CN110084502A - A kind of power quality controlling equipment running status appraisal procedure and device - Google Patents
A kind of power quality controlling equipment running status appraisal procedure and device Download PDFInfo
- Publication number
- CN110084502A CN110084502A CN201910320261.4A CN201910320261A CN110084502A CN 110084502 A CN110084502 A CN 110084502A CN 201910320261 A CN201910320261 A CN 201910320261A CN 110084502 A CN110084502 A CN 110084502A
- Authority
- CN
- China
- Prior art keywords
- phase voltage
- value
- phase
- voltage
- power quality
- 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 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 39
- 210000002569 neuron Anatomy 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 12
- 230000005611 electricity Effects 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 238000003825 pressing Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 claims 1
- 230000004075 alteration Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 39
- 230000006872 improvement Effects 0.000 abstract description 12
- 230000009194 climbing Effects 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 29
- 239000011159 matrix material Substances 0.000 description 16
- 230000008569 process Effects 0.000 description 14
- 238000012544 monitoring process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000013441 quality evaluation Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000003909 pattern recognition Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 101100499229 Mus musculus Dhrsx gene Proteins 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004870 electrical engineering Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000819 phase cycle Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000004335 scaling law Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000032258 transport 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
- G06Q10/06—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
- 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
- G06Q10/06395—Quality analysis or management
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention provides a kind of power quality controlling equipment running status appraisal procedure and device, this method comprises: obtaining abatement equipment historical parameter information within certain a period of time；Probabilistic neural network is trained using the historical parameter information as training sample；Assessed using probabilistic neural network is trained as assessment models whether abatement equipment puts into operation；Determine whether abatement equipment puts into operation according to assessment result.Institute's climbing form type of the present invention can accurately identify abatement equipment operating condition, comprehensively, rationally and image reflection regulation effect, it provides effective theoretical and data for the management of abatement equipment and the improvement of resolution to support, engineering value with higher and practical universality.
Description
Technical field
The present invention relates to electric power network technique field more particularly to a kind of power quality controlling equipment running status appraisal procedure and
Device.
Background technique
With the rapid development of science and technology, disturbance type multiplicity, the different new spy of disturbance feature is presented in the interference source in power grid
Point.It is the typical interference source of representative, electric energy matter with smelting iron and steel factory, electric railway traction station, photovoltaic plant, wind power plant etc.
Amount level need to meet concerned countries standard, and grid company just allows its grid-connected[1-5].Interference source installs power quality controlling equipment,
Power quality problem is actively administered, is smoothly grid-connected inevitable choice.But abatement equipment is user's assets, grid company without
Method knows equipment operation condition, lacks the status information that puts into operation of abatement equipment, improvement feelings that can not effectively in real time to interference source
Condition is monitored.It is required to meet grid company production run and management, it is necessary to which the operating status of abatement equipment is carried out
Accurate evaluation.Bibliography:
[1] Ou Yangsen, Liang Weibin (Ouyang Sen, the Liang Weibin) electric railway of based on PSCAD/EMTDC
Access electricity quality evaluation method (the An evaluation method of power quality about of power grid
Electrified railways connected to power grid based on PSCAD/EMTDC) [J] electrician electricity
Energy new technology (Advanced Technology of Electrical Engineering and Energy), 2016,35
(12):52-58.
[2] Tian Xu, Jiang Qirong, Wei Yingdong wait (Tian Xu, Jiang Qirong, Wei Yingdong, et al) electric
Gasification railway, which does not power off, excessively mutually studies (Research on railway novel with electric energy quality compensating device
uninterruptible phase-separation passing and power quality compensation
Device) [J] electrician's electric energy new technology (Advanced Technology of Electrical Engineering and
Energy),2018(4).
[3] Ou Yangsen, Liang Weibin, Su Weijian wait (Ouyang Sen, Liang Weibin, Su Weijian, et al)
The modeling of large-sized photovoltaic power station and power quality Pre-Evaluation method (Modeling and power based on electrical external characteristics
quality pre-evaluation method of large photovoltaic power station based on
Electric external characteristics) [J] electrician's electric energy new technology (Advanced Technology
ofElectrical Engineering and Energy),2018(5).
[4] Li Guodong, Pang Wenjie, Ge Leijiao wait (Li Guodong, Pang Wenjie, Ge Leijiao, et al)
Based on grid-connected photovoltaic system stationary power quality comprehensive assessment (the Steady-state power for improving radar map method
quality synthetic evaluation of grid-connected photovoltaic system based on
Improved radar chart) [J] electrician's electric energy new technology (Advanced Technology of Electrical
Engineering and Energy),2016,35(5):8-12.
[5] Wu Jie, Zhao Lixia, Zhao Fanfan wait (Wu Jie, Zhao Lixia, Zhao Fanfan, et al) one kind to change
New method (the A new method to improve power of inverter grid-connected system power quality under kind three-phase imbalance
Quality of inverter grid system under three-phase unbalance) the new skill of [J] electrician's electric energy
Art (Advanced Technology of Electrical Engineering and Energy), 2016,35 (11): 8-
13。
Summary of the invention
It is an object of the invention to solve the problems of the above-mentioned prior art, a kind of use stable state power index collection is provided
As the input parameter of probabilistic neural network, the method and device assessed abatement equipment operating status.
A kind of power quality controlling equipment running status appraisal procedure, comprising:
Obtain abatement equipment historical parameter information within the set time；The parameter information includes: voltage magnitude parameter, electricity
Corrugating distortion parameter；
Probabilistic neural network is trained using the historical parameter information as training sample；
Assessed using probabilistic neural network is trained as assessment models whether abatement equipment puts into operation；
Determine whether abatement equipment puts into operation according to assessment result.
Further, power quality controlling equipment running status appraisal procedure as described above, the parameter information include
Voltage magnitude parameter；
The voltage magnitude parameter includes: A phase voltage deviation VDA, B phase voltage deviation VDB, C phase voltage deviation VDC, three-phase
Voltage unbalance VS2S1；
The parameter information includes voltage waveform distortion parameter, and the voltage waveform distortion parameter includes: that A phase phase voltage is humorous
Wave total harmonic distortion VTHDA, B phase phase voltage total harmonic distortion VTHDB, C phase voltage total harmonic distortion VTHDC, A phase voltage it is long when dodge
Variate PltA, B phase voltage it is long when flickering value PltB, C phase voltage it is long when flickering value PltC。
Further, power quality controlling equipment running status appraisal procedure as described above, the probabilistic neural network
Include input layer, mode layer, summation layer and output layer；
The input layer, for the input value of acquisition to be passed to all mode units of mode layer, the nerve of input layer
First number is identical as the dimension of input feature value, and the input feature value is made of input value, and dimension is input parameter
Number；
The neuron number of the mode layer and the quantity of training sample are identical, and the center of each mode layer neuron is corresponding
One training sample, in this layer in the i-th class j-th of neuron output are as follows:
Wherein, σ is the smoothing parameter of probabilistic neural network, and value has determined the song of the mitriform centered on training sample point
The width of line；XijFor the center of j-th of neuron in the i-th class, X represents input sample feature vector, and d represents input sample feature
Vector dimension；
The summation layer is for the output for belonging to of a sort neuron in mode layer to be weighted and averaged, for layer of summing
Number is identical as the quantity of class categories:
In the formula, Pi(X) belong to the weighted average of the output of same class neuron for mode layer, N represents the training of the i-th class
The number of sample；
The output layer is according to all kinds of probability Estimations to input vector, and using Bayes classification rule, selecting has most
Classification of the classification of big posterior probability as output:
Class (X)=argmax { Pi(X)} (3)
Class (X) represents probabilistic neural network for the classification results of some input sample.
Further, power quality controlling equipment running status appraisal procedure as described above, to probabilistic neural network into
Before row training, to the A phase voltage deviation VDA, B phase voltage deviation VDB, C phase voltage deviation VDCIt is normalized；
The normalized is handled according to following interval type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate the actual measured value of voltage deviation, xth1, xth2Respectively indicate the survey
The upper limit value and lower limit value of the index national standard under amount point voltage class.
Further, power quality controlling equipment running status appraisal procedure as described above, to probabilistic neural network into
Before row training, to imbalance of three-phase voltage VS2S1, A phase phase voltage total harmonic distortion VTHDA, B phase phase voltage harmonic wave resultant distortion
Rate VTHDB, C phase voltage total harmonic distortion VTHDC, A phase voltage it is long when flickering value PltA, B phase voltage it is long when flickering value PltB, C phase electricity
Flickering value P when pressing longltCIt is handled by formula (5) the minimal type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate index actual measured value, xthIt indicates under the measurement point voltage class
The national standard limit of the index.
A kind of power quality controlling equipment running status assessment device, comprising:
History parameters acquiring unit, for obtaining abatement equipment historical parameter information within certain a period of time；The parameter
Information includes: voltage magnitude parameter, voltage waveform distortion parameter；
Training unit, for being trained using the historical parameter information as training sample to probabilistic neural network；
Assessment unit, for whether being put into operation to abatement equipment using training probabilistic neural network as assessment models
It is assessed；
Judging unit, for determining whether abatement equipment puts into operation according to assessment result.
Further, power quality controlling equipment running status as described above assesses device, the voltage magnitude parameter
It include: A phase voltage deviation VDA, B phase voltage deviation VDB, C phase voltage deviation VDC, imbalance of three-phase voltage VS2S1；
The voltage waveform distortion parameter includes: to respectively refer to A phase phase voltage total harmonic distortion VTHDA, B phase phase voltage it is humorous
Wave total harmonic distortion VTHDB, C phase voltage total harmonic distortion VTHDC, A phase voltage it is long when flickering value PltA, B phase voltage it is long when flickering value
PltB, C phase voltage it is long when flickering value PltC。
Further, power quality controlling equipment running status as described above assesses device, including the first initialization list
Member, the second initialization unit；
First initialization unit is used for before probabilistic neural network is trained, to the A phase voltage deviation VDA、
B phase voltage deviation VDB, C phase voltage deviation VDCIt is normalized；
The normalized is handled according to following interval type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate the actual measured value of voltage deviation, xth1, xth2Respectively indicate the survey
The upper limit value and lower limit value of the index national standard under amount point voltage class.
Before second initialization unit is used to be trained probabilistic neural network, to imbalance of three-phase voltage
VS2S1, A phase phase voltage total harmonic distortion VTHDA, B phase phase voltage total harmonic distortion VTHDB, C phase voltage total harmonic distortion
VTHDC, A phase voltage it is long when flickering value PltA, B phase voltage it is long when flickering value PltB, C phase voltage it is long when flickering value PltCBy formula (5) institute
Minimal type index pretreatment formula is stated to be handled:
In formula, ujIndicate pretreated value, xjIndicate index actual measured value, xthIt indicates under the measurement point voltage class
The national standard limit of the index.
A kind of power quality controlling equipment running status assessment equipment, including processor and it is stored with computer program generation
The memory of code；
When the computer program code is run by the processor, causes the calculating equipment to execute basis and such as take up an official post
Power quality controlling equipment running status appraisal procedure described in one.
A kind of computer readable storage medium is stored with program code, the journey on the computer readable storage medium
Described in any item power quality controlling equipment running status appraisal procedures as described above are realized when sequence code executes.
The utility model has the advantages that
Probabilistic neural network has very simple, quick training process when carrying out pattern-recognition, it is based on Bayes
Minimum Risk Criterion carries out decision, and when training sample is enough, probabilistic neural network converges on Bayes Optimum decision, classification
Ability is strong.Institute's climbing form type of the present invention can accurately identify abatement equipment operating condition, be the management and improvement of abatement equipment
The improvement of scheme provides effective theoretical and data and supports, engineering value with higher and practical universality.
Detailed description of the invention
Fig. 1 is power quality controlling of embodiment of the present invention equipment running status appraisal procedure flow chart；
Fig. 2 is probabilistic neural network structure chart；
Fig. 3 is Analysis of Hierarchy Structure figure；
Fig. 4 is power quality controlling of embodiment of the present invention equipment running status apparatus for evaluating structure chart.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, the technical solution in the present invention is carried out below
It clearly and completely describes, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
Fig. 1 is power quality controlling of embodiment of the present invention equipment running status appraisal procedure flow chart, as shown in Figure 1, should
Method the following steps are included:
Step 101: obtaining abatement equipment historical parameter information within certain a period of time；The parameter information includes: voltage
Magnitude parameters, voltage waveform distortion parameter；
Step 102: probabilistic neural network being trained using the historical parameter information as training sample；
Step 103: whether being put into operation progress using probabilistic neural network is trained as assessment models to abatement equipment
Assessment；
Step 104: determining whether abatement equipment puts into operation according to assessment result.
Specifically, present invention proposition uses input parameter of the stable state power index collection as probabilistic neural network, to improvement
Equipment running status is classified, and realizes the assessment of abatement equipment operating status.Probabilistic neural network tool when carrying out pattern-recognition
There are very simple, quick training process, it is based on Bayesian Smallest Risk criterion and carries out decision, when training sample is enough
When, probabilistic neural network converges on Bayes Optimum decision, and classification capacity is strong.The monitoring that Electric Power Quality On-line Monitor System obtains
Data break is intensive, closely related with the investment state of load condition and interference source abatement equipment.Probabilistic neural network
(Probabilistic Neural Network, PNN) is with the training time is short, is not likely to produce local optimum, classification accuracy rate
The features such as higher, is suitble to most carry out pattern-recognition to online data.The present invention is proposed using probabilistic neural network to abatement equipment
Operation conditions classify, whether as required the normal operation of monitoring user's abatement equipment completes regulation effect and runs shape
State assessment.
The superiority and inferiority of power quality is measured usually in terms of voltage magnitude, voltage waveform distortion, frequency three, installs electric energy
For quality controlling equipment often in order to solve the problems, such as voltage magnitude and voltage waveform distortion problem, voltage magnitude problem includes voltage
Deviation, non-equilibrium among three phase voltages etc.；Voltage waveform distortion problem includes harmonic wave, voltage fluctuation and flicker etc., therefore the present invention selects
Select voltage deviation VDA、VDB、VDC, imbalance of three-phase voltage VS2S1, total harmonic distortion VTHDA、VTHDB、VTHDC, voltage it is long when
Flickering PltA、PltB、PltCInput parameter of totally ten parameters as probabilistic neural network.
The probabilistic neural network is a kind of supervised learning algorithm, needs to use the data of label as network training
Then sample predicts with the model that study obtains unknown sample that it is by input layer, mode layer, summation layer and output layer
Composition, structure chart are as shown in Figure 2.
(1) input layer
Network inputs are 10 parameters contained in the classification index system, therefore contained neuron number in input layer
It is 10.
Input value is passed to all mode units by the input layer, the neuron number and input feature vector of input layer to
The dimension of amount is identical, and the input feature value is made of input value, and dimension is the number for inputting parameter, of the present invention to be
Ten parameters, so the dimension of input feature value is also ten, input parameter is 10, then the dimension of input feature value is
10, then input layer contains 10 neurons altogether, stores 10 parameters respectively.
(2) mode layer
The neuron number of the mode layer and the quantity of training sample are identical, and each mode unit has a center,
As current training sample.In this layer in the i-th class j-th of neuron output are as follows:
Wherein, σ is the smoothing parameter of probabilistic neural network, and value has determined the song of the mitriform centered on training sample point
The width of line；XijFor the center of j-th of neuron in the i-th class.
What the mode unit referred to is exactly that process of the mode layer neuron from input layer to mode layer is exactly in input layer
The input parameter that is stored of neuron be separately input in each neuron of mode layer (each neuron of mode layer
A corresponding training sample), calculation formula (1) obtains the output of each neuron of mode layer.
Monitoring data used in the present invention are that acquisition in every three minutes is primary, are carried out using three day datas to network in example
Training, therefore the neuron number in mode layer is 1440.To increase training sample, it is only necessary to increase mode layer neuron
Number.Smoothing factor σ is generally provided by experience, and the present invention takes σ=0.1.
(3) summation layer
Summation layer shares 2 neurons, respectively corresponds two kinds of different operating conditions of abatement equipment, i.e. 1. abatement equipments are not put into
Operation；2. abatement equipment puts into operation.
The number of summation layer is identical as the quantity of class categories.Summation layer will belong to of a sort neuron in mode layer
Output is weighted and averaged:
Output layer is according to all kinds of probability Estimations to input vector, using Bayes classification rule, selects after having maximum
Test classification of the classification of probability as output:
Class (X)=argmax { Pi(X)} (3)
When the Class (X) of output is 1, represents algorithm and determine that abatement equipment does not put into operation, as the Class (X) of output
When being 2, represents algorithm and determine that abatement equipment puts into operation.
Preferably due to different types of power quality index, dimension is different, and generating different dimension brings can not be public
Degree property, the big index of absolute value are affected for training result, and therefore, the present invention need to refer to training to eliminate this influence
Mark is normalized.Power quality index measured value is expressed as to the per unit value of its voltage class index limits, it can be same
When eliminate the influence that its different magnitude and dimension generate.
For voltage deviation, formula can be pre-processed by formula (4) interval type index:
In formula, xjIndicate the actual measured value of the index, xth1, xth2Respectively indicate the index under the measurement point voltage class
The upper limit value and lower limit value of national standard.The index xjIndicate A phase voltage deviation VDAOr B phase voltage deviation VDBOr C phase voltage deviation VDC's
Actual measured value.
For three-phase imbalance, voltage harmonic, voltage flicker, formula can be pre-processed by formula (5) minimal type index:
In formula, xjIndicate index actual measured value, xthIndicate the national standard limit of the index under the measurement point voltage class, institute
State index xjIndicate imbalance of three-phase voltage VS2S1Or A phase phase voltage total harmonic distortion VTHDAOr B phase phase voltage harmonic wave resultant distortion
Rate VTHDBOr C phase voltage total harmonic distortion VTHDCOr A phase voltage it is long when flickering value PltAOr B phase voltage it is long when flickering value PltBOr C
Flickering value P when phase voltage is longltC。
The advantages of preprocess method of the present invention is the influence that can have both eliminated index difference magnitude and different dimensions, can be with
The superiority and inferiority for directly judging individual event power quality index is assessed for subsequent regulation effect.Uniformly, ujIt is the bigger the better, and
If uj>=0, then the single index is qualified, uj< 0, then the single index is unqualified.
In addition, the present invention controlling by the electricity quality evaluation evaluation of result abatement equipment before and after comparison abatement equipment investment
Effect is managed, and regulation effect evaluation is divided into single item evaluation and overall merit.Single item evaluation is based on measurement data, to some
Effectiveness indicator problem is examined；Overall merit is on the basis of single item evaluation, with analytic hierarchy process (AHP) (Analytic
Hierarchy process, AHP) propose stationary power quality overall target, comprehensively reflect equipment regulation effect.
The present invention evaluates the improvement of abatement equipment by the electricity quality evaluation result before and after comparison investment abatement equipment
Effect, and regulation effect assessment is divided into single item evaluation and overall merit.Single item evaluation is based on measurement data, to some effect
Fruit On Index is examined；Overall merit is to propose stable state electric energy matter with analytic hierarchy process (AHP) on the basis of single item evaluation
The overall target of amount reflects equipment regulation effect comprehensively.
Single item evaluation
The present invention both eliminates the influence of index difference magnitude and different dimensions after pre-processing to initial data,
It can also directly judge the superiority and inferiority of individual event power quality index.When carrying out the evaluation of abatement equipment regulation effect, three numbers of phases are taken
According to average value, voltage deviation V is obtainedD, three-phase voltage negative phase-sequence degree of unbalancedness VS2S1, total harmonic distortion VTHDAnd voltage is long
When flickering PltTotally 4 input parameters form assessment indicator system.
In order to evaluate the regulation effect of abatement equipment, need to compare the electricity quality evaluation knot of abatement equipment investment front and back
Fruit.In view of calculation amount size and realization a possibility that, take and refer to after (or before cutting out) abatement equipment investment in hour
Target average value uj1And before abatement equipment investment in (or cut out after) hour index average value uj2, by the two it
Difference is used as abatement equipment regulation effect evaluation index uj0:
uj0=uj1-uj2 (6)
Overall merit
The present invention determines every individual event by analytic hierarchy process (AHP) (Analytic hierarchy process, AHP) decision
Index weights, to complete the overall merit to abatement equipment regulation effect.
Analytic hierarchy process (AHP) is a kind of criteria decision-making method for combining qualitative and quantitative analysis[23].It is a kind of evaluation
Method, but more often it is used to parameter weight[24-26]。
Fig. 3 is the analytic hierarchy structure figure for evaluating power quality controlling equipment regulation effect index weights.Destination layer is electricity
Energy quality controlling recruitment evaluation, subordinate's rule layer are voltage magnitude problem B1With voltage waveform distortion B2.Voltage magnitude problem B1In
The index for including is voltage deviation C1With imbalance of three-phase voltage C2.Voltage waveform distortion B2In include index be voltage harmonic
C3With voltage flicker C4。
In sequence calculates, single sequencing problem of the relatively upper a certain factor of a level of the factor of each level can be reduced to again
A series of judgement of pairs of factors is compared.In order to which by multilevel iudge quantification, analytic hierarchy process (AHP) introduces 1-9 scaling law (such as table 1
It is shown), and write as judgment matrix form, table 2 lists destination layer to the judgment matrix of rule layer.After forming judgment matrix, i.e.,
Can by calculate judgment matrix maximum eigenvalue corresponding to feature vector, calculate a certain layer for a upper level some
The relative importance weight of element.After calculating single sequencing weight of a certain level relative to the upper each factor of a level, use
The weight weighted comprehensive of upper level factor itself, can calculate total hierarchial sorting weight.In short, successively from top to bottom
Calculate ranking value of the lowermost layer factor relative to top relative importance weight or relative superior or inferior order.
The element of judgment matrix is all larger than 0, and diagonal element is 1.If matrix element meets Bij=1/Bji, then to appoint
Meaning i, j, k have Bij×Bjk=Bik, judgment matrix is Consistent Matrix at this time, i.e. expert is each to judge in judge index importance
Between it is harmonious, conflicting result will not occur.
1 1-9 Scale Method of table
Note: 2,4,6,8 and 1/2,1/4,1/6,1/8 is mediate.
2 rule layer judgment matrix of table
Evaluate concrete scheme
According to the analysis and expertise to measured data, by regulation effect be divided into it is excellent, good, in, poor four grades.
1) when regulation effect index is less than 0, regulation effect be it is poor, abatement equipment cannot not only improve electric energy matter at this time
Amount, also deteriorates power quality more；
2) during when regulation effect index is in the section 0-0.1, regulation effect is, abatement equipment omits power quality index
There is improvement result；
3) when regulation effect index is in the section 0.1-0.3 regulation effect be it is good, abatement equipment is to power quality index
Have clear improvement effect；
4) when regulation effect index is greater than 0.3, regulation effect is excellent, improvement effect of the abatement equipment to power quality index
Fruit is very prominent.
Another object of the present invention is to provide a kind of power quality controlling equipment running status to assess device, such as Fig. 4 institute
Show, which includes:
History parameters acquiring unit, for obtaining abatement equipment historical parameter information within certain a period of time；The parameter
Information includes: voltage magnitude parameter, voltage waveform distortion parameter；
Training unit, for being trained using the historical parameter information as training sample to probabilistic neural network；
Assessment unit, for whether being put into operation to abatement equipment using training probabilistic neural network as assessment models
It is assessed；
Judging unit, for determining whether abatement equipment puts into operation according to assessment result.
Preferably, the power quality controlling equipment running status assesses device, including the first initialization unit；
First initialization unit is used for before probabilistic neural network is trained, to the A phase voltage deviation VDA、
B phase voltage deviation VDB, C phase voltage deviation VDCIt is normalized；
The normalized is handled according to following interval type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate the actual measured value of voltage deviation, xth1, xth2Respectively indicate the survey
The upper limit value and lower limit value of the index national standard under amount point voltage class.
Second initialization unit；
Before second initialization unit is used to be trained probabilistic neural network, to imbalance of three-phase voltage
VS2S1, A phase phase voltage total harmonic distortion VTHDA, B phase phase voltage total harmonic distortion VTHDB, C phase voltage total harmonic distortion
VTHDC, A phase voltage it is long when flickering value PltA, B phase voltage it is long when flickering value PltB, C phase voltage it is long when flickering value PltCBy formula (5) institute
Minimal type index pretreatment formula is stated to be handled:
In formula, ujIndicate pretreated value, xjIndicate index actual measured value, xthIt indicates under the measurement point voltage class
The national standard limit of the index.
The present invention also provides a kind of power quality controlling equipment running status assessment equipment, including processor and it is stored with
The memory of computer program code；
When the computer program code is run by the processor, causes the calculating equipment to execute basis and such as take up an official post
Power quality controlling equipment running status appraisal procedure described in one.
The present invention also provides a kind of computer readable storage medium, program is stored on the computer readable storage medium
Code realizes described in any item power quality controlling equipment running status assessment side as described above when said program code executes
Method.
Sample calculation analysis
The electric energy quality monitoring data that the present invention chooses Anhui Province 35kV substation are analyzed as example, the power transformation
The power quality controlling equipment that connect interference source is installed of standing is static reactive generator (Static Var Generator, SVG),
And the switching experiment of SVG is carried out within 2 months in 2018, record has corresponding switch data as shown in table 3.
3 SVG switch motion situation of table
Understand through investigation, after 13 days 2 months cut out before SVG investment with 14 days 2 months SVG, SVG is in the state that do not put into operation.
The judgement of abatement equipment operation conditions
Input probability neural network after monitoring data pretreatment in 11 days 2 months to 13 days 2 months is trained by the present invention, generally
Rate neural network is realized by the newpnn function of MATLAB/Simulink.
Monitoring data of monitoring device 3 minutes records have 480 datas record daily.According to national standard[6-9], electricity
Pressure deviation takes the maximum value in 3 minutes, and flickering then took in 3 minutes when three-phase imbalance, total harmonic distortion and long voltage
95% probability value.Since length is limited, only 13 days 2 months partial datas are shown in the text.
Table 4 is the monitoring data before pretreatment, wherein voltage deviation, voltage tri-phase unbalance factor, voltage harmonic resultant distortion
Rate is indicated with percents.
Table 5 is pretreated monitoring data, since the voltage class of substation is 35kV, pre-processes the voltage in formula
The national standard limit of flickering when deviation, voltage tri-phase unbalance factor, total harmonic distortion and long voltage[6-9]Respectively 10%,
2%, 3% and 1.Last in table 5 is classified as operating condition classification known to training data, and 1, which represents abatement equipment, does not put into, and 2 represent
Abatement equipment investment.Judging only to need when unknown data can output category result by 2-11 column data input neural network.
Table clustering target collection on 4 February 13 (part)
Index set (part) after pretreatment on table 5 February 13
The neural network that 16 days -2 months on the 11st 2 months data are used as unknown data input training to complete is classified,
And compare classification results and known correct result, it is as shown in table 6 to obtain classification accuracy rate.As can be seen from Table 6, do not having
2 months of switch motion 11,12,15 days and 16 days, the accuracy of classification is 100%.And the 2 of SVG switch motion
On the moon 13 and 14 days, a small amount of the reason of judging result by accident occur is to need the regular hour that can just play improvement electric energy after SVG is put into
The effect of quality index, so the movement of the opposite SVG switch of the variation of power quality index has certain delay.Though and result
So there is fraction of erroneous judgement, but the accuracy of all classification is all 95% or more, within the acceptable range.
6 classification results accuracy of table
The assessment of abatement equipment regulation effect
Through investigating, it is photovoltaic plant which, which connects interference source, and the operating mode of SVG is reactive compensation state.Through special
Family's judgement, when SVG is in reactive compensation state, voltage magnitude problem B1Than voltage waveform distortion B2Problem is obviously important, voltage
Deviation C1Than imbalance of three-phase voltage C2It is slightly important, total harmonic distortion C3Flickering C when long with voltage4It is of equal importance.At this time
Judgment matrix A of the rule layer for destination layer are as follows:
Judgment matrix of the indicator layer for rule layer are as follows:
Judgment matrix is obviously Consistent Matrix.
For matrix A, relatively important weight computing result is WT=[0.8333,0.1667]；
For matrix B1, relatively important weight computing result is WT=[0.7500,0.2500]；
For matrix B2, relatively important weight computing result is WT=[0.5000,0.5000]；
Then index weights distribution is as shown in table 7.
The distribution of 7 index weights of table
The average value for taking 13 days 2 months indices the latter hour data before SVG is put into, before abatement equipment investment
Power quality evaluation index afterwards, as shown in table 8, table 9.
Power quality index evaluation before 8 SVG of table is put into
Power quality index is evaluated after 9 SVG of table investment
Power quality index evaluation result after being put into abatement equipment subtracts the power quality before abatement equipment is put into and refers to
Mark evaluation result to get regulation effect evaluation result is arrived, as shown in table 10.
The evaluation of 10 SVG regulation effect of table
According to the judgment criteria that 3.3 sections are proposed, it is as shown in table 11 to be governed recruitment evaluation grade.It uses 14 days 2 months
SVG, which cuts out front and back result and assessed, will also obtain identical result.
11 SVG regulation effect evaluation grade of table
It has clear improvement effect after substation investment SVG to voltage deviation index, this is also the master of this substation installation SVG
Syllabus.However SVG not only has an impact to voltage deviation, also other indexs can be made to change.Voltage harmonic index is thrown in SVG
Slightly improve after entering, and imbalance of three-phase voltage, voltage flicker index deteriorate after SVG investment, this is the control strategy by SVG
It determines.Although imbalance of three-phase voltage and voltage flicker deteriorate after SVG investment, the degree very little deteriorated, so surely
State comprehensive power quality index still improves significantly to power quality index when being shown in substation investment SVG.
Example shows that the investment of abatement equipment not only can make target power quality index change, other indexs also can
It is inevitably affected, the regulation effect evaluation of programme that the single item evaluation that is mentioned of the present invention is combined with overall merit can be with
The regulation effect of the reaction abatement equipment of full scale image, engineering value with higher.
Complicated, abatement equipment difficult management the status for power quality interference source in current power grid, the present invention is according to electricity
It can monitoring data realization abatement equipment operating status assessment and regulation effect evaluation.
1) present invention proposes to use input parameter of the stable state power index collection as probabilistic neural network, transports to abatement equipment
Row state carries out pattern-recognition, realizes the assessment of abatement equipment operating status.
2) method that the present invention proposes the electricity quality evaluation result of comparison abatement equipment investment front and back, passes through single item evaluation
The mode combined with overall merit realizes the regulation effect evaluation of abatement equipment.Single item evaluation be based on measurement data,
The regulation effect of single Index For Steady-state is examined；Overall merit is on the basis of single item evaluation, with analytic hierarchy process (AHP)
It proposes the overall target of stationary power quality, reflects equipment regulation effect comprehensively.
3) present invention verifies proposed method using Anhui Power Grid substation measured data.Example proves that the present invention is mentioned
Model can accurately identify that abatement equipment operating condition, comprehensive, reasonable and vivid reflection regulation effect are abatement equipment
Management and the improvement of resolution provide it is effective theoretical supported with data, engineering value with higher with it is practical pervasive
Property.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations.Ability
Technical staff in domain is it should be appreciated that embodiments herein can provide as method, system or computer program product.Therefore, originally
The form of complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in application.And
And it wherein includes the computer-usable storage medium of computer usable program code that the application, which can be used in one or more,
The form for the computer program product implemented in (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.).
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, to the greatest extent
Invention is explained in detail referring to above-described embodiment for pipe, it should be understood by those ordinary skilled in the art that: still
It can be with modifications or equivalent substitutions are made to specific embodiments of the invention, and without departing from any of spirit and scope of the invention
Modification or equivalent replacement, should all cover within the scope of the claims of the present invention.
Claims (10)
1. a kind of power quality controlling equipment running status appraisal procedure characterized by comprising
Obtain abatement equipment historical parameter information within the set time；
Probabilistic neural network is trained using the historical parameter information as training sample；
Assessed using probabilistic neural network is trained as assessment models whether abatement equipment puts into operation；
Determine whether abatement equipment puts into operation according to assessment result.
2. power quality controlling equipment running status appraisal procedure according to claim 1, which is characterized in that the parameter
Information includes voltage magnitude parameter；
The voltage magnitude parameter includes: A phase voltage deviation VDA, B phase voltage deviation VDB, C phase voltage deviation VDC, three-phase voltage
Uneven VS2S1；
The parameter information includes voltage waveform distortion parameter, and the voltage waveform distortion parameter includes: that A phase phase voltage harmonic wave is total
Aberration rate VTHDA, B phase phase voltage total harmonic distortion VTHDB, C phase voltage total harmonic distortion VTHDC, A phase voltage it is long when flickering value
PltA, B phase voltage it is long when flickering value PltB, C phase voltage it is long when flickering value PltC。
3. power quality controlling equipment running status appraisal procedure according to claim 1, which is characterized in that the probability
Neural network includes input layer, mode layer, summation layer and output layer；
The input layer, for the input value of acquisition to be passed to all mode units of mode layer, the neuron of input layer
Number is identical as the dimension of input feature value, and the input feature value is made of input value, and dimension is for inputting parameter
Number；
The neuron number of the mode layer and the quantity of training sample are identical, and the center of each mode layer neuron is one corresponding
Training sample, in this layer in the i-th class j-th of neuron output are as follows:
Wherein, σ is the smoothing parameter of probabilistic neural network, and value has determined the bell curve centered on training sample point
Width；XijFor the center of j-th of neuron in the i-th class, X represents input sample feature vector, and d represents input sample feature vector
Dimension；
The summation layer for the output for belonging to of a sort neuron in mode layer to be weighted and averaged, the number for layer of summing with
The quantity of class categories is identical:
In the formula, Pi(X) belong to the weighted average of the output of same class neuron for mode layer, N represents the training sample of the i-th class
Number；
The output layer is according to all kinds of probability Estimations to input vector, using Bayes classification rule, selects after having maximum
Test classification of the classification of probability as output:
Class (X)=arg max { Pi(X)} (3)
Class (X) represents probabilistic neural network for the classification results of some input sample.
4. power quality controlling equipment running status appraisal procedure according to claim 2, it is characterised in that: to probability mind
Before being trained through network, to the A phase voltage deviation VDA, B phase voltage deviation VDB, C phase voltage deviation VDCIt is normalized
Processing；
The normalized is handled according to following interval type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate the actual measured value of voltage deviation, xth1, xth2Respectively indicate the measurement point
The upper limit value and lower limit value of the index national standard under voltage class.
5. power quality controlling equipment running status appraisal procedure according to claim 2, which is characterized in that probability mind
Before being trained through network, to imbalance of three-phase voltage VS2S1, A phase phase voltage total harmonic distortion VTHDA, B phase phase voltage it is humorous
Wave total harmonic distortion VTHDB, C phase voltage total harmonic distortion VTHDC, A phase voltage it is long when flickering value PltA, B phase voltage it is long when flickering value
PltB, C phase voltage it is long when flickering value PltCIt is handled by formula (5) the minimal type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate index actual measured value, xthIndicate that this refers under the measurement point voltage class
Target national standard limit.
6. a kind of power quality controlling equipment running status assesses device characterized by comprising
History parameters acquiring unit, for obtaining abatement equipment historical parameter information within certain a period of time；The parameter information
It include: voltage magnitude parameter, voltage waveform distortion parameter；
Training unit, for being trained using the historical parameter information as training sample to probabilistic neural network；
Assessment unit, for whether being put into operation progress to abatement equipment using training probabilistic neural network as assessment models
Assessment；
Judging unit, for determining whether abatement equipment puts into operation according to assessment result.
7. power quality controlling equipment running status according to claim 6 assesses device, the voltage magnitude parameter packet
It includes: A phase voltage deviation VDA, B phase voltage deviation VDB, C phase voltage deviation VDC, imbalance of three-phase voltage VS2S1；
The voltage waveform distortion parameter includes: to respectively refer to A phase phase voltage total harmonic distortion VTHDA, B phase phase voltage harmonic wave it is always abnormal
Variability VTHDB, C phase voltage total harmonic distortion VTHDC, A phase voltage it is long when flickering value PltA, B phase voltage it is long when flickering value PltB, C phase
Flickering value P when voltage is longltC。
8. power quality controlling equipment running status according to claim 6 assesses device, it is characterised in that: including first
Initialization unit, the second initialization unit；
First initialization unit is used for before probabilistic neural network is trained, to the A phase voltage deviation VDA, B phase
Voltage deviation VDB, C phase voltage deviation VDCIt is normalized；
The normalized is handled according to following interval type index pretreatment formula:
In formula, ujIndicate pretreated value, xjIndicate the actual measured value of voltage deviation, xth1, xth2Respectively indicate the measurement point
The upper limit value and lower limit value of the index national standard under voltage class.
Before second initialization unit is used to be trained probabilistic neural network, to imbalance of three-phase voltage VS2S1, A phase
Phase voltage total harmonic distortion VTHDA, B phase phase voltage total harmonic distortion VTHDB, C phase voltage total harmonic distortion VTHDC, A phase electricity
Flickering value P when pressing longltA, B phase voltage it is long when flickering value PltB, C phase voltage it is long when flickering value PltCRefer to by formula (5) described minimal type
Mark pretreatment formula is handled:
In formula, ujIndicate pretreated value, xjIndicate index actual measured value, xthIndicate that this refers under the measurement point voltage class
Target national standard limit.
9. a kind of power quality controlling equipment running status assessment equipment, which is characterized in that including processor and be stored with meter
The memory of calculation machine program code；
When the computer program code is run by the processor, cause the calculating equipment execute according to claim 1-
Power quality controlling equipment running status appraisal procedure described in any one of 5.
10. a kind of computer readable storage medium, which is characterized in that be stored with program generation on the computer readable storage medium
Code realizes the power quality controlling equipment running status as described in any one of claims 1 to 5 when said program code executes
Appraisal procedure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910320261.4A CN110084502A (en) | 2019-04-19 | 2019-04-19 | A kind of power quality controlling equipment running status appraisal procedure and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910320261.4A CN110084502A (en) | 2019-04-19 | 2019-04-19 | A kind of power quality controlling equipment running status appraisal procedure and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084502A true CN110084502A (en) | 2019-08-02 |
Family
ID=67415886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910320261.4A Pending CN110084502A (en) | 2019-04-19 | 2019-04-19 | A kind of power quality controlling equipment running status appraisal procedure and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084502A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330142A (en) * | 2020-11-03 | 2021-02-05 | 浙江华电器材检测研究所有限公司 | Multi-access electric automobile charging pile electric energy quality operation and maintenance management platform |
| CN113221441A (en) * | 2020-12-24 | 2021-08-06 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
| CN113269041A (en) * | 2021-04-25 | 2021-08-17 | 南京南瑞水利水电科技有限公司 | Signal abnormity detection method applied to synchronization device |
| CN114118404A (en) * | 2021-10-20 | 2022-03-01 | 广西电网有限责任公司 | Electric energy meter phase unbalance state syndrome research and judgment method based on neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103512751A (en) * | 2013-07-03 | 2014-01-15 | 辽宁大学 | Bearing health state identification method based on probabilistic neural network |
| CN103544542A (en) * | 2013-10-16 | 2014-01-29 | 天津大学 | Power system transient stability margin predicting method |
| CN106251059A (en) * | 2016-07-27 | 2016-12-21 | 中国电力科学研究院 | A kind of cable status appraisal procedure based on probabilistic neural network algorithm |
| CN107276072A (en) * | 2017-06-16 | 2017-10-20 | 东北电力大学 | A kind of method of utilization steady state information qualitative assessment power system transient stability margin |
| CN109165807A (en) * | 2018-07-03 | 2019-01-08 | 安徽理工大学 | A kind of energy quality comprehensive assessment method based on probabilistic neural network |
-
2019
- 2019-04-19 CN CN201910320261.4A patent/CN110084502A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103512751A (en) * | 2013-07-03 | 2014-01-15 | 辽宁大学 | Bearing health state identification method based on probabilistic neural network |
| CN103544542A (en) * | 2013-10-16 | 2014-01-29 | 天津大学 | Power system transient stability margin predicting method |
| CN106251059A (en) * | 2016-07-27 | 2016-12-21 | 中国电力科学研究院 | A kind of cable status appraisal procedure based on probabilistic neural network algorithm |
| CN107276072A (en) * | 2017-06-16 | 2017-10-20 | 东北电力大学 | A kind of method of utilization steady state information qualitative assessment power system transient stability margin |
| CN109165807A (en) * | 2018-07-03 | 2019-01-08 | 安徽理工大学 | A kind of energy quality comprehensive assessment method based on probabilistic neural network |
Non-Patent Citations (1)
| Title |
|---|
| 成于思: "人工智能技术在建设工程争议解决中的应用", 《人工智能技术在建设工程争议解决中的应用》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330142A (en) * | 2020-11-03 | 2021-02-05 | 浙江华电器材检测研究所有限公司 | Multi-access electric automobile charging pile electric energy quality operation and maintenance management platform |
| CN113221441A (en) * | 2020-12-24 | 2021-08-06 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
| CN113221441B (en) * | 2020-12-24 | 2022-12-02 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
| CN113269041A (en) * | 2021-04-25 | 2021-08-17 | 南京南瑞水利水电科技有限公司 | Signal abnormity detection method applied to synchronization device |
| CN113269041B (en) * | 2021-04-25 | 2023-10-10 | 南京南瑞水利水电科技有限公司 | Signal abnormality detection method applied to synchronous device |
| CN114118404A (en) * | 2021-10-20 | 2022-03-01 | 广西电网有限责任公司 | Electric energy meter phase unbalance state syndrome research and judgment method based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A hierarchical self-adaptive data-analytics method for real-time power system short-term voltage stability assessment | |
| CN110084502A (en) | A kind of power quality controlling equipment running status appraisal procedure and device | |
| He et al. | Robust online dynamic security assessment using adaptive ensemble decision-tree learning | |
| Wang et al. | Decision tree based online stability assessment scheme for power systems with renewable generations | |
| CN110826228B (en) | Regional power grid operation quality limit evaluation method | |
| CN110210670A (en) | A kind of prediction technique based on power-system short-term load | |
| CN110705831A (en) | Power angle instability mode pre-judgment model construction method after power system fault and application thereof | |
| Saatloo et al. | Hierarchical extreme learning machine enabled dynamic line rating forecasting | |
| Xue et al. | Adaptive ultra-short-term wind power prediction based on risk assessment | |
| CN112308425A (en) | Method for constructing distribution transformer health evaluation index system | |
| Xu et al. | Intelligent Systems for Stability Assessment and Control of Smart Power Grids | |
| CN109711686A (en) | Voltage dip severity appraisal procedure based on multiobjective decision-making analytic hierarchy process (AHP) | |
| Shahriyari et al. | A Deep Learning-Based Approach for Comprehensive Rotor Angle Stability Assessment | |
| Zhang et al. | Data-driven risk assessment early-warning model for power system transmission congestions | |
| Khalyasmaa et al. | Training samples construction for energy utilities operational assets management | |
| CN116436080A (en) | Comprehensive evaluation method and system for participating in power grid regulation and control by flexible resource clusters | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| Hanshen et al. | An intelligent transformer warning model based on data-driven bagging decision tree | |
| Paramathma et al. | Artificial neural network based static security assessment module using PMU measurements for smart grid application | |
| Liu et al. | A conservative prediction model of power system transient stability | |
| Wu et al. | Transformer combination weighting evaluation model based on bp neural network | |
| Ghasempour et al. | Multiple Output Sparse Gaussian Processes for Short-Term Electric Load Forecasting | |
| López et al. | Phasor measurement unit placement for wide area instability detection and prediction | |
| Sauer et al. | Integrated security analysis | |
| Yan et al. | Cross-domain feature extraction-based household characteristics identification approach using smart meter data |
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: 20190802 |
|
| RJ01 | Rejection of invention patent application after publication |