CN106374514A - Three-phase imbalance governing device with field vibration wireless warning function and implementing method thereof - Google Patents
Three-phase imbalance governing device with field vibration wireless warning function and implementing method thereof Download PDFInfo
- Publication number
- CN106374514A CN106374514A CN201610980556.0A CN201610980556A CN106374514A CN 106374514 A CN106374514 A CN 106374514A CN 201610980556 A CN201610980556 A CN 201610980556A CN 106374514 A CN106374514 A CN 106374514A
- Authority
- CN
- China
- Prior art keywords
- data
- voltage
- voltage dip
- electrical network
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/26—Arrangements for eliminating or reducing asymmetry in polyphase networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/50—Arrangements for eliminating or reducing asymmetry in polyphase networks
Abstract
The invention provides a three-phase imbalance governing device with a field vibration wireless warning function and an implementing method thereof. Current feature data of a power grid is acquired by a data acquisition unit; a voltage sag knowledge base forming unit extracts data with the same feature type with the feature data from historical data, carries out classification on the extracted data to form a sample set according to a preset category attribute, and further screens out data which meets preset conditions from the sample set to form a voltage sag strong-association rule knowledge base; an identification unit determines a current voltage sag reason of the power grid according to the current feature data of the power grid in the voltage sag strong-association rule knowledge base; and a governing unit determines a power grid electric energy quality governance compensation scheme according to the current voltage sag reason, and carries out compensation on a voltage at a user side according to the power grid electric energy quality governance compensation scheme. By implementing the three-phase imbalance governing device with the field vibration wireless warning function and the implementing method thereof, which are provided by the invention, dependence on a waveform is avoided, strong-association rules in historical voltage sags are mined on the basis of analysis on the historical data, and prediction and governance on a future voltage sag possibility are achieved.
Description
Technical field
The present invention relates to quality of power supply three-phase imbalance Treatment process field, more particularly, to scene vibration radio alarm function
Three-phase imbalance controlling device and its implementation.
Background technology
With science and technology and industrial expansion, the requirement to the quality of power supply for the very high industrial user of many automaticities
More and more higher.In production or IT Enterprises, due to most of device and SCM Based digitial controller or electric power
Electronic device is all very sensitive to various electromagnetic interference, and the therefore very slight disturbance of electrical network all can lead to the said goods can not be just
Often work or some function reduction are so that enterprise suffers huge loss.
Currently preferably electric power signal has the three phase sine waveform of fixed frequency and amplitude, but in actual life,
Due to the unsymmetry of fault, circuit and equipment, startup of bulk loads etc. so that electric power signal produces the phenomenon deviateing
It is referred to as power quality problem.
In the research of the quality of power supply, most important analysis the reason be exactly quality of power supply event, if can quickly know
The reason event occurs, has important meaning for prevention and failure removal.In conventional art, to the quality of power supply analysis of causes
Research be based primarily upon experiment and the emulation of electrical network three-phase imbalance, but the conventional art Shortcomings based on experiment and emulation
Part, it is disadvantageous in that: one, electrical network is much complicated than analogue system, the model of simplification cannot simulated real system completely,
Thus producing error；2nd, the testing equipment in electrical network is only able to detect the temporary range of decrease degree of voltage dip and persistent period it is impossible to note
The waveform of record super large data volume, thus deviation in the reason lead to quality of power supply event analysis.
In addition, the scene of three-phase imbalance controlling device is not when having attendant on duty, need anti-illegal-inbreak, mesh
The means of front more effectively anti-illegal-inbreak are to adopt vibration detecting, are perceived by vibration detector during illegal invasion and send out
The vibration signal going out, sends scene alarm, to improve its operation stability after vibration signal being processed by circuit.
Content of the invention
Embodiment of the present invention technical problem to be solved is, provides the three-phase with scene vibration radio alarm function
Uneven controlling device and implementation method, it is to avoid the dependence to waveform, based on the analysis of historical data, excavate history voltage dip
In Strong association rule, reach the prediction to following voltage dip probability and improvement.
In order to solve above-mentioned technical problem, the three-phase embodiments providing with live vibrating alert function is uneven
Weighing apparatus controlling device, described three-phase imbalance controlling device includes:
Data capture unit, the characteristic current for obtaining electrical network, the characteristic type of described characteristic includes electricity
The pressure time that temporarily the three-phase temporary range of decrease degree of fall, three phase durations of voltage dip and voltage dip occur；
Voltage dip knowledge base forms unit, has same characteristic features for extracting from historical data with described characteristic
The data of type, and according to default category attribute, classification formation sample set is carried out to the data of described extraction, and further
The data formation voltage dip Strong association rule knowledge base meeting predetermined condition is filtered out in described sample set；
Recognition unit is for according to the described electrical network current signature data getting, strong in the voltage dip of described formation
In correlation rule knowledge base, determine the current voltage sag reason of electrical network；
Governance unit, for temporarily dropping reason according to the current voltage of described determination, determines that electrical network power quality controlling compensates
Scheme, and according to the electrical network power quality controlling compensation scheme of described determination, user side voltage is compensated；
Live vibrating alert unit, including vibration signal detector, rc wave filter, alarm master controller, vibration signal is visited
Survey device live vibration signal is detected and be input to alarm master controller by rc wave filter, a/d signal sampling module, described
Alarm master controller is connected with the audible-visual annunciator for scene alarm, and alarm master controller is also associated with RF transceiver i,
Also include 485 gateway nodes, this 485 gateway node include RF transceiver ii, serial data communication module,
485 drive circuits, 485 interfaces, between described RF transceiver i and RF transceiver ii, less radio-frequency connects, and realizes vibration
The radio communication of the signal between the vibration signal of signal sensor and 485 gateway nodes.
Wherein, described voltage dip knowledge base forms unit and includes:
Data preprocessing module, for extracting the number with described characteristic with same characteristic features type from historical data
According to, and the described data extracted is carried out sliding-model control；
Sample set forms module, for according to default category attribute, the data of described sliding-model control is carried out point
Class, forms sample set；
Voltage dip knowledge base forms module, for carrying out apriori calculating to the sample set of described formation, filters out
Support that the data that angle value is more than the first preset value forms sample relation integration, and the sample relation integration of described formation is entered again
Row apriori calculates, and filters out the data formation voltage dip Strong association rule knowledge base that confidence value is more than the second preset value.
Wherein, described recognition unit includes:
Decision tree setup module, for the voltage dip Strong association rule knowledge base according to described formation and default classification
Attribute, by id3 algorithm, obtains the minimum decision tree of the corresponding comentropy of each pre-set categories attribute；
Voltage sag reason identification module, for according to the described electrical network current signature data getting, obtaining from described
The minimum decision tree of the corresponding comentropy of each pre-set categories attribute in, determine the reason electrical network current voltage temporarily drops.
Wherein, described voltage sag reason identification module includes:
Voltage dip matched sub-block, for using cbr inference method by the described electrical network current signature data getting
The decision tree minimum with the described corresponding comentropy of each category attribute obtaining is mated；
Detection sub-module, for when there is matching condition, detecting whether the matching condition of described presence is unique rule；
First identification submodule, for when being uniquely rule when the matching condition described presence is detected it is determined that described
The reason uniquely rule temporarily drops for described electrical network current voltage；
Second identification submodule, during for corresponding to many rules when the matching condition described presence is detected, obtains described
To support angle value be ranked up with confidence value, determine support angle value be corresponding regular conduct during maximum with confidence value
The reason described electrical network current voltage temporarily drops.
Wherein, when described default category attribute includes that voltage dip is separate, voltage dip amplitude, voltage dip continue
Between, voltage dip time of origin and transmission characteristic；Wherein, described voltage dip is separate includes one and mutually temporarily drops biphase temporary liter, biphase
Temporarily fall one mutually temporarily rises, three-phase temporarily drops and biphase temporary fall one is mutually constant；Described voltage dip amplitude is the current electricity of voltage dip
Ratio between pressure value and standard voltage value；Described voltage dip time of origin includes the working time model of default bulk loads
Enclose the run time scope leading to fault with thunderstorm, and the working time scope of described bulk loads is led to described thunderstorm
The run time scope sum of fault is one day；It is 1 that described transmission characteristic includes active event that value is 0 and value
Passive event.
The embodiment of the present invention additionally provides the realization side of the three-phase imbalance controlling device with live vibrating alert function
Method, it is realized on aforesaid device, and methods described includes:
S1, obtain the current characteristic of electrical network, the three-phase that the characteristic type of described characteristic includes voltage dip is temporary
The time that range of decrease degree, three phase durations of voltage dip and voltage dip occur；
S2, extract from historical data, with described characteristic, there is the data of same characteristic features type, and according to default
Category attribute, carries out classification formation sample set to the data of described extraction, and filters out in described sample set further
The data meeting predetermined condition forms voltage dip Strong association rule knowledge base；
S3, according to the described electrical network current signature data getting, know in the voltage dip Strong association rule of described formation
Know in storehouse, determine the current voltage sag reason of electrical network；And
S4, reason is temporarily dropped according to the current voltage of described determination, determine electrical network power quality controlling compensation scheme, and according to
The electrical network power quality controlling compensation scheme of described determination compensates to user side voltage.
Wherein, described step s2 specifically includes:
Extract from historical data and with described characteristic there is the data of same characteristic features type, and extract described
Data carries out sliding-model control；
According to default category attribute, the data of described sliding-model control is classified, form sample set；
Apriori calculating is carried out to the sample set of described formation, filters out the number supporting angle value to be more than the first preset value
According to formation sample relation integration, and again apriori calculating is carried out to the sample relation integration of described formation, filter out confidence level
Value forms voltage dip Strong association rule knowledge base more than the data of the second preset value.
Wherein, described step s3 specifically includes:
Voltage dip Strong association rule knowledge base according to described formation and default category attribute, by id3 algorithm, obtain
To the decision tree that the corresponding comentropy of each pre-set categories attribute is minimum；
According to the described electrical network current signature data getting, from the described corresponding letter of each pre-set categories attribute obtaining
In the minimum decision tree of breath entropy, determine the reason electrical network current voltage temporarily drops.
Wherein, the described voltage dip Strong association rule knowledge base according to described formation and default category attribute, pass through
Id3 algorithm, the concrete steps obtaining the minimum decision tree of the corresponding comentropy of each pre-set categories attribute include:
A, using the data in the voltage dip Strong association rule knowledge base of described formation as training data；
B, the letter according to each pre-set categories attribute comprising in the described default category attribute described training data of calculating
Breath gain, selects information gain maximum as the Split Attribute of root node, and calculates decision ruless and pass to ground floor
Prefix information；
C, judge whether to create new decision ruless；If it is, execution next step d；If it is not, then, jump to
Step e；
D, the new decision ruless of described generation are saved in rule set, delete simultaneously and in described training data, comprise institute
State the sample of the new decision ruless of generation, produce new data set, and using the new data set of described generation as described instruction
After practicing data, return to step b；
E, continue to determine whether to produce new prefix information；If it is, execution next step f；If it is not, then, redirect
To step i；
F, the decision tree number of plies add one；
G, judge the number of plies of described decision tree whether less than the sum of all properties comprising in described training data；If
It is then to execute next step h；If it is not, then, jump to step i；
H, calculate under described new prefix information, the information of each pre-set categories attribute comprising in described training data
Gain, selects the Split Attribute of the number of plies corresponding node as described current decision tree for the information gain maximum, and calculates decision-making
Rule and the prefix information passing to next layer, return to step c；
I, training terminate, and build decision tree according to described calculated decision ruless.
Wherein, the electrical network current signature data getting described in described basis, belongs to from the described each pre-set categories obtaining
Property the minimum decision tree of corresponding comentropy in, determine that the concrete steps of the reason electrical network current voltage temporarily drops include:
For using cbr inference method by the described electrical network current signature data getting and the described each classification obtaining
Minimum decision tree is mated the corresponding comentropy of attribute；
When there is matching condition, detect whether the matching condition of described presence is unique rule；
When the matching condition described presence is detected is uniquely rule it is determined that described unique rule is worked as described electrical network
The reason front voltage dip；
When the corresponding many rules of the matching condition described presence is detected, by the described support angle value obtaining and confidence level
Value is ranked up, and determines and supports that angle value is that corresponding rule during maximum temporarily drops as described electrical network current voltage with confidence value
The reason.
Implement the embodiment of the present invention, have the advantages that
The analysis based on historical data for the three-phase imbalance controlling device in the present invention, by carrying out to voltage dip event
Causality classification, the Strong association rule being excavated using apriori algorithm in history voltage dip forms voltage dip Strong association rule
Knowledge base, then using voltage dip Strong association rule knowledge base as training set, determine that current voltage temporarily drops reason, and corresponding
Electrical network power quality controlling compensation scheme compensates to user side voltage, thus avoiding the dependence to waveform, reaches to future
The purpose of the prediction of voltage dip probability.
In addition, the present invention also has live vibrating alert, anti-illegal-inbreak, can also wirelessly will shake simultaneously
Dynamic signal is wirelessly transferred and gives the host computer that 485 interfaces are connected, and realizes record and the wireless remote alarm work(of vibration signal data
Energy.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, according to
These accompanying drawings obtain other accompanying drawings and still fall within scope of the invention.
Fig. 1 is the system structure diagram of three-phase imbalance controlling device provided in an embodiment of the present invention；
Fig. 2 is the system structure diagram that in Fig. 1, voltage dip knowledge base forms unit；
Fig. 3 is the system structure diagram of recognition unit in Fig. 1；
Fig. 4 is the system structure diagram of voltage sag reason identification module in Fig. 3；
Fig. 5 is the flow chart of three-phase imbalance controlling device implementation method provided in an embodiment of the present invention；
Fig. 6 is the flow chart of step s3 in Fig. 5；
Fig. 7 is the flow chart of step s31 in Fig. 6；
Fig. 8 is the flow chart of step s32 in Fig. 6；
Fig. 9 is the application scenario diagram of step s3 in Fig. 6；
The theory diagram of Figure 10 scene vibration radio alarm unit.
Specific embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, the present invention is made into one
Step ground describes in detail.
As shown in figure 1, administering dress for the three-phase imbalance with live vibrating alert function provided in an embodiment of the present invention
Put, described device includes:
Data capture unit 110, the characteristic current for obtaining electrical network, the characteristic type of described characteristic includes
The time that the three-phase temporary range of decrease degree of voltage dip, three phase durations of voltage dip and voltage dip occur；
Voltage dip knowledge base forms unit 120, has identical for extraction from historical data and described characteristic
The data of characteristic type, and according to default category attribute, classification formation sample set is carried out to the data of described extraction, and enters
One step filters out the data formation voltage dip Strong association rule knowledge base meeting predetermined condition in described sample set；
Recognition unit 130, for according to the described electrical network current signature data getting, in the voltage dip of described formation
In Strong association rule knowledge base, determine the current voltage sag reason of electrical network；
Governance unit 140, for temporarily dropping reason according to the current voltage of described determination, determines that electrical network power quality controlling is mended
Repay scheme, and according to the electrical network power quality controlling compensation scheme of described determination, user side voltage is compensated.
As shown in Fig. 2 described voltage dip knowledge base forms unit 120 including:
Data preprocessing module 1201, has same characteristic features type for extracting from historical data with described characteristic
Data, and the described data extracted is carried out sliding-model control；
Sample set forms module 1202, for according to default category attribute, entering to the data of described sliding-model control
Row classification, forms sample set；
Voltage dip knowledge base forms module 1203, for apriori calculating is carried out to the sample set of described formation, sieve
Select the data supporting angle value to be more than the first preset value and form sample relation integration, and to the sample relation integration of described formation again
Secondary carry out apriori calculating, filter out confidence value be more than the second preset value data formed voltage dip Strong association rule know
Know storehouse.
As shown in figure 3, described recognition unit 130 includes:
Decision tree setup module 1301, for the voltage dip Strong association rule knowledge base according to described formation and default
Category attribute, by id3 algorithm, obtains the minimum decision tree of the corresponding comentropy of each pre-set categories attribute；
Voltage sag reason identification module 1302, for according to the described electrical network current signature data getting, from described
In the decision tree of each pre-set categories attribute corresponding comentropy minimum obtaining, determine the reason electrical network current voltage temporarily drops.
As shown in figure 4, described voltage sag reason identification module 1302 includes:
Voltage dip matched sub-block 13021, for using cbr inference method by the described electrical network current signature getting
The decision tree minimum with the described corresponding comentropy of each category attribute obtaining is mated data；
Detection sub-module 13022, for when there is matching condition, detecting whether the matching condition of described presence is unique
Rule；
First identification submodule 13023, for when detect described presence matching condition be uniquely rule when it is determined that
The reason described unique rule temporarily drops for described electrical network current voltage；
Second identification submodule 13024, during for corresponding to many rules when the matching condition described presence is detected, by institute
State the support angle value obtaining to be ranked up with confidence value, determine and support that angle value is corresponding rule during maximum with confidence value
The reason temporarily drop as described electrical network current voltage.
In embodiments of the present invention, default category attribute includes that voltage dip is separate, voltage dip amplitude, voltage dip
Persistent period, voltage dip time of origin and transmission characteristic；Wherein, voltage dip separate include one mutually temporarily drop biphase temporary liter, two
Mutually temporarily fall one mutually temporarily rises, three-phase temporarily drops and biphase temporary fall one is mutually constant；Voltage dip amplitude is the current voltage of voltage dip
Ratio between value and standard voltage value；Voltage dip time of origin includes working time scope and the thunder of default bulk loads
Rain leads to the run time scope of fault, and the working time scope of bulk loads leads to fault with described thunderstorm
Run time scope sum is one day；Transmission characteristic includes the active event that value is 0 and the passive event that value is 1.
As shown in figure 5, the three-phase imbalance with live vibrating alert function for, in the embodiment of the present invention, providing is administered
The implementation method of device, it is realized on above-mentioned device, and methods described includes:
The current characteristic of step s1, acquisition electrical network, the characteristic type of described characteristic includes the three of voltage dip
The time that mutually temporarily range of decrease degree, three phase durations of voltage dip and voltage dip occur；
Detailed process is to obtain the current characteristic of electrical network, this feature data is by the data shape of multiple characteristic type items
Become, the characteristic type of this feature data includes but is not limited to the three-phase temporary range of decrease degree of voltage dip, the three-phase of voltage dip continues
Time and the time of voltage dip generation.
Step s2, extract from historical data, with described characteristic, there is the data of same characteristic features type, and according to pre-
If category attribute, the data of described extraction is carried out with classification and forms sample set, and sieve in described sample set further
Select the data formation voltage dip Strong association rule knowledge base meeting predetermined condition；
Detailed process is, step s21, extracts the data with characteristic with same characteristic features type from historical data,
And the described data extracted is carried out sliding-model control；
Specifically, main carry out pretreatment to historical data, remove redundancy and the data damaged, thus reducing answering of data
Miscellaneous degree and process capacity, then individually extract some attributes needing according to the characteristic type in step s1, and will
Historical data carries out sliding-model control, becomes the multiple data blocks for ease of analyzing and calculate.
Step s22, according to default category attribute, the data of described sliding-model control is classified, formed sample set
Close；
Specifically, pre-setting five features as category attribute, and according to default five features to sliding-model control
Data classified, formed sample set m；Wherein, five features are respectively that voltage dip is separate, voltage dip amplitude, electricity
Persistent period, voltage dip time of origin and transmission characteristic temporarily drop in pressure.
Because voltage is three-phase, therefore biphase temporary liter mutually temporarily drops in the separate inclusion one of voltage dip, biphase temporary fall one mutually temporarily rises,
Three-phase temporarily drops and biphase temporary fall one is mutually constant etc..Voltage dip amplitude is current voltage value and the standard voltage value of voltage dip
Between ratio；As an example, temporarily the current voltage value of fall voltage is 198v, and normal voltage is 220v, and calculate is temporary
Range of decrease degree is 0.9.The time that the voltage dip persistent period terminates for voltage dip deducts the time that it starts.Due to leading to voltage
The fault that temporarily most important two factors of fall start for bulk loads and thunderstorm causes, therefore voltage dip time of origin
Also serve as a key character, and operate between load operationally, thunderstorm all may be distributed in whole day, therefore voltage dip is sent out
The raw time can be set to one day 24 hours, mark off the working time scope of bulk loads as needed and thunderstorm leads in one day
The run time scope of fault；As an example, am8:00 to pm5:00 is preset as the working time of bulk loads
Scope, remaining time, (after same day pm5:00 to second day am8:00) was preset as the run time model that thunderstorm leads to fault
Enclose, measurable startup for bulk loads is caused therefore the reason voltage dip in am8:00 to pm5:00, and in am8:
The reason outside 00 to pm5:00, voltage dip in the time period measurable for thunderstorm fault.It is 0 that transmission characteristic includes value
Active event (source event) and the passive event that value is 1.Active event (source event) all has extraneous factor to cause, and quilt
Dynamic event is propagated in electrical network by existing voltage dip event and is caused.
Step s23, the sample set to described formation carry out apriori calculating, filter out support angle value pre- more than first
If the data of value forms sample relation integration, and carries out apriori calculating again to the sample relation integration of described formation, screening
Go out the data formation voltage dip Strong association rule knowledge base that confidence value is more than the second preset value.
Specifically, apriori calculating, and the definition according to the first preset value are carried out to the sample set m being formed, if
Degree of holding is less than this first preset value, then need again to be calculated according to apriori, therefore the sample set m being formed is being carried out
After apriori calculates, the support angle value finally giving should be greater than the first preset value, and it is default more than first to filter out support angle value
The data of value forms sample relation integration, and carries out apriori calculating again to this sample relation integration；In the same manner, according to second
The definition of preset value, if confidence value is less than this second preset value, needs again to enter again on the basis of sample relation integration
Row apriori calculates, and the confidence value finally giving should be greater than this second preset value.Preset due to supporting that angle value is more than first
Value, and confidence value is more than the second preset value, then show that sample set m has relatedness after apriori calculating, meet pre-
Fixed strength of association, thus forming voltage dip Strong association rule knowledge base, in order to carry out this knowledge base as training set
Build decision tree.
Step s3, according to the described electrical network current signature data getting, associate by force rule in the voltage dip of described formation
Then in knowledge base, determine the current voltage sag reason of electrical network；
Detailed process is, as shown in fig. 6, the concrete steps of step s3 are accomplished by
Step s31, the voltage dip Strong association rule knowledge base according to described formation and default category attribute, pass through
Id3 algorithm, obtains the minimum decision tree of the corresponding comentropy of each pre-set categories attribute；
Step s32, according to the described electrical network current signature data getting, from the described each pre-set categories attribute obtaining
In the minimum decision tree of corresponding comentropy, determine the reason electrical network current voltage temporarily drops.
In step s31, decision tree is built using id3 algorithm.The fork attribute selecting every time all makes comentropy maximum
Reduce.If all samples belong to same class in a sample set, now comentropy is minimum；If broadly falling into different classes,
Now comentropy is maximum.Let s be the set of n data sample, sample set is divided into c different class ci(i=1,2 ...,
C), each class ciThe number of samples containing is ni, then the comentropy that s is divided into c class is
Wherein, pi is that in s, sample belongs to the i-th class ciProbability, that is,
Assume that the collection of all different values of attribute a is combined into xa, svThe sample set for v for the value of attribute a in s, i.e. sv={ s
∈ s | a (s)=v }.Sample set s on each branch node after selecting attribute a, to this nodevThe entropy of classification is e
(sv).The expectation entropy that a leads to is selected to be defined as each subset svEntropy weighted sum, weights be belong to svSample account for original sample
The ratio of this sI.e. expectation entropy is
Wherein, e (sv) it is by svIn sample be divided into the comentropy of c class.The information relative to sample set s for the attribute a increases
(s a) is defined as beneficial gain
Gain (s, a)=e (s)-e (s, a)
Select every time to make the maximum attribute of information gain, now, comentropy reduces at most.
Therefore, as shown in fig. 7, step s31 to implement step as follows:
Step s310, using the data in voltage dip Strong association rule knowledge base as training data；
Step s320, the information according to each pre-set categories attribute comprising in default category attribute calculating training data
Gain, selects information gain maximum as the Split Attribute of root node, and before calculating decision ruless and passing to ground floor
Sew information；
Step s330, judge whether to create new decision ruless；If it is, execution next step s340；If not,
Then jump procedure s350,
Step s340, by produce new decision ruless be saved in rule set, simultaneously delete training data in comprise produce
The sample of raw new decision ruless, produces new data set, using this new data set as after training data, return to step
s320；
Step s350, continue to determine whether to produce new prefix information；If it is, execution next step s360；If
No, then jump to step s390；
Step s360, the decision tree number of plies add one；
Step s370, judge the number of plies of this decision tree whether less than the sum of all properties comprising in training data；As
Fruit is then to execute next step s380；If it is not, then jumping to step s390；
Step s380, calculate under new prefix information, the information of each pre-set categories attribute comprising in training data
Gain, selects information gain maximum as the Split Attribute of the number of plies corresponding node of current decision tree, and calculates decision ruless
And pass to the prefix information of next layer, return to step s330；
Step s390, training terminate, and build decision tree according to calculated decision ruless.
In step s32, as shown in figure 8, the concrete steps of step s32 are accomplished by
Specifically, step s321, for using cbr inference method by the described electrical network current signature data getting and institute
State the minimum decision tree of the corresponding comentropy of each category attribute obtaining to be mated；
Step s322, when there is matching condition, detect described presence matching condition whether be unique rule；
Step s323, when detect described presence matching condition be uniquely rule when it is determined that described unique rule is
The reason described electrical network current voltage temporarily drops；
Step s324, when the corresponding many rules of the matching condition described presence is detected, by the described support obtaining
Value is ranked up with confidence value, determines and supports that angle value and confidence value are that corresponding rule during maximum is worked as described electrical network
The reason front voltage dip；Wherein, support that angle value is ranked up from high to low with confidence value.
As an example, as shown in figure 9, electrical network is current to be determined in step s32 to the decision tree obtaining in step s31
The application scenarios of voltage sag reason further illustrate:
Using separate for voltage dip as with reference to attribute, being set to root node, the matching condition of setting to should have a plurality of rule,
Including voltage dip separate temporarily drop for three-phase, voltage dip amplitude > 40% and voltage dip time of origin be am8:00 extremely
Three rules of pm5:00, therefore when finding have a temporary range of decrease degree to be 50%, occur when the three-phase of am9:00 temporarily drops, permissible
Preliminary judgement is that bulk loads startup leads to.
Step s4, reason is temporarily dropped according to the current voltage of described determination, determine electrical network power quality controlling compensation scheme, and
According to the electrical network power quality controlling compensation scheme of described determination, user side voltage is compensated.
Implement the embodiment of the present invention, have the advantages that
The analysis based on historical data for the device in the present invention, by carrying out causality classification to voltage dip event, adopts
The Strong association rule that apriori algorithm excavates in history voltage dip forms voltage dip Strong association rule knowledge base, then by electricity
Pressure temporarily drops Strong association rule knowledge base as training set, determines that current voltage temporarily drops reason, and the corresponding electrical network quality of power supply
Administer compensation scheme user side voltage is compensated, thus avoiding the dependence to waveform, reaching may to following voltage dip
The purpose of the prediction of property.
As shown in Figure 10, the present invention also has live vibrating alert unit, including vibration signal detector, rc wave filter,
Alarm master controller, vibration signal detector live vibration signal is detected and to pass through rc wave filter, a/d signal sampling module defeated
Enter to alarm master controller, described alarm master controller is connected with for the live audible-visual annunciator alerting, and alerts main control
RF transceiver i is also associated with device, also includes 485 gateway nodes, this 485 gateway node include RF transceiver ii,
Serial data communication module, 485 drive circuits, 485 interfaces, wireless between described RF transceiver i and RF transceiver ii
Radio frequency connects, and realizes the radio communication of the signal between the vibration signal of vibration signal detector and 485 gateway nodes.
In addition, lcd display screen, keyboard interface and memory element are also associated with described master controller.The present embodiment institute
The alarm master controller stated adopts the arm7tdmi-s microcontroller lpc2368 of nxp company.
It should be noted that in said apparatus embodiment, each included system unit simply enters according to function logic
Row divides, but is not limited to above-mentioned division, as long as being capable of corresponding function；In addition, each functional unit
Specific name also only to facilitate mutual distinguish, is not limited to protection scope of the present invention.
One of ordinary skill in the art will appreciate that it is permissible for realizing all or part of step in above-described embodiment method
Instruct related hardware to complete by program, described program can be stored in a computer read/write memory medium,
Described storage medium, such as rom/ram, disk, CD etc..
Above disclosed be only present pre-ferred embodiments, certainly the right model of the present invention can not be limited with this
Enclose, the equivalent variations therefore made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (10)
1. a kind of with scene vibration radio alarm function three-phase imbalance controlling device it is characterised in that described three-phase not
Balance controlling device includes:
Data capture unit, the characteristic current for obtaining electrical network, it is temporary that the characteristic type of described characteristic includes voltage
The time that the three-phase temporary range of decrease degree of fall, three phase durations of voltage dip and voltage dip occur；
Voltage dip knowledge base forms unit, has same characteristic features type for extracting from historical data with described characteristic
Data, and according to default category attribute, classification is carried out to the data of described extraction and forms sample set, and further in institute
State and in sample set, filter out the data formation voltage dip Strong association rule knowledge base meeting predetermined condition；
Recognition unit, for according to the described electrical network current signature data getting, associating by force in the voltage dip of described formation
In rule-based knowledge base, determine the current voltage sag reason of electrical network；
Governance unit, for temporarily dropping reason according to the current voltage of described determination, determines electrical network power quality controlling compensation scheme,
And according to the electrical network power quality controlling compensation scheme of described determination, user side voltage is compensated；
Live vibrating alert unit, including vibration signal detector, rc wave filter, alarm master controller, vibration signal detector
Live vibration signal is detected and alarm master controller is input to by rc wave filter, a/d signal sampling module, described alarm
Master controller is connected with the audible-visual annunciator for scene alarm, and alarm master controller is also associated with RF transceiver i,
Also include 485 gateway nodes, this 485 gateway node include RF transceiver ii, serial data communication module, 485
Drive circuit, 485 interfaces, between described RF transceiver i and RF transceiver ii, less radio-frequency connects, and realizes vibration signal
The radio communication of the signal between the vibration signal of detector and 485 gateway nodes.
2. three-phase imbalance controlling device as claimed in claim 1 is it is characterised in that described voltage dip knowledge base forms list
Unit includes:
Data preprocessing module, for extracting the data with described characteristic with same characteristic features type from historical data,
And the described data extracted is carried out sliding-model control；
Sample set forms module, for according to default category attribute, classifying, shape to the data of described sliding-model control
Become sample set；
Voltage dip knowledge base forms module, for carrying out apriori calculating to the sample set of described formation, filters out support
The data that angle value is more than the first preset value forms sample relation integration, and the sample relation integration of described formation is carried out again
Apriori calculates, and filters out the data formation voltage dip Strong association rule knowledge base that confidence value is more than the second preset value.
3. three-phase imbalance controlling device as claimed in claim 1 is it is characterised in that described recognition unit includes:
Decision tree setup module, belongs to for the voltage dip Strong association rule knowledge base according to described formation and default classification
Property, by id3 algorithm, obtain the minimum decision tree of the corresponding comentropy of each pre-set categories attribute；
Voltage sag reason identification module, for according to the described electrical network current signature data getting, from described obtain every
In the minimum decision tree of the corresponding comentropy of one pre-set categories attribute, determine the reason electrical network current voltage temporarily drops.
4. three-phase imbalance controlling device as claimed in claim 3 is it is characterised in that described voltage sag reason identification module
Including:
Voltage dip matched sub-block, for using cbr inference method by the described electrical network current signature data getting and institute
State the minimum decision tree of the corresponding comentropy of each category attribute obtaining to be mated；
Detection sub-module, for when there is matching condition, detecting whether the matching condition of described presence is unique rule；
First identification submodule, for when being uniquely rule when the matching condition described presence is detected it is determined that described unique
The reason rule temporarily drops for described electrical network current voltage；
Second identification submodule, for when the corresponding many rules of the matching condition described presence is detected, obtains described
Support that angle value is ranked up with confidence value, determine and support that angle value is corresponding rule during maximum as described with confidence value
The reason electrical network current voltage temporarily drops.
5. the three-phase imbalance controlling device as any one of claim 1-4 is it is characterised in that described default classification
Attribute includes that voltage dip is separate, voltage dip amplitude, the voltage dip persistent period, voltage dip time of origin and transmission special
Property；Wherein, described voltage dip separate include one mutually temporarily dropping biphase temporary liter, biphase temporary fall one mutually temporarily rises, three-phase temporarily drops and two
Mutually temporarily fall one is mutually constant；Described voltage dip amplitude is the ratio between the current voltage value of voltage dip and standard voltage value；
Described voltage dip time of origin includes the working time scope of default bulk loads and thunderstorm leads to the operation of fault
Time range, and the working time scope of described bulk loads leads to the run time scope sum of fault with described thunderstorm
For one day；Described transmission characteristic includes the active event that value is 0 and the passive event that value is 1.
6. a kind of with scene vibration radio alarm function three-phase imbalance controlling device implementation method it is characterised in that
It is realized on the three-phase imbalance controlling device as any one of claim 1-5, and methods described includes:
The current characteristic of s1, acquisition electrical network, the characteristic type of described characteristic includes the temporary range of decrease of three-phase of voltage dip
The time that degree, three phase durations of voltage dip and voltage dip occur；
S2, extract from historical data, with described characteristic, there is the data of same characteristic features type, and according to default classification
Attribute, carries out classification formation sample set to the data of described extraction, and filters out satisfaction in described sample set further
The data of predetermined condition forms voltage dip Strong association rule knowledge base；
S3, according to the described electrical network current signature data getting, in the voltage dip Strong association rule knowledge base of described formation
In, determine the current voltage sag reason of electrical network；And
S4, reason is temporarily dropped according to the current voltage of described determination, determine electrical network power quality controlling compensation scheme, and according to described
The electrical network power quality controlling compensation scheme determining compensates to user side voltage.
7. method as claimed in claim 6 is it is characterised in that described step s2 specifically includes:
Extract from historical data, with described characteristic, there is the data of same characteristic features type, and by the described data extracted
Carry out sliding-model control；
According to default category attribute, the data of described sliding-model control is classified, form sample set；
Apriori calculating is carried out to the sample set of described formation, filters out the data shape supporting angle value to be more than the first preset value
Become sample relation integration, and again apriori calculating is carried out to the sample relation integration of described formation, filter out confidence value big
Data in the second preset value forms voltage dip Strong association rule knowledge base.
8. method as claimed in claim 6 is it is characterised in that described step s3 specifically includes:
Voltage dip Strong association rule knowledge base according to described formation and default category attribute, by id3 algorithm, obtain every
The minimum decision tree of the corresponding comentropy of one pre-set categories attribute；
According to the described electrical network current signature data getting, from the described corresponding comentropy of each pre-set categories attribute obtaining
In minimum decision tree, determine the reason electrical network current voltage temporarily drops.
9. method as claimed in claim 8 is it is characterised in that the described voltage dip Strong association rule according to described formation is known
Know storehouse and default category attribute, by id3 algorithm, obtain the minimum decision tree of the corresponding comentropy of each pre-set categories attribute
Concrete steps include:
A, using the data in the voltage dip Strong association rule knowledge base of described formation as training data；
B, the information increasing according to each pre-set categories attribute comprising in the described default category attribute described training data of calculating
Benefit, selects information gain maximum as the Split Attribute of root node, and calculates decision ruless and the prefix passing to ground floor
Information；
C, judge whether to create new decision ruless；If it is, execution next step d；If it is not, then, jump to step
e；
D, the new decision ruless of described generation are saved in rule set, delete simultaneously and in described training data, comprise described product
The sample of raw new decision ruless, produces new data set, and using the new data set of described generation as described training number
According to rear, return to step b；
E, continue to determine whether to produce new prefix information；If it is, execution next step f；If it is not, then, jump to step
Rapid i；
F, the decision tree number of plies add one；
G, judge the number of plies of described decision tree whether less than the sum of all properties comprising in described training data；If it is,
Then execute next step h；If it is not, then, jump to step i；
, under described new prefix information, the information of each pre-set categories attribute comprising in described training data increases for h, calculating
Benefit, selects the Split Attribute of the number of plies corresponding node as described current decision tree for the information gain maximum, and calculates decision-making rule
Then and pass to the prefix information of next layer, return to step c；
I, training terminate, and build decision tree according to described calculated decision ruless.
10. method as claimed in claim 8 is it is characterised in that the electrical network current signature data that gets described in described basis,
From the minimum decision tree of the described corresponding comentropy of each pre-set categories attribute obtaining, determine what electrical network current voltage temporarily dropped
The concrete steps of reason include:
For using cbr inference method by the described electrical network current signature data getting and the described each category attribute obtaining
Minimum decision tree is mated corresponding comentropy；
When there is matching condition, detect whether the matching condition of described presence is unique rule；
When the matching condition described presence is detected is uniquely rule it is determined that described unique rule is currently electric for described electrical network
The reason pressure temporarily drops；
When the corresponding many rules of the matching condition described presence is detected, the described support angle value obtaining is entered with confidence value
Row sequence, determines and supports that angle value and confidence value are that corresponding rule during maximum is former as the temporary fall of described electrical network current voltage
Cause.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610980556.0A CN106374514A (en) | 2016-11-08 | 2016-11-08 | Three-phase imbalance governing device with field vibration wireless warning function and implementing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610980556.0A CN106374514A (en) | 2016-11-08 | 2016-11-08 | Three-phase imbalance governing device with field vibration wireless warning function and implementing method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106374514A true CN106374514A (en) | 2017-02-01 |
Family
ID=57894349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610980556.0A Pending CN106374514A (en) | 2016-11-08 | 2016-11-08 | Three-phase imbalance governing device with field vibration wireless warning function and implementing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106374514A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221682A (en) * | 2008-01-21 | 2008-07-16 | 徐承东 | Wireless vibration detecting and warning system |
| CN104463706A (en) * | 2014-12-10 | 2015-03-25 | 深圳供电局有限公司 | Method and system for power grid to detect reasons of voltage sag incident |
| CN105471096A (en) * | 2014-09-12 | 2016-04-06 | 张万生 | Micro-network intelligent monitoring system based on multiple heterogeneous information fusion technology |
-
2016
- 2016-11-08 CN CN201610980556.0A patent/CN106374514A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221682A (en) * | 2008-01-21 | 2008-07-16 | 徐承东 | Wireless vibration detecting and warning system |
| CN105471096A (en) * | 2014-09-12 | 2016-04-06 | 张万生 | Micro-network intelligent monitoring system based on multiple heterogeneous information fusion technology |
| CN104463706A (en) * | 2014-12-10 | 2015-03-25 | 深圳供电局有限公司 | Method and system for power grid to detect reasons of voltage sag incident |
Non-Patent Citations (1)
| Title |
|---|
| 吴昌汉 等: "采用SVG技术治理三相电压不平衡", 《天然气与石油》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104463706B (en) | A kind of method and system that voltage dip business reasons are detected for power network | |
| CN111931860A (en) | Abnormal data detection method, device, equipment and storage medium | |
| CN102881125B (en) | Alarm monitoring system based on multi-information fusion centralized processing platform | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| JP2018170006A (en) | Generic framework to detect cyber threats in electric power grid | |
| CN109840157A (en) | Method, apparatus, electronic equipment and the storage medium of fault diagnosis | |
| CN111352971A (en) | Bank system monitoring data anomaly detection method and system | |
| CN107450426A (en) | Foundation pit construction deformable statistical analysis method and system | |
| CN107633050A (en) | A kind of method that stealing probability is judged based on big data analysis electricity consumption behavior | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN106056879B (en) | A kind of ammeter remote monitoring system based on intelligent recognition | |
| CN105282758A (en) | Self-adaptive dynamic construction method of WIFI indoor positioning system fingerprint database | |
| CN105627528A (en) | Alarm method for cold station group control system | |
| CN103592587A (en) | Partial discharge diagnosis method based on data mining | |
| CN103746831A (en) | Alarm analysis method, device and system | |
| CN104267346A (en) | Remote fault diagnosis method of generator excitation system | |
| CN106153114A (en) | A kind of remotely control intelligent building monitoring system | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN109002810A (en) | Model evaluation method, Radar Signal Recognition method and corresponding intrument | |
| CN105005852A (en) | Image analysis based intelligent monitoring system for dormitory environment | |
| CN103903398A (en) | Gas detection remote alarm, monitoring and control method based on mobile phone | |
| CN106451503A (en) | Three-phase unbalanced treatment device with temperature and vibration warning unit and realization method thereof | |
| CN110147827A (en) | A kind of failure prediction method based on IAALO-SVM and similarity measurement | |
| CN106600034A (en) | Three-phase unbalance governance device having in-situ temperature alarm function and realization method thereof | |
| CN106655225A (en) | Three-phase imbalance treatment device and realization method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170201 |
|
| RJ01 | Rejection of invention patent application after publication |