of Euclidean distancem(x), i.e.,
For the current state of equipment.
Preferably, the computing unit includes acquisition unit, input-output unit and rate of exchange unit；
The acquisition unit needs to compare the equipment operating data of two equipment of relative status for acquiring in real time；
The input-output unit obtains equipment for equipment operating data to be inputted trained appraisal of equipment model
Current state fm(x)；
The rate of exchange unit, for the current state of two equipment of the rate of exchange, if the current state f of two equipmentm(x) not
Together, then rate of exchange fm(x) state；If the current state f of two equipmentm(x) it is the same classification plane, then compares two equipment
Current state fm(x) corresponding Euclidean distance, the close relativity safe operation state of Euclidean distance are preferable.
Preferably, the equipment includes substation, passway for transmitting electricity and power supply area equipment；
The equipment operating data includes equipment operational defect, equipment operating condition, the abnormal method of operation of equipment and sets
Standby service life redundancy；
The equipment operational defect is divided into critical, serious, general and nothing, for evaluating power equipment running state；
The equipment operating condition includes active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit and normal；
The abnormal method of operation of equipment includes maintenance, interval transformation, grid switching operation and normality；
The equipment life redundancy is the percentage of equipment remaining life, by machinery equipment periodic measurement, in real time
The measured data of analysis determine the state and the development trend in future of equipment.
Advantageous effects of the invention:
1. forming the real-time of grid equipment by constructing multistage evaluation index the present invention is based on historical Device operation data
Appraisement system compensates for the low deficiency of fortune inspection state evaluation timeliness；
2. the present invention is based on the historical experience that power system monitor personnel have, using SVM algorithm training appraisal of equipment mould
Type reduces monitoring personnel and manually determines the amount of labour of risk equipment, and improves the reliability of evaluation result, helps to be promoted
The safety operation level of power grid.
Detailed description of the invention
Fig. 1 is a kind of method for real-time monitoring flow chart of grid equipment safe operation state of the invention；
Fig. 2 is classification plane in a kind of method for real-time monitoring embodiment of grid equipment safe operation state of the invention
Effect diagram；
Fig. 3 is that data drop to one in a kind of method for real-time monitoring embodiment of grid equipment safe operation state of the invention
Distribution schematic diagram after dimension；
Fig. 4 is a kind of method for real-time monitoring embodiment flow chart of grid equipment safe operation state of the invention；
Fig. 5 is a kind of structural block diagram of the real-time monitoring system of grid equipment safe operation state of the invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
In the embodiment of the present invention, the equipment includes substation, passway for transmitting electricity and power supply area equipment；
The equipment operating data includes equipment operational defect, equipment operating condition, the abnormal method of operation of equipment and sets
Standby service life redundancy；
The equipment operational defect is divided into critical, serious, general and nothing, for evaluating power equipment running state；
The equipment operating condition includes active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit and normal；
The abnormal method of operation of equipment includes maintenance, interval transformation, grid switching operation and normality；
The equipment life redundancy is the percentage of equipment remaining life, by machinery equipment periodic measurement, in real time
The measured data of analysis determine the state and the development trend in future of equipment.
The present invention is described in further detail by taking the electric network composition of somewhere as an example below such as:
This area is related to device type and includes breaker, route, main transformer, bus, capacitor, reactor, be grounded change, be used
Change, arc-extinction device, highly resistance, disconnecting link (handcart), SF6 rheology, route buckling, mother set, the protection of control box, breaker, measure and control device,
Combining unit, intelligent terminal, route protection, the protection of highly resistance non-electric quantity, highly resistance protection, short-line protection, bus protection, bypass are protected
Shield, mother protection, sectionalised protection, the protection of interior bridge, the protection of main transformer body non-electric quantity, the cooling equipment of main transformer, main transformer on-load voltage regulation,
Main transformer extinguishing device, main transformer protection close intelligence integrated device, protect and survey integrated device, low pressure capacitive reactance device protective device, ground connection change protection
It is device, reactor (oil anti-) non-electric quantity protection, AC system, direct current system, ups system, fire-fighting, technical precaution, public observing and controlling, standby
Automatic bus, low-frequency low-voltage load shedding device, stability control device, fault disconnection device, overload cutoff device, telemechanical apparatus, exchange
Machine, fault oscillograph, conservative management machine, phasor measuring set, time synchronism apparatus, Network Analyzer totally 55 class equipment；
It is related to operation data based on equipment operating data in one hour of past and management information, including remote signalling, distant
Control (tune), telemetering operation and warning information, equipment deficiency information, equipment running status information (such as overhaul of the equipments, interval transformation
Deng), equipment life information etc. respectively combs each its specifying information of voltage class substation equipment.
Equipment operational defect index counts critical defect, major defect existing for equipment and general defect situation,
It is used to support the evaluation to power equipment running state.
Equipment operating condition index is used to reflect information of the important telemetering amount beyond alarm bound section, it is possible to influence
The telemetering magnitude of grid equipment operating status, such as equipment is active and reactive, electric current, voltage, temperature of oil in transformer and section tidal current,
It is the important information for needing real time monitoring, handling in time.
Equipment surplus life target is supported by the state evaluation of fortune inspection, and equipment remaining life is by machinery equipment
Periodic measurement analyzes resulting data in time, determines that the state and the development trend in future of equipment are realized by long term monitoring
To the precognition of equipment operation condition.
The abnormal method of operation index of equipment is in inspecting state for describing equipment, equipment is in interval transformation, needs
Carry out the special method of operation situation of the equipment such as grid switching operation.
Equipment operational defect index is divided into critical, serious, general, four two-level index of nothing；
Equipment operating condition index is divided into active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit, normal five two-level index；
Equipment remaining life is from fortune inspection state evaluation as a result, only including a two-level index；
The abnormal method of operation of equipment is divided into maintenance, interval transformation, four grid switching operation, normality two-level index.
Above two layers of index constitutes equipment Real-Time Evaluation index system.
As shown in Figure 1, a kind of method for real-time monitoring of grid equipment safe operation state of the invention, including following step
It is rapid:
S1: based on historical Device operation data training appraisal of equipment model；
In embodiment, based on historical Device operation data training appraisal of equipment model described in step S1, comprising the following steps:
S101: acquiring and handles historical Device operation data；
The processing historical Device operation data, specifically: by PCA Principal Component Analysis Method by various kinds of equipment operation data
Dimensionality reduction is simultaneously mapped to feature space, data drop to it is one-dimensional after distribution situation it is as shown in Figure 3.
The PCA method of sklearn encapsulation, the code for being PCA is pca=PCA (n_components=1).PCA method ginseng
Number n_components, if being set as integer, n_components=k.If being set to decimal, illustrate dimensionality reduction
The information that data afterwards can retain.
S102: the weight that the corresponding equipment scoring score combination expert of historical Device operation data provides after processing will be gone through
History equipment operating data be labeled as equipment running status be it is outstanding, well, pass and alarm four class data sets, be denoted as Kn, n=
1,2,3,4；
Such as: critical, serious, the general and nothing in the equipment operational defect, respectively corresponding equipment scoring score is 0,
1,2,3；
Active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit in the equipment operating condition and normal, respectively correspond and set
Standby scoring score is 0,1,2,3,4；
Maintenance, interval transformation, grid switching operation and normality in the abnormal method of operation of equipment, respectively correspond equipment and comment
Dividing score is 0,1,2,3；
The equipment life redundancy is the percentage of equipment remaining life, the percentage range (0- of equipment remaining life
100%) four sections are divided into, respectively corresponding equipment scoring score is 0,1,2,3.
Appraisal of equipment total score are as follows: ∑ equipment scoring * weight, wherein weight is provided by expertise；
Appraisal of equipment total score is equally divided into 4 sections, the corresponding historical Device operation data in each section is labeled as setting
Standby operating status be it is outstanding, well, pass and four class data sets of alarm, be denoted as Kn, n=1,2,3,4.
S103: the data set is split as training dataset and predictive data set according to the ratio of 7:3；
S104: off-line training appraisal of equipment model classifiers, comprising the following steps:
It is concentrated in training data, by K1As positive collection, K2、K3、K4As negative collection, K1、K2、K3、K4It is input to SVM instruction together
Practice and be trained in machine learning algorithm, obtains Optimal Separating Hyperplane f1(x)；
By K2As positive collection, K1、K3、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f2(x)；
By K3As positive collection, K1、K2、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f3(x)；
By K4As positive collection, K1、K2、K3As negative collection, K1、K2、K3、K4Be input to together SVM training machine learning algorithm into
Row training, obtains Optimal Separating Hyperplane f4(x)；
The Optimal Separating Hyperplane fm(x)=ωTX+b, m=1,2,3,4；Wherein, ωTFor the slope of Optimal Separating Hyperplane, X=
[x1,x2,…,x4], b is constant.
The effect for plane of classifying is as shown in Figure 2, it can be seen that the different data of color are uniformly allocated in by straight line
Both sides.
S105: off-line verification equipment current state, specifically:
Calculate separately and in comparison prediction data set every class data to corresponding Optimal Separating Hyperplane f1(x)、f2(x)、f3
(x)、f4(x) Euclidean distance, the smallest Optimal Separating Hyperplane f of Euclidean distancem(x), the as current state of equipment.
The python method for calculating Euclidean distance is as follows: d=np.sqrt (np.sum (np.square (x-y))).
In embodiment, using gaussian kernel function training svm classifier:
Clf=svm.SVC (C=0.8, kernel='rbf', gamma=20, decision_function_shape
=' ovr').
Wherein:
C:float parameter default is 1.0
The penalty coefficient of error items.C is bigger, i.e., bigger to the punishment degree of misclassification sample, therefore quasi- in training sample
True rate is higher, but generalization ability reduces, that is, reduces to the classification accuracy of test data.On the contrary, holding if reducing C
Perhaps there are some misclassification error samples in training sample, generalization ability is strong.The case where having noise for training sample, generally adopts
With the latter, concentrate the sample of mistake classification as noise training sample.Due in this experiment using artificial mark there may be
The classification of mistake, therefore it is set as 0.8.
Kernel='rbf' uses gaussian kernel function.
Gamma is the coefficient of gaussian kernel function.
Decision_function_shape: handling more classification problems, one-to-one that ovo, the multi-purpose ovr of a pair is used to be defaulted as
ovr。
The classifier of the embodiment of the present invention accuracy rate (by point pair sample number divided by all sample numbers) are as follows: training set
Accuracy rate be 0.9366666667, the accuracy rate of forecast set is 0.85.
S2: the relative evaluation of equipment room is calculated based on equipment operating data and appraisal of equipment model.
In embodiment, the opposite of equipment room is calculated based on equipment operating data and appraisal of equipment model described in step S2 and is commented
Valence, comprising the following steps:
S201: acquisition needs to compare the equipment operating data of two equipment of relative status in real time；
The equipment operating data for needing to compare relative status acquired in real time is denoted as:
Wherein, rijIndicate i-th of device class to the value of j-th of setup measures.
S202: equipment operating data is inputted into trained appraisal of equipment model, obtains the current state f of equipmentm(x)；
S203: the current state of two equipment of the rate of exchange, if the current state f of two equipmentm(x) different, then rate of exchange fm(x)
State；If the current state f of two equipmentm(x) it is the same classification plane, then compares the current state f of two equipmentm(x)
Corresponding Euclidean distance, the close relativity safe operation state of Euclidean distance are preferable.
As shown in figure 4, the method also includes S3 in embodiment: pushing equipment relativity is safely operated state evaluation knot
Fruit, i.e., according to above step calculate equipment Real-Time Evaluation as a result, confirmation distinct device type in risk equipment that may be present,
Then its result is pushed to monitoring person on duty, person on duty reports dispatcher or reinforce monitoring according to its severity.
As shown in figure 5, a kind of real-time monitoring system of grid equipment safe operation state of the invention, including training unit
And computing unit；
The training unit, for based on historical Device operation data training appraisal of equipment model；
In embodiment, the equipment includes substation, passway for transmitting electricity and power supply area equipment；
The equipment operating data includes equipment operational defect, equipment operating condition, the abnormal method of operation of equipment and sets
Standby service life redundancy；
The equipment operational defect is divided into critical, serious, general and nothing, for evaluating power equipment running state；
The equipment operating condition includes active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit and normal；
The abnormal method of operation of equipment includes maintenance, interval transformation, grid switching operation and normality；
The equipment life redundancy is the percentage of equipment remaining life, by machinery equipment periodic measurement, in real time
The measured data of analysis determine the state and the development trend in future of equipment.
In embodiment, the training unit includes acquisition and processing unit, mark unit, split cells, off-line training list
Member and off-line verification unit；
The acquisition and processing unit, for acquiring and handling historical Device operation data；
In the acquisition and processing unit, by various kinds of equipment operation data dimensionality reduction and mapped by PCA Principal Component Analysis Method
To feature space.
The mark unit, for the corresponding equipment of treated historical Device operation data to score score combination expert
The weight provided, by historical Device operation data be labeled as equipment running status be it is outstanding, well, pass and alarm four class numbers
According to collection, it is denoted as Kn, n=1,2,3,4；
The split cells, for the data set to be split into training dataset and predictive data set in proportion；
The off-line training unit is used for off-line training appraisal of equipment model classifiers；
In the off-line training unit, concentrated in training data, by K1As positive collection, K2、K3、K4As negative collection, K1、K2、
K3、K4It is input in SVM training machine learning algorithm and is trained together, obtain Optimal Separating Hyperplane f1(x)；
By K2As positive collection, K1、K3、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f2(x)；
By K3As positive collection, K1、K2、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm together
It is trained, obtains Optimal Separating Hyperplane f3(x)；
By K4As positive collection, K1、K2、K3As negative collection, K1、K2、K3、K4Be input to together SVM training machine learning algorithm into
Row training, obtains Optimal Separating Hyperplane f4(x)；
The Optimal Separating Hyperplane fm(x)=ωTX+b, m=1,2,3,4；Wherein, ωTFor the slope of Optimal Separating Hyperplane, X=
[x1,x2,…,x4], b is constant.
The off-line verification unit is used for off-line verification equipment current state.
In the off-line verification unit, calculates separately and every class data are super to corresponding classification in comparison prediction data set
Plane f1(x)、f2(x)、f3(x)、f4(x) Euclidean distance, the smallest Optimal Separating Hyperplane f of Euclidean distancem(x), as equipment is worked as
Preceding state.
The computing unit, for calculating the relative evaluation of equipment room based on equipment operating data and appraisal of equipment model.
In embodiment, the computing unit includes acquisition unit, input-output unit and rate of exchange unit；
The acquisition unit needs to compare the equipment operating data of two equipment of relative status for acquiring in real time；
The input-output unit obtains equipment for equipment operating data to be inputted trained appraisal of equipment model
Current state fm(x)；
The rate of exchange unit, for the current state of two equipment of the rate of exchange, if the current state f of two equipmentm(x) not
Together, then rate of exchange fm(x) state；If the current state f of two equipmentm(x) it is the same classification plane, then compares two equipment
Current state fm(x) corresponding Euclidean distance, the close relativity safe operation state of Euclidean distance are preferable.
In embodiment, the system also includes push units, are safely operated state evaluation knot for pushing equipment relativity
Fruit.
Present invention applicant combines Figure of description to be described in detail and describe implementation example of the invention, still
It should be appreciated by those skilled in the art that implementing example above is only the preferred embodiments of the invention, explanation is only in detail
Help reader more fully understands spirit of that invention, and it is not intended to limit the protection scope of the present invention, on the contrary, any be based on this hair
Any improvement or modification made by bright spirit should all be fallen within the scope and spirit of the invention.
Claims (16)
1. a kind of method for real-time monitoring of grid equipment safe operation state, which comprises the following steps:
S1: based on historical Device operation data training appraisal of equipment model；
S2: the relative evaluation of equipment room is calculated based on equipment operating data and appraisal of equipment model.
2. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 1, which is characterized in that institute
The method of stating further includes S3: pushing equipment relativity is safely operated state evaluation result.
3. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 1, which is characterized in that step
Based on historical Device operation data training appraisal of equipment model described in rapid S1, comprising the following steps:
S101: acquiring and handles historical Device operation data；
S102: the weight that the corresponding equipment scoring score combination expert of historical Device operation data that treated provides, by history
Equipment operating data be labeled as equipment running status be it is outstanding, well, pass and alarm four class data sets, be denoted as Kn, n=1,
2,3,4；
S103: the data set is split into training dataset and predictive data set in proportion；
S104: off-line training appraisal of equipment model classifiers；
S105: off-line verification equipment current state.
4. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 3, which is characterized in that step
Processing historical Device operation data described in rapid S101, specifically: various kinds of equipment operation data is dropped by PCA Principal Component Analysis Method
It ties up and is mapped to feature space.
5. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 3, which is characterized in that step
Off-line training appraisal of equipment model classifiers described in rapid S104, comprising the following steps:
It is concentrated in training data, by K1As positive collection, K2、K3、K4As negative collection, K1、K2、K3、K4It is input to SVM training airplane together
It is trained in device learning algorithm, obtains Optimal Separating Hyperplane f1(x)；
By K2As positive collection, K1、K3、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm and carries out together
Training, obtains Optimal Separating Hyperplane f2(x)；
By K3As positive collection, K1、K2、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm and carries out together
Training, obtains Optimal Separating Hyperplane f3(x)；
By K4As positive collection, K1、K2、K3As negative collection, K1、K2、K3、K4SVM training machine learning algorithm is input to together to be instructed
Practice, obtains Optimal Separating Hyperplane f4(x)；
The Optimal Separating Hyperplane fm(x)=ωTX+b, m=1,2,3,4；Wherein, ωTFor the slope of Optimal Separating Hyperplane, X=[x1,
x2,…,x4], b is constant.
6. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 3, which is characterized in that step
Off-line verification equipment current state described in rapid S105, specifically:
Calculate separately and in comparison prediction data set every class data to corresponding Optimal Separating Hyperplane f1(x)、f2(x)、f3(x)、f4
(x) Euclidean distance, the smallest Optimal Separating Hyperplane f of Euclidean distancem(x), the as current state of equipment.
7. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 1, which is characterized in that step
The relative evaluation of equipment room is calculated described in rapid S2 based on equipment operating data and appraisal of equipment model, comprising the following steps:
S201: acquisition needs to compare the equipment operating data of two equipment of relative status in real time；
S202: equipment operating data is inputted into trained appraisal of equipment model, obtains the current state f of equipmentm(x)；
S203: the current state of two equipment of the rate of exchange, if the current state f of two equipmentm(x) different, then rate of exchange fm(x) shape
State；If the current state f of two equipmentm(x) it is the same classification plane, then compares the current state f of two equipmentm(x) corresponding
Euclidean distance, Euclidean distance it is close relativity safe operation state it is preferable.
8. the method for real-time monitoring of -7 any a kind of grid equipment safe operation states according to claim 1, feature
It is, the equipment includes substation, passway for transmitting electricity and power supply area equipment；
The equipment operating data includes equipment operational defect, equipment operating condition, the abnormal method of operation of equipment and equipment longevity
Order redundancy；
The equipment operational defect is divided into critical, serious, general and nothing, for evaluating power equipment running state；
The equipment operating condition includes active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit and normal；
The abnormal method of operation of equipment includes maintenance, interval transformation, grid switching operation and normality；
The equipment life redundancy is the percentage of equipment remaining life, by being analyzed in real time to machinery equipment periodic measurement
Measured data determine the state and the development trend in future of equipment.
9. a kind of real-time monitoring system of grid equipment safe operation state, which is characterized in that including training unit and calculate single
Member；
The training unit, for based on historical Device operation data training appraisal of equipment model；
The computing unit, for calculating the relative evaluation of equipment room based on equipment operating data and appraisal of equipment model.
10. a kind of real-time monitoring system of grid equipment safe operation state according to claim 9, which is characterized in that
The system also includes push units, are safely operated state evaluation result for pushing equipment relativity.
11. a kind of real-time monitoring system of grid equipment safe operation state according to claim 9, which is characterized in that
The training unit includes acquisition and processing unit, mark unit, split cells, off-line training unit and off-line verification unit；
The acquisition and processing unit, for acquiring and handling historical Device operation data；
The mark unit, for the corresponding equipment scoring score combination expert of historical Device operation data to provide by treated
Weight, by historical Device operation data be labeled as equipment running status be it is outstanding, well, pass and alarm four class data
Collection, is denoted as Kn, n=1,2, and 3,4；
The split cells, for the data set to be split into training dataset and predictive data set in proportion；
The off-line training unit is used for off-line training appraisal of equipment model classifiers；
The off-line verification unit is used for off-line verification equipment current state.
12. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 11, which is characterized in that
In the acquisition and processing unit, feature sky by various kinds of equipment operation data dimensionality reduction and is mapped to by PCA Principal Component Analysis Method
Between.
13. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 11, which is characterized in that
In the off-line training unit, concentrated in training data, by K1As positive collection, K2、K3、K4As negative collection, K1、K2、K3、K4Together
It is input in SVM training machine learning algorithm and is trained, obtain Optimal Separating Hyperplane f1(x)；
By K2As positive collection, K1、K3、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm and carries out together
Training, obtains Optimal Separating Hyperplane f2(x)；
By K3As positive collection, K1、K2、K4As negative collection, K1、K2、K3、K4It is input in SVM training machine learning algorithm and carries out together
Training, obtains Optimal Separating Hyperplane f3(x)；
By K4As positive collection, K1、K2、K3As negative collection, K1、K2、K3、K4SVM training machine learning algorithm is input to together to be instructed
Practice, obtains Optimal Separating Hyperplane f4(x)；
The Optimal Separating Hyperplane fm(x)=ωTX+b, m=1,2,3,4；Wherein, ωTFor the slope of Optimal Separating Hyperplane, X=[x1,
x2..., x4], b is constant.
14. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 11, which is characterized in that
In the off-line verification unit, calculate separately and in comparison prediction data set every class data to corresponding Optimal Separating Hyperplane f1
(x)、f2(x)、f3(x)、f4(x) Euclidean distance, the smallest Optimal Separating Hyperplane f of Euclidean distancem(x), the as current shape of equipment
State.
15. a kind of method for real-time monitoring of grid equipment safe operation state according to claim 9, which is characterized in that
The computing unit includes acquisition unit, input-output unit and rate of exchange unit；
The acquisition unit needs to compare the equipment operating data of two equipment of relative status for acquiring in real time；
The input-output unit obtains working as equipment for equipment operating data to be inputted trained appraisal of equipment model
Preceding state fm(x)；
The rate of exchange unit, for the current state of two equipment of the rate of exchange, if the current state f of two equipmentm(x) different, then compare
Valence fm(x) state；If the current state f of two equipmentm(x) it is the same classification plane, then compares the current shape of two equipment
State fm(x) corresponding Euclidean distance, the close relativity safe operation state of Euclidean distance are preferable.
16. special according to a kind of method for real-time monitoring of any grid equipment safe operation state of claim 9-15
Sign is that the equipment includes substation, passway for transmitting electricity and power supply area equipment；
The equipment operating data includes equipment operational defect, equipment operating condition, the abnormal method of operation of equipment and equipment longevity
Order redundancy；
The equipment operational defect is divided into critical, serious, general and nothing, for evaluating power equipment running state；
The equipment operating condition includes active out-of-limit, active heavy duty, overtemperature, voltage out-of-limit and normal；
The abnormal method of operation of equipment includes maintenance, interval transformation, grid switching operation and normality；
The equipment life redundancy is the percentage of equipment remaining life, by being analyzed in real time to machinery equipment periodic measurement
Measured data determine the state and the development trend in future of equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910563097.XA CN110322135A (en) | 2019-06-26 | 2019-06-26 | A kind of method for real-time monitoring and system of grid equipment safe operation state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910563097.XA CN110322135A (en) | 2019-06-26 | 2019-06-26 | A kind of method for real-time monitoring and system of grid equipment safe operation state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110322135A true CN110322135A (en) | 2019-10-11 |
Family
ID=68120527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910563097.XA Pending CN110322135A (en) | 2019-06-26 | 2019-06-26 | A kind of method for real-time monitoring and system of grid equipment safe operation state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110322135A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111158981A (en) * | 2019-12-26 | 2020-05-15 | 西安邮电大学 | Real-time monitoring method and system for reliable running state of CDN hard disk |
| CN111369179A (en) * | 2020-04-09 | 2020-07-03 | 广东电网有限责任公司电力科学研究院 | Closed-loop detection method and device for distribution automation terminal equipment |
| CN111428780A (en) * | 2020-03-20 | 2020-07-17 | 上海理工大学 | Power grid abnormal operation state identification method based on data driving |
| CN111800194A (en) * | 2020-06-22 | 2020-10-20 | 北京理工大学 | Nonlinear compensation method for few-mode multi-core OAM optical fiber transmission probability distribution |
| CN111935263A (en) * | 2020-07-31 | 2020-11-13 | 南京南瑞信息通信科技有限公司 | Power grid equipment bearing capacity evaluation result pushing method and system |
| CN112379659A (en) * | 2020-11-12 | 2021-02-19 | 西安石油大学 | Petroleum drilling machine fault prediction system |
| CN112414462A (en) * | 2020-11-16 | 2021-02-26 | 贵州电网有限责任公司 | Multistage abnormal data processing method in transformer load condition monitoring |
| CN113113972A (en) * | 2021-06-15 | 2021-07-13 | 北京德风新征程科技有限公司 | Monitoring information generation method and device, electronic equipment and computer readable medium |
| CN114123192A (en) * | 2021-11-30 | 2022-03-01 | 广东电网有限责任公司 | Method, system, equipment and medium for checking operation state of power grid station bus |
| CN114664064A (en) * | 2022-04-25 | 2022-06-24 | 中广核核电运营有限公司 | Alarm device and transformer system of cooler |
| CN116743618A (en) * | 2023-08-14 | 2023-09-12 | 武汉华瑞测智能技术有限公司 | Data acquisition and analysis method, equipment and medium of station remote equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046402A (en) * | 2015-06-23 | 2015-11-11 | 国家电网公司 | State evaluating method applied to secondary equipment of intelligent transformer station |
| US20180128863A1 (en) * | 2015-05-21 | 2018-05-10 | Hitachi, Ltd. | Energy Demand Predicting System and Energy Demand Predicting Method |
| CN109359896A (en) * | 2018-12-10 | 2019-02-19 | 国网福建省电力有限公司 | A kind of Guangdong power system method for prewarning risk based on SVM |
-
2019
- 2019-06-26 CN CN201910563097.XA patent/CN110322135A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180128863A1 (en) * | 2015-05-21 | 2018-05-10 | Hitachi, Ltd. | Energy Demand Predicting System and Energy Demand Predicting Method |
| CN105046402A (en) * | 2015-06-23 | 2015-11-11 | 国家电网公司 | State evaluating method applied to secondary equipment of intelligent transformer station |
| CN109359896A (en) * | 2018-12-10 | 2019-02-19 | 国网福建省电力有限公司 | A kind of Guangdong power system method for prewarning risk based on SVM |
Non-Patent Citations (7)
| Title |
|---|
| 孙兆兵: "基于支持向量机的轧钢电机状态综合评价方法", 《四川冶金》 * |
| 张珂珩等: "基于全息时标量测数据挖掘的配电网设备健康状态诊断分析", 《计算机测量与控制》 * |
| 施健等: "基于LS-SVM的电力通信网性能劣化评估与预测模型研究", 《计算机与数字工程》 * |
| 曹海欧等: "基于模糊支持向量机的继电保护状态在线评价", 《电力系统保护与控制》 * |
| 杜秋实等: "柱上真空断路器检修评价研究", 《吉林电力》 * |
| 缪芸等: "基于模糊层次分析法与支持向量机的变压器风险评估", 《现代电力》 * |
| 胡元潮等: "基于TOPSIS 法的变电站一次设备智能化评估", 《电力自动化设备》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111158981A (en) * | 2019-12-26 | 2020-05-15 | 西安邮电大学 | Real-time monitoring method and system for reliable running state of CDN hard disk |
| CN111428780A (en) * | 2020-03-20 | 2020-07-17 | 上海理工大学 | Power grid abnormal operation state identification method based on data driving |
| CN111428780B (en) * | 2020-03-20 | 2023-04-07 | 上海理工大学 | Power grid abnormal operation state identification method based on data driving |
| CN111369179A (en) * | 2020-04-09 | 2020-07-03 | 广东电网有限责任公司电力科学研究院 | Closed-loop detection method and device for distribution automation terminal equipment |
| CN111800194B (en) * | 2020-06-22 | 2021-06-18 | 北京理工大学 | Nonlinear compensation method for few-mode multi-core OAM optical fiber transmission probability distribution |
| CN111800194A (en) * | 2020-06-22 | 2020-10-20 | 北京理工大学 | Nonlinear compensation method for few-mode multi-core OAM optical fiber transmission probability distribution |
| CN111935263A (en) * | 2020-07-31 | 2020-11-13 | 南京南瑞信息通信科技有限公司 | Power grid equipment bearing capacity evaluation result pushing method and system |
| CN111935263B (en) * | 2020-07-31 | 2023-10-24 | 南京南瑞信息通信科技有限公司 | Power grid equipment bearing capacity evaluation result pushing method and system |
| CN112379659A (en) * | 2020-11-12 | 2021-02-19 | 西安石油大学 | Petroleum drilling machine fault prediction system |
| CN112414462A (en) * | 2020-11-16 | 2021-02-26 | 贵州电网有限责任公司 | Multistage abnormal data processing method in transformer load condition monitoring |
| CN113113972A (en) * | 2021-06-15 | 2021-07-13 | 北京德风新征程科技有限公司 | Monitoring information generation method and device, electronic equipment and computer readable medium |
| CN113113972B (en) * | 2021-06-15 | 2021-09-21 | 北京德风新征程科技有限公司 | Monitoring information generation method and device, electronic equipment and computer readable medium |
| CN114123192A (en) * | 2021-11-30 | 2022-03-01 | 广东电网有限责任公司 | Method, system, equipment and medium for checking operation state of power grid station bus |
| CN114664064A (en) * | 2022-04-25 | 2022-06-24 | 中广核核电运营有限公司 | Alarm device and transformer system of cooler |
| CN114664064B (en) * | 2022-04-25 | 2023-12-05 | 中广核核电运营有限公司 | Alarm device of cooler and transformer system |
| CN116743618A (en) * | 2023-08-14 | 2023-09-12 | 武汉华瑞测智能技术有限公司 | Data acquisition and analysis method, equipment and medium of station remote equipment |
| CN116743618B (en) * | 2023-08-14 | 2023-10-24 | 武汉华瑞测智能技术有限公司 | Data acquisition and analysis method, equipment and medium of station remote equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110322135A (en) | A kind of method for real-time monitoring and system of grid equipment safe operation state | |
| CN106529696B (en) | Early warning method and early warning device for equipment in power grid | |
| CN102663530B (en) | HVDC (High Voltage Direct Current) transmission system safe early warning and evaluating system | |
| CN108320043A (en) | A kind of distribution network equipment state diagnosis prediction method based on electric power big data | |
| CN101859409A (en) | Power transmission and transformation equipment state overhauling system based on risk evaluation | |
| CN107633354A (en) | A kind of integrated evaluating method stood with straight-flow system running status health degree | |
| CN106384210A (en) | Power transmission and transformation equipment maintenance priority ordering method based on maintenance risk premium | |
| CN104392391A (en) | Power grid running safety risk quantification method | |
| CN103761690A (en) | Evaluation method based on voltage reactive power control system in grid system | |
| CN107256449A (en) | A kind of relay protection device of intelligent substation state evaluation and appraisal procedure | |
| CN105046402A (en) | State evaluating method applied to secondary equipment of intelligent transformer station | |
| CN103996099B (en) | Method for conducting intelligent evaluation on student operation in training system | |
| CN109670676A (en) | Distributing net platform region method for prewarning risk and system based on Support Vector data description | |
| CN110826228B (en) | Regional power grid operation quality limit evaluation method | |
| CN105447657A (en) | Risk-based operation and maintenance management system of 750KV power equipment | |
| CN106295240A (en) | A kind of Condition Assessment for Power Transformer method based on fuzzy mathematics | |
| CN102930408B (en) | A kind of 750kV electric grid secondary equipment state appraisal procedure based on information fusion | |
| Catterson et al. | The impact of smart grid technology on dielectrics and electrical insulation | |
| CN105184490A (en) | Power grid dispatching operation process risk auxiliary pre-control system | |
| CN106408016A (en) | Distribution network power outage time automatic identification model construction method | |
| Zhukov et al. | A hybrid artificial neural network for voltage security evaluation in a power system | |
| Zhang et al. | Power grid fault diagnosis based on a deep pyramid convolutional neural network | |
| CN106655181A (en) | Priority setting method and system for power grid nodes | |
| CN111091294A (en) | Elasticity evaluation method for power distribution system containing microgrid | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system |
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: 20191011 |
|
| RJ01 | Rejection of invention patent application after publication |