CN103777091B - A kind of high ferro electric energy quality monitoring data classification method based on K average - Google Patents
A kind of high ferro electric energy quality monitoring data classification method based on K average Download PDFInfo
- Publication number
- CN103777091B CN103777091B CN201310676852.8A CN201310676852A CN103777091B CN 103777091 B CN103777091 B CN 103777091B CN 201310676852 A CN201310676852 A CN 201310676852A CN 103777091 B CN103777091 B CN 103777091B
- Authority
- CN
- China
- Prior art keywords
- car
- electric energy
- high ferro
- time
- monitoring data
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000003064 k means clustering Methods 0.000 claims abstract description 4
- 230000005611 electricity Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 abstract description 6
- 238000010606 normalization Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 3
- 229910052742 iron Inorganic materials 0.000 abstract description 3
- 238000007670 refining Methods 0.000 abstract description 2
- 230000003137 locomotive effect Effects 0.000 description 7
- 238000000819 phase cycle Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The present invention proposes a kind of high ferro electric energy quality monitoring data classification method based on K average, first the power quality data only having a high ferro operation on supply arm is isolated by the method, then utilize the operation time of high ferro, power quality index statistical value as sample data normalization after, carry out K mean cluster, the classification of the final electric energy quality monitoring data obtaining different automobile types.The present invention is according to high ferro Traction Station electric energy quality monitoring data, it is provided that a kind of simple and efficient method carrying out separating by the power quality data only having a high ferro operation on certain supply arm；Utilize K means clustering algorithm, complete the power quality data for high ferro vehicle and classify；The most only study the power quality problem brought in certain type high ferro running to electrical network to provide the foundation.Can also be for various operating mode and carry out electric energy quality monitoring data classification, provide basis for refining the quality of power supply specificity analysis of high iron load further.
Description
Technical field
The invention belongs to the power quality data analysis field of high ferro, it is provided that relate to a kind of high ferro quality of power supply based on K average prison
Survey data classification method.
Background technology
High-speed railway is with energy-saving and environmental protection, the feature such as efficient, safe, comfortable, quick, punctual in China's fast development, and it is just
The trip changing people maked rapid progress and life.But high-speed railway locomotive power is big, road speed is high, gives and undertake its confession
The quality of power supply of the electrical network along the line of electricity task brings certain impact.
China Express Railway uses AC-DC-AC high-power locomotive, at high speed (more than highest running speed 350km/h), high density
(minimum tracking interval 3min), the operation mode of big marshalling (maximum 16 marshallings)；The most Beijing-Shanghai high-speed iron of high-speed railway
The Transportation Model on road takes bullet train and overline train to mix the pattern of race, the particularity of this decision maker's high-speed railway traction load and
Complexity.Electrified high-speed railway locomotive belongs to non-linear and impact load, and it mainly brings the electricity such as negative phase-sequence and harmonic wave to electrical network
Can quality impact；The quality of power supply characteristic causing electrical network during the locomotive operation of different automobile types simultaneously is different, particularly harmonic characterisitic.
Miscellaneous equipment in electrical network is not only adversely affected by these, and the stability and reliability to self-operating constitutes a threat to.Electricity
The electric locomotive of electrified railway is the high-power single-phase rectification load that undulatory property is the biggest, and due to train adding in running
Factor and the confessions such as speed, coasting, the various states of braking, and line slope, turning radius, meteorological condition, driver operation
The change of train quantity in electric arm, traction load random fluctuation.Therefore, when carrying out the analysis of electric energy metrical, it is necessary to fully examine
Consider the part throttle characteristics to electric locomotive.Using different friendship-straight electric locomotives, its harmonic content produced is different.In order to further
Studying the quality of power supply characteristic after certain vehicle puts into operation, assess its impact brought to electrical network, the present invention proposes a kind of for vehicle
The method that electric energy quality monitoring data are classified research.
Summary of the invention
In order to overcome the defect of prior art, it is an object of the invention to propose a kind of high ferro electric energy quality monitoring based on K average
Data classification method, first the power quality data that supply arm only has a high ferro operation is isolated, is then utilized by the method
After operation time, power quality index and the statistical value thereof of high ferro is as sample data normalization, carry out K mean cluster, finally
Obtain the classification of the electric energy quality monitoring data of different automobile types.This invention is to study the spy of the quality of power supply after certain vehicle puts into operation further
Property, assess its impact brought to electrical network, and then take positive counter-measure to provide the foundation for electrical network.
The present invention is achieved through the following technical solutions:
A kind of high ferro electric energy quality monitoring data classification method based on K average, it is characterised in that the method comprises the steps:
(1) the electric energy quality monitoring data of high ferro Traction Station are obtained by online electric energy quality monitor；
(2) according to have car to run time electric energy quality monitoring data and high ferro in the operation time of supply arm, filter out supply arm
The upper power quality data only having a car operation；
(3) for only having the power quality data that a car runs on supply arm, operation time and the electric energy of a high ferro are calculated
The statistical value of quality index；
(4) using the statistical value running time and power quality index in step (3) as sample data, and it is normalized
Process；
(5) sample data after being normalized is carried out K mean cluster, to obtain the electric energy quality monitoring of different automobile types
Data are classified.
Further, in step (1), the electric energy quality monitoring data of described high ferro Traction Station include voltage deviation, electric current, bear
Sequence electric current, frequency departure, active power, reactive power, electricity, harmonic wave, m-Acetyl chlorophosphonazo, phase angle, voltage fluctuation and flicker,
Tri-phase unbalance factor, voltage swell, voltage dip and short time voltage interruption etc..
Further, in step (2), described in electric energy quality monitoring data when having car to run include active power, negative-sequence current
With phase angle etc..
Further, in step (2), described in filter out and only have under power quality data when car runs includes on supply arm
State step:
When () electric energy quality monitoring data when there being car to run are simultaneously greater than pre-set threshold value a, then being considered as supply arm has the moment of car,
The moment that supply arm has car is ranked up the time series obtaining there is the car period from front to back；
B (), according to there being car time series, calculates each time span having the car period continuously；
C () judges each time span having the car period continuously and the size of the shortest transit time, divide there being the car period continuously；
D () judges each time span having the car period continuously and the size of the longest transit time, will have car Time segments division continuously for many
What what car ran have car period and only car ran has the car period, and then draws when only having a car operation on supply arm
Power quality data.
Further, in step (3), described power quality index include active power, reactive power, electric current, negative-sequence current,
And the content of harmonic wave and number of times etc.；The statistical value of described power quality index include the maximum of power quality index, minima,
Average and variance etc..
Further, in step (3), the time of running of a described high ferro is according to the described electric energy matter only having when a car runs
The absolute difference playing, stopping the moment corresponding to amount data obtains；
Assume vector chronological for power quality index p be P, P=[p (1), p (2) ..., p (i) ..., p (n)], wherein p (i) and p (n)
Being respectively i-th and the power quality index of n sampling instant, the maximum of the most described power quality index index p is
pmax=max (P), minima are pmin=min (P), meansigma methods areVariance is
Further, in step (4), the operation time of a high ferro and the statistical value of power quality index are mapped to [0 ,+1]
Interval, sets X 'i=(x′I, l, x 'I, 2..., x 'I, j... x 'I, M) it is i-th sample data, tool M eigenvalue altogether, by following formula to sample number
According to being normalized calculating:
In formula, x 'I, jThe jth eigenvalue of i-th sample data, xI, jNormalized value for the jth feature of i-th sample data.
Further, in step (5), K-means clustering process is as follows:
A () chooses 4 samples from sample data, as the initial cluster center of 4 bunches；
B sample data is distributed to closest cluster centre according to minimal distance principle by ()；
C (), according to cluster result, recalculates the sample average in each cluster as new cluster centre；
D () repeats step b and c until cluster centre no longer changes.
E () cluster terminates, obtain 4 bunches.
Compared with prior art, the beneficial effects of the present invention is:
1) present invention is according to high ferro Traction Station electric energy quality monitoring data, it is provided that a kind of simple and efficient only having on certain supply arm
The method that the power quality data of one high ferro operation carries out separating；Utilize K means clustering algorithm, complete for high ferro vehicle
Power quality data classification.
2) present invention is to study the power quality problem brought in certain type high ferro running to electrical network to provide the foundation.Additionally,
Institute of the present invention extracting method also can carry out electric energy quality monitoring data for operating mode (including load braking, startup, stable operation etc.)
Classification, provides basis for refining the quality of power supply specificity analysis of high iron load further.
Accompanying drawing explanation
Fig. 1 is the flow chart of the classification of the electric energy quality monitoring data for high ferro vehicle of the present invention；
Fig. 2 is to only have a power quality data classification process figure when car runs on the supply arm of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings the detailed description of the invention of the present invention is described in further detail.
This example elaborates a kind of high ferro electric energy quality monitoring data classification method based on K average, its flow chart as it is shown in figure 1,
Comprise the steps:
(1) the electric energy quality monitoring data of high ferro Traction Station are obtained by online electric energy quality monitor.
High ferro traction power supply station electric energy quality monitoring packet contains active power (P), reactive power (Q), electric current (I), harmonic wave (Ih,
I1Represent fundamental current), m-Acetyl chlorophosphonazo (Iih), voltage (merit, flickering (Pst), negative phase-sequence (μ2) etc. index.
(2) according to have car to run time electric energy quality monitoring data and high ferro at the transit time of supply arm, filter out power supply
Only having the power quality data that a car runs on arm, it implements process as shown in Figure 2.
The I present invention has car period and nothing first against the index such as active power, negative-sequence current and phase angle of the quality of power supply to supply arm
The power quality data of car period carries out preliminary classification.
According to there being high ferro to enter after supply arm, by some index of Monitoring Data such as power, negative-sequence current and phase angle are the biggest
In predetermined threshold value as criterion, obtain any instant t1 (i) on supply arm (i=1,2 ... n, n represent sampled point number)
There is car situation: have car y=1 and without car y=0.The moment having car y=1 situation corresponding is arranged in order be formed as having the car period time
Between sequence t (j).
Then II according to there being car time series, calculates each time span having the car period continuously.
Utilize time difference i.e. t (the j+1)-t (j) of latter point and former point whether more than 10s as criterion, find and connect on supply arm
Continuous initial time t_b and end time t_e having the car period.Detailed process is as follows: if t (j+1)-t (j) < 10s, then j=j+1,
Enter next one point to judge；If t (j+1)-t (j) >=10s, then it is assumed that t (j) was the n-th end having the car period continuously
Only moment t_e (n), t (j+1) is (n+1)th initial time t_b (n+1) having the car period continuously.
Therefore, there is the initial time t_b (n+1) of car period according to a certain end time t_e (n) having the car period continuously continuously with this
Between difference can try to achieve each time span having the car period continuously.
III has the division of car period continuously.
One high ferro was about between 4min to 6min in the normal pass time of supply arm, and the shortest transit time is 4min,
The long running time is 6min.The most complete having the car period continuously to obtain, the present invention utilizes high ferro on supply arm
The shortest transit time 4min is further judged.Concrete operations are as follows: calculate the n-th time span having the car period
T_interal=t_e-t_b, if t_interal >=4min, then it represents that n-th to have the car period would be complete for this；If
T_interal < 4min, then connect thereafter have the car period, being formed new has the car period, until this new time having the car period
Length is more than the shortest transit time 4min, and what so this was new have, and the car period is also complete has the car period.
IV finally by have continuously car Time segments division be many cars run have the car period and only a car operation have the car period.
In order to obtain the power quality data that only a high ferro is run, the present invention utilizes the maximum duration conduct that single high ferro is run
Criterion, if there being the time span ＞ 6min of car period, then it is assumed that be many cars run have the car period；If have the car period time
Between length≤6min, then it is assumed that be car run have the car period, the power quality data that this period is corresponding, it is simply that the present invention
To be obtained only has the power quality data that a high ferro is run.
(3) for the power quality data only having on supply arm when high ferro is run, calculate a high ferro the operation time,
Power quality index and statistical value thereof.
Wherein the time of running of a car can only have the start-stop corresponding to the power quality data that a high ferro is run according to obtained
Moment subtracts each other acquisition.Power quality index is primarily referred to as the indexs such as power, electric current, harmonic content, overtone order, negative-sequence current.
The statistical value of power quality index includes the maximum of power quality index, minima, average, variance etc..Assume power index
The chronological vector of p be P, P=[p (1), p (2) ..., p (i) ..., p (n)], wherein p (i) and p (n) are respectively i-th and n and adopt
The power quality index value in sample moment, then the maximum of this index p is pmax=max (P), minima are pmin=min (P), average
Value is Variance is
(4) using operation time, power quality index and statistical value thereof as sample data, it is normalized.
For improving the generalization ability of model, reducing the time of procedural training, sample data is carried out normalized.In this example
Operation time, power quality index and the statistical value thereof of all high ferros are mapped to [0 ,+1] interval, it is assumed that X 'i=(x′I, 1x′I, 2' ..., x 'I, m)
It is i-th sample data, there is x 'I, 1, x 'I, 2..., x 'I, mM ties up variable, i.e. m eigenvalue altogether.
Normalization formula is:
In above formula, x 'i,jThe jth eigenvalue of i-th sample data, xI, jNormalization for the jth feature of i-th sample data
Value, the i-th sample data after normalization is Xi=xi,1, xI, 2..., xI, m)。
(5) K-mean cluster is carried out
(5a) according to vehicle: bullet train 8 is organized into groups, bullet train 16 is organized into groups, medium trains 8 is organized into groups and medium trains 16
Marshalling, power quality data when being run by only car is divided into four classes；
(5b) 4 initial cluster center V are choseni(1), i=1,2 ..., 4, i represent the sequence number of class, and parenthetic 1 represents initial
Interative computation number of times；
Such as: 4 initial cluster centers can choose to obtain more dispersion according to practical situation, and such as 16 marshaling power are general
It is 2 times of 8 marshaling power, thus can go out to select initial cluster center at 1 times power and 2 times powers respectively.
(5c) one by one by data sample (X to be clustered1, X2..., Xj..., XN) distribute to 4 cluster centres by minimum distance criterion
In some Vi(t).Calculate jth data sample XjWith 4 cluster centre Vi(t), i=1,2 ..., the distance of 4
d(Xj, Vi(t)), i=1,2,3,4, if d is (Xj, Vi(t)) minimum, then XjIt is the i-th class, is designated as X 'j；
Wherein, XjAnd XNRepresent jth and N number of data sample；T represents interative computation number of times, is initially 1；I represents class
Sequence number, i=1,2 ..., 4；
(5d) 4 new cluster centres are calculated:。CiRepresent the number of samples of the i-th class.
If (5e) Vi(t+1)=Vi(t), i=1,2 ..., 4, then algorithm terminates, and sample data is gathered the most at last is four classes, i.e. obtains four
Class sample data；Otherwise, t=t+1, return step (5c).
(6) the four class cluster sample datas obtained in step (5), it is simply that the electric energy quality monitoring data of four kinds of different automobile types.
Finally should be noted that: above example is only in order to illustrate that technical scheme is not intended to limit, although reference
The present invention has been described in detail by above-described embodiment, those of ordinary skill in the field it is understood that still can to this
Invention detailed description of the invention modify or equivalent, and without departing from spirit and scope of the invention any amendment or etc.
With replacing, it all should be contained in the middle of scope of the presently claimed invention.
Claims (11)
1. a high ferro electric energy quality monitoring data classification method based on K average, it is characterised in that the method includes walking as follows
Rapid:
(1) the electric energy quality monitoring data of high ferro Traction Station are obtained by online electric energy quality monitor；
(2) according to have car to run time electric energy quality monitoring data and high ferro in the operation time of supply arm, filter out supply arm
The upper power quality data only having a car operation；
(3) for only having the power quality data that a car runs on supply arm, operation time and the electric energy of a high ferro are calculated
The statistical value of quality index；
(4) using the statistical value running time and power quality index in step (3) as sample data, and it is normalized
Process；
(5) sample data after being normalized is carried out K mean cluster, to obtain the electric energy quality monitoring of different automobile types
Data are classified.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 1, it is characterised in that
In step (1), the electric energy quality monitoring data of described high ferro Traction Station include that voltage deviation, electric current, negative-sequence current, frequency are inclined
Difference, active power, reactive power, electricity, harmonic wave, m-Acetyl chlorophosphonazo, phase angle, voltage fluctuation and flicker, tri-phase unbalance factor,
Voltage swell, voltage dip and short time voltage are interrupted.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 1, it is characterised in that
In step (2), described in electric energy quality monitoring data when having car to run include active power, negative-sequence current and phase angle.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 1, it is characterised in that
In step (2), described in filter out and only have power quality data when car runs on supply arm and comprise the steps:
When () electric energy quality monitoring data when there being car to run are simultaneously greater than pre-set threshold value a, then being considered as supply arm has the moment of car,
The moment that supply arm has car is ranked up the time series obtaining there is the car period from front to back；
B (), according to there being car time series, calculates each time span having the car period continuously；
C () judges each time span having the car period continuously and the size of the shortest transit time, divide there being the car period continuously；
D () judges each time span having the car period continuously and the size of the longest transit time, will have car Time segments division continuously for many
What what car ran have car period and only car ran has the car period, and then draws when only having a car operation on supply arm
Power quality data.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 4, it is characterised in that
In step (b), calculate each time span having the car period continuously and comprise the steps:
Judge to have in car time series in adjacent two moment time difference of later moment in time and previous moment whether more than 10s；
Such as ＜ 10s, then enter the subsequent time with later moment in time and judge；
Such as 10s, then previous moment being considered as this end time having the car period continuously, later moment in time is considered as next car continuously
The initial time of period, determines each time span having the car period continuously with this.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 4, it is characterised in that
In step (c), comprise the steps: there being the car period to carry out division continuously
Judge each time span having the car period continuously and the size of the shortest transit time；
Such as the shortest transit time, represent that this has the car period to be complete continuously；
Transit time as the shortest in ＜, then have this car period to have the car period to be formed continuously with rear one continuously and new have the car period continuously,
Till this new time span having the car period continuously is more than or equal to the shortest transit time.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 4, it is characterised in that
In step (d), by described have continuously car Time segments division be many cars run have car period and only when having car of a car operation
Section comprises the steps:
Judge each time span having the car period continuously and the size of the longest transit time；
Transit time as the longest in ＞, then it is assumed that be many cars run have the car period；
Such as the longest transit time, then it is assumed that be only car run have the car period, the power quality data that this period is corresponding
It is power quality data when only a car runs.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 1, it is characterised in that
In step (3), described power quality index includes containing of active power, reactive power, electric current, negative-sequence current and harmonic wave
Amount and number of times；The statistical value of described power quality index includes the maximum of power quality index, minima, average and variance.
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 8, it is characterised in that
In step (3), the time of running of a described high ferro is according to corresponding to the described power quality data only having when a car runs
Play, stop the absolute difference in moment to obtain；
Assume vector chronological for power quality index p be P, P=[p (1), p (2) ..., p (i) ..., p (n)], wherein p (i) and p (n)
Being respectively i-th and the power quality index of n sampling instant, the maximum of the most described power quality index p is pmax=max (P),
Minima is pmin=min (P), meansigma methods areVariance is
High ferro electric energy quality monitoring data classification method based on K average the most according to claim 1, it is characterised in that
In step (4), the operation time of a high ferro and the statistical value of power quality index are mapped to [0 ,+1] interval, set
X′i=(x 'i,1,x′i,2,...,x′i,j,...,x′i,M) it is i-th sample data, tool M eigenvalue altogether, by following formula, sample data is carried out normalizing
Change and calculate:
In formula, x'i,jThe jth eigenvalue of i-th sample data, xi,jNormalized value for the jth feature of i-th sample data.
11. high ferro electric energy quality monitoring data classification methods based on K average according to claim 1, it is characterised in that
In step (5), the method that the sample data after being normalized carries out K mean cluster comprises the steps:
Power quality data when only car is run by () according to vehicle a is divided into four classes, described vehicle to include bullet train 8
Organize into groups, bullet train 16 is organized into groups, medium trains 8 is organized into groups and medium trains 16 is organized into groups；
B () randomly selects initialization cluster centre Vi(1)；
Wherein, i=1,2 ..., 4, i represent the sequence number of class；1 represents primary iteration operation times；
C () is one by one by sample data (X to be clustered1,X2,...,Xj,....,XN) distribute to 4 clusters according to following minimum range rule
Some V in the minds of ini(t), described minimum range rule is:
Calculate jth sample data XjWith 4 cluster centre Vi(t), i=1,2 ..., the distance d (X of 4j,Vi(t)), i=1,2,3,4,
If d is (Xj,Vi(t)) minimum, then XjIt is the i-th class, is designated as
Wherein, XjAnd XNRepresent jth and N number of sample data；T represents interative computation number of times, is initially 1；I represents class
Sequence number, i=1,2 ..., 4；
D () is by following formula 4 new cluster centres of calculating:
Wherein, CiRepresent the number of the i-th class sample data；
If (e) Vi(t+1)=Vi(t), i=1,2 ..., 4, then this K means clustering algorithm terminates, and sample data to be gathered be four classes；
Otherwise, make interative computation number of times t=t+1, jump to step (c).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310676852.8A CN103777091B (en) | 2013-12-13 | 2013-12-13 | A kind of high ferro electric energy quality monitoring data classification method based on K average |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310676852.8A CN103777091B (en) | 2013-12-13 | 2013-12-13 | A kind of high ferro electric energy quality monitoring data classification method based on K average |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103777091A CN103777091A (en) | 2014-05-07 |
| CN103777091B true CN103777091B (en) | 2016-08-31 |
Family
ID=50569566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310676852.8A Active CN103777091B (en) | 2013-12-13 | 2013-12-13 | A kind of high ferro electric energy quality monitoring data classification method based on K average |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103777091B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105445675B (en) * | 2014-08-04 | 2018-06-29 | 格力电器（武汉）有限公司 | The mass analysis method of AC power |
| CN104462802A (en) * | 2014-11-26 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Method for analyzing outlier data in large-scale data |
| CN104915681B (en) * | 2015-06-05 | 2019-01-15 | 华南理工大学 | Take into account substation's clustering method of voltage dip monitoring information and its relation factor |
| CN105021888B (en) * | 2015-07-06 | 2018-09-18 | 广州供电局有限公司 | Harmonic data monitoring method based on data clusters |
| CN105445577B (en) * | 2015-11-12 | 2019-03-22 | 全球能源互联网研究院 | A kind of power quality interference source industry and mining city method |
| CN105550450B (en) * | 2015-12-17 | 2020-10-13 | 国网智能电网研究院 | Electric energy quality interference source characteristic harmonic modeling method |
| CN108241863A (en) * | 2016-12-23 | 2018-07-03 | 全球能源互联网研究院 | The joint clustering method and device that a kind of high ferro power quality analysis data are selected |
| CN107064667A (en) * | 2017-01-11 | 2017-08-18 | 国家电网公司 | A kind of electrified railway traction load electricity quality evaluation system based on improvement gauss hybrid models |
| CN108428055B (en) * | 2018-03-12 | 2021-11-23 | 华南理工大学 | Load clustering method considering load longitudinal characteristics |
| CN108508294A (en) * | 2018-03-29 | 2018-09-07 | 深圳众厉电力科技有限公司 | A kind of high ferro electric energy quality monitoring system |
| CN108761227A (en) * | 2018-04-02 | 2018-11-06 | 深圳市益鑫智能科技有限公司 | A kind of high ferro power quality data processing system |
| CN109301837B (en) * | 2018-09-21 | 2020-08-25 | 中国科学院自动化研究所 | Method and device for judging whether high-speed rail line has train section or not based on electric energy quality data |
| CN110866840A (en) * | 2019-11-12 | 2020-03-06 | 南昌工程学院 | Database modeling method for power load characteristic quantity training based on knowledge graph |
| CN111007420B (en) * | 2019-12-26 | 2022-06-14 | 智洋创新科技股份有限公司 | Method for on-line screening performance of monomers in storage battery pack |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339208A (en) * | 2008-08-12 | 2009-01-07 | 中国矿业大学 | Voltage quality monitoring and perturb automatic classification method based on analysis in time-domain |
| CN101439726A (en) * | 2007-11-22 | 2009-05-27 | 保定市天河电子技术有限公司 | Method for detecting train passage situation and system thereof |
| CN102608452A (en) * | 2012-02-24 | 2012-07-25 | 安徽建筑工业学院 | High speed train equipment state and electric energy quality monitoring system and method |
| CN102981075A (en) * | 2012-11-22 | 2013-03-20 | 江苏省电力公司电力科学研究院 | Monitoring system of power quality recording data of high-speed electrified railway |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8661374B2 (en) * | 2011-09-14 | 2014-02-25 | Texas Instruments Incorporated | Placement aware clock gate cloning and fanout optimization |
-
2013
- 2013-12-13 CN CN201310676852.8A patent/CN103777091B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101439726A (en) * | 2007-11-22 | 2009-05-27 | 保定市天河电子技术有限公司 | Method for detecting train passage situation and system thereof |
| CN101339208A (en) * | 2008-08-12 | 2009-01-07 | 中国矿业大学 | Voltage quality monitoring and perturb automatic classification method based on analysis in time-domain |
| CN102608452A (en) * | 2012-02-24 | 2012-07-25 | 安徽建筑工业学院 | High speed train equipment state and electric energy quality monitoring system and method |
| CN102981075A (en) * | 2012-11-22 | 2013-03-20 | 江苏省电力公司电力科学研究院 | Monitoring system of power quality recording data of high-speed electrified railway |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103777091A (en) | 2014-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103777091B (en) | A kind of high ferro electric energy quality monitoring data classification method based on K average | |
| CN107618519B (en) | A kind of fuel cell hybrid tramcar parameter matching combined optimization method | |
| CN103605757B (en) | High-speed rail power quality data sorting method based on SVM (support vector machine) | |
| Calderaro et al. | Optimal siting and sizing of stationary supercapacitors in a metro network using PSO | |
| CN107316125A (en) | A kind of active distribution network economical operation evaluation method based on economical operation domain | |
| CN104393590B (en) | Electrical network Transient Instability pattern INTELLIGENT IDENTIFICATION method | |
| CN108537281A (en) | A kind of power consumer feature recognition sorting technique based on random forest | |
| CN112712281B (en) | Cloud model-based energy storage working condition adaptability comprehensive evaluation method and system | |
| Wang et al. | An efficient optimal sizing strategy for a hybrid electric air-ground vehicle using adaptive spiral optimization algorithm | |
| CN106899014A (en) | A kind of modeling and forecasting method of the electric railway load decomposed based on waveform | |
| Lee et al. | Learning to recognize driving patterns for collectively characterizing electric vehicle driving behaviors | |
| Wang et al. | Power allocation strategy for urban rail HESS based on deep reinforcement learning sequential decision optimization | |
| Zhang et al. | A double‐deep Q‐network‐based energy management strategy for hybrid electric vehicles under variable driving cycles | |
| CN108508294A (en) | A kind of high ferro electric energy quality monitoring system | |
| Li et al. | Incentive learning-based energy management for hybrid energy storage system in electric vehicles | |
| Qu et al. | Optimization research on hybrid energy storage system of high‐speed railway | |
| Gao et al. | Hyper-spherical search optimized fuzzy logic control considering operating conditions for hybrid tram | |
| CN104156605A (en) | Method and device for establishing motor vehicle state comprehensive assessment system | |
| Luo et al. | Parallel-reinforcement-learning-based online energy management strategy for energy storage traction substations in electrified railroad | |
| Feng et al. | Assessing energy consumption of high-speed trains based on mechanical energy | |
| Calderaro et al. | Deterministic vs heuristic algorithms for eco-driving application in metro network | |
| Yang et al. | Hierarchical energy management of a hybrid propulsion system considering speed profile optimization | |
| Wang et al. | Fuzzy control strategy for a compound energy system for an urban rail train based on the required power | |
| Wang et al. | Transmission ratio optimization of electric vehicle powertrain | |
| CN108983635B (en) | Stability analysis method for CRH5 type motor train unit input multi-grid electric coupling system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160118 Address after: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant after: State Grid Corporation of China Applicant after: State Grid Smart Grid Institute Applicant after: Jiangsu Electric Power Company Address before: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant before: State Grid Corporation of China Applicant before: State Grid Smart Grid Institute |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |