CN106932670B - A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory - Google Patents
A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory Download PDFInfo
- Publication number
- CN106932670B CN106932670B CN201710069321.0A CN201710069321A CN106932670B CN 106932670 B CN106932670 B CN 106932670B CN 201710069321 A CN201710069321 A CN 201710069321A CN 106932670 B CN106932670 B CN 106932670B
- Authority
- CN
- China
- Prior art keywords
- evidence
- indicate
- membership
- formula
- degree
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 206010048669 Terminal state Diseases 0.000 claims abstract description 54
- 230000004927 fusion Effects 0.000 claims abstract description 27
- 238000003745 diagnosis Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims description 8
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 7
- 239000000571 coke Substances 0.000 claims description 6
- 230000011664 signaling Effects 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000020411 cell activation Effects 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 238000005315 distribution function Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 55
- 238000012423 maintenance Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Abstract
The invention discloses a kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory, step includes: that specified state characteristic quantity is counted from the operation information that distribution power automation terminal is uploaded to distribution main website；Distribution power automation terminal state is classified, structural regime characteristic quantity corresponds to the fuzzy membership function of different distribution power automation terminal states；Determine every degree of membership parameter of fuzzy membership function；Using distribution power automation terminal state classification results as single element proposition, Basic probability assignment function and evidence fusion result are calculated to single element proposition and framework of identification based on fuzzy membership function；Evidence fusion result and preset SOT state of termination diagnosis decision rule are matched, the current state of distribution power automation terminal is obtained.The present invention has the advantages that can accurately to judge using operation information that distribution power automation terminal device noumenon be in which kind of state, testing result are accurate and reliable, it is convenient and efficient to diagnose, have higher operability.
Description
Technical field
The present invention relates to distribution power automation terminal condition diagnosing technologies, and in particular to a kind of matching based on D-S evidence theory
Electric automation SOT state of termination diagnostic method.
Background technique
Can the operating status of distribution power automation terminal is directly related to entire electrical power distribution automatization system effectively play work
With.However, this kind of equipment is commonly mounted directly to outdoor or is located at easy screen type environment, vulnerable to adverse circumstances and external rings
The influence in border, devices from different manufacturers quality is irregular in addition, therefore the unknown exception of a variety of causes frequent occurrence.In order to grasp
The status information of terminal, to arrange maintenance in time before the failure occurs, it is necessary to carry out the presence diagnosis of terminal.
Distribution power automation terminal is a kind of electronic equipment of failure mechanism complexity, has profound associated letter with all kinds of failures
It number is often hidden in inside hardware, and existing terminal oneself state perception means lack, it is difficult to these signals are monitored
And analysis.Under conditions present, the operation information that distribution main website can only be uploaded to by distribution power automation terminal counts some shapes
State index, in this, as the characteristic quantity of the indirect reflection SOT state of termination.D-S evidence theory is that Dempster was mentioned first in 1967
Out, a kind of inexact reasoning further to be grown up by his student Shafer in 1976 is theoretical, also referred to as Dempster/
Shafer evidence theory (abbreviation D-S evidence theory), D-S evidence theory have processing not as a kind of uncertain reasoning method
The ability for determining information is mainly characterized by meeting and discusses weaker condition than Bayesian probability, has directly expression " uncertain "
The ability of " not knowing ".Therefore, it is directly diagnosed using D-S evidence theory and determines distribution power automation terminal state, but such as
What is directly diagnosed based on D-S evidence theory and determines distribution power automation terminal state, and a crucial skill urgently to be resolved is had become
Art problem.
Summary of the invention
The technical problem to be solved in the present invention: in view of the above problems in the prior art, providing one kind can be using operation letter
Breath accurately judge distribution power automation terminal device noumenon be in which kind of state, testing result are accurate and reliable, diagnose facilitate it is fast
The distribution power automation terminal method for diagnosing status based on D-S evidence theory that is prompt, having higher operability.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention are as follows:
A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory, step include:
1) specified state characteristic quantity is counted from the operation information that distribution power automation terminal is uploaded to distribution main website；
2) distribution power automation terminal state is classified, structural regime characteristic quantity corresponds to different distribution power automation terminal states
Fuzzy membership function；
3) every degree of membership parameter of fuzzy membership function is determined；
4) it is directed to the corresponding evidence of each state characteristic quantity, different distribution power automation terminals is corresponded to according to state characteristic quantity
The fuzzy membership of state calculates corresponding each unit element proposition A under each evidenceiAnd by single element proposition AiIt constitutes
The Basic probability assignment function of framework of identification Ω,
5) calculate Basic probability assignment function on evidence evidence theory fusion result；
6) by evidence theory fusion result and the preset SOT state of termination diagnosis decision rule match, obtain distribution from
Corresponding distribution power automation terminal state in the classification of the dynamicization SOT state of termination.
Preferably, the state characteristic quantity specified in step 1) includes exception reporting frequency F1, contradiction report frequency F2, terminal
Offline frequency F3, the exception reporting frequency F1Signified exception reporting specifically refers to the alarm thing of distribution power automation terminal upload
The record of distribution power automation terminal ontology exception described, the exception reporting includes that encrypted authentication failure, cell activation are different in part
Often, key pair updates failed database, the failure of access encryption equipment, device exception, the low six classes report of cell voltage；The contradiction report
Accuse frequency F2Signified contradiction report refers to illogical in the alarm event and data information of terminal upload or mutually conflicting
Record, the contradiction report include that remote signalling report and event sequence report that not pairs of, remote signalling state and telemetry mismatch, eventually
End power supply line's fault trip report mismatches three classes report with power loss report is exchanged；The offline frequency F of terminal3Signified end
End refers to that terminal loses with distribution main website offline and writes to each other.
Preferably, the exception reporting frequency F1Calculation expression such as formula (1) shown in, contradiction report frequency F2Calculating
Shown in expression formula such as formula (2), the offline frequency F of terminal3Calculation expression such as formula (3) shown in；
F1=H/T (1)
In formula (1), F1Indicate exception reporting frequency, unit be times/day, H indicate statistics duration in exception reporting number,
T indicates statistics duration；
F2=S/T (2)
In formula (2), F2Indicate contradiction report frequency, unit be times/day, S indicate statistics duration in contradiction report number,
T indicates statistics duration；
F3=M/T (3)
In formula (3), F3Indicate that the offline frequency of terminal, unit are times/day, M indicates terminal disconnection number in statistics duration T, T
Indicate statistics duration.
Preferably, when distribution power automation terminal state is classified by step 2), distribution power automation terminal state is classified to good
Good, general, early warning three classes, and trapezoidal membership function shown in formula (4)~(6) is respectively adopted as fuzzy membership function；
In formula (4)~(6), μ1(x) indicate that distribution power automation terminal state is good fuzzy membership function value, μ2(x)
Expression distribution power automation terminal state is general fuzzy membership function value, μ3(x) indicate that distribution power automation terminal state is
The fuzzy membership function value of early warning, t1~t4For every degree of membership parameter of fuzzy membership function.
Preferably, the detailed step of step 3) includes:
3.1) the multiple groups degree of membership initial parameter value of fuzzy membership function is inputted；
3.2) initial weight of each group degree of membership initial parameter value is determined；
3.3) traversal selects a degree of membership parameter as current degree of membership parameter item；
3.4) weighted average of current degree of membership parameter item is calculated；
3.5) it is directed to current degree of membership parameter item, the deviation judged whether there is between initial value and weighted average is less than
Preset threshold value ψ is jumped and if so, being worth weighted average as final determine of current degree of membership parameter item and is executed step
It is rapid 3.7)；Step 3.6) is executed if it does not exist, then jumping；
3.6) weight that each group degree of membership initial parameter value is updated according to the deviation between initial value and weighted average, is jumped
Turn to execute step 3.4)；
3.7) judge whether that all degree of membership parameter traversals finish, if traversal finishes, jump and execute step 4)；It is no
Then, it jumps and executes step 3.3).
Preferably, step 3.2) determines shown in the expression formula such as formula (7) of the initial weight of each group degree of membership initial parameter value,
Step 3.4) calculates shown in the expression formula such as formula (8) of the weighted average of current degree of membership parameter item；
Gs(k)=1/W (7)
In formula (7), Gs(k)Indicate the weight of s degree of membership parameters in kth group degree of membership parameter, W is affiliated degree of membership
The group number total amount of parameter；
In formula (8), tGsIndicate the weighted average of s degree of membership parameters, Gs(k)It indicates the in kth group degree of membership parameter
The weight of s degree of membership parameters, ts(k)Indicate the value of s degree of membership parameters in kth group degree of membership parameter, W is affiliated is subordinate to
Spend the group number total amount of parameter.
Preferably, step 3.6) updates shown in the expression formula such as formula (9) of the weight of each group degree of membership initial parameter value；
In formula (9), Gs(k)Indicate the weight of s degree of membership parameters in kth group degree of membership parameter, ts(k)Indicate that kth group is subordinate to
The value of s degree of membership parameters, t in category degree parameterGsIndicate that the weighted average of s degree of membership parameters, W are affiliated degree of membership
The group number total amount of parameter.
Preferably, corresponding each unit element proposition A under each evidence is calculated in step 4)iAnd by single element proposition Ai
Shown in the expression formula such as formula (10) of the Basic probability assignment function of the framework of identification Ω of composition；
In formula (10), m (Ai) indicate single element proposition AiBasic probability assignment function, m (Ω) indicates framework of identification Ω
Basic probability assignment function, single element proposition AiIt is corresponded with distribution power automation terminal state, wherein i=1,2 ..., P, P are
The classification total quantity of distribution power automation terminal state, μiIt (x) is characteristic quantity x to proposition { AiFuzzy membership, ω is evidence
Weight；Shown in the expression formula of intermediate variable α such as formula (11), shown in the expression formula of intermediate variable β such as formula (12)；
In formula (11) and formula (12), μiIt (x) is characteristic quantity x to proposition { AiFuzzy membership, μm(x) characteristic quantity x is indicated
To the maximum value in the fuzzy membership of each proposition, wherein i=1,2 ..., P, P are that the classification of distribution power automation terminal state is total
Quantity.
Preferably, step 5) calculates shown in the expression formula such as formula (13) of the basic probability assignment after D-S evidence fusion；
In formula (13), m (A) indicates that the basic probability assignment after D-S evidence fusion, A indicate proposition to be assessed, and Φ is indicated
Empty set, m1、m2For the Basic probability assignment function of two evidence bodies on framework of identification Ω, m1The burnt member of evidence be respectively X1,
X2,…,XN, m2Coke member be respectively Y1,Y2,…,YM, XgIndicate the burnt member of g-th of evidence of first evidence, YhIndicate second
The burnt member of h-th of evidence of evidence, m1(Xg) indicate first evidence to XgBasic probability assignment, m2(Yh) indicate second evidence
To YhBasic probability assignment, g=1,2 ..., N, h=1,2 ..., Q, N indicate the burnt first number of the evidence of first evidence, Q table
Show the burnt first number of the evidence of second evidence, conflict spectrum of the K between evidence, shown in the expression formula of K such as formula (14)；
In formula (14), Φ indicates empty set, m1、m2For the Basic probability assignment function of two evidence bodies on framework of identification Ω,
m1The burnt member of evidence be respectively X1,X2,…,XN, m2Coke member be respectively Y1,Y2,…,YQ, XgIndicate g-th of first evidence
The burnt member of evidence, YhIndicate the burnt member of h-th of evidence of second evidence, m1(Xg) indicate first evidence to XgElementary probability point
Match, m2(Yh) indicate second evidence to YhBasic probability assignment, g=1,2 ..., N, h=1,2 ..., Q, N indicate first
The burnt first number of the evidence of evidence, Q indicate the burnt first number of the evidence of second evidence.
Preferably, the detailed step of step 6) includes:
6.1) first determine whether D-S evidence theory evidence fusion result whether and meanwhile meet three SOT state of termination shown in formula (15)
Decision rule is diagnosed, if there is single element proposition AmMeet three SOT state of termination diagnosis decision rules shown in formula (15) simultaneously,
Then judging unit element proposition AmAs final distribution power automation terminal state output, exit；Otherwise, it jumps and performs the next step；
In formula (15), rule1~rule3 respectively indicates three SOT state of termination diagnosis decision rules, m (Am) indicate single element
Proposition AmBasic probability assignment function, m (Ω) indicate framework of identification Ω Basic probability assignment function, m (Ai) indicate single element
Proposition AiBasic probability assignment function, m (Aj) indicate single element proposition AjBasic probability assignment function, ε and λ are default
Be greater than zero real number；
6.2) judge m (A3Whether) >=λ is true, wherein m (A3) indicate single element proposition A3Basic probability assignment function, λ
For it is preset be greater than zero real number, if set up if determine that final distribution power automation terminal state is alert status；Otherwise, it jumps
Turn to perform the next step；
6.3) judge m (A3Whether) < λ is true, wherein m (A3) indicate single element proposition A3Basic probability assignment function, λ
For it is preset be greater than zero real number, if set up if determine that final distribution power automation terminal state is general state.
The present invention is based on the distribution power automation terminal method for diagnosing status of D-S evidence theory to have an advantage that
1, it is special to count specified state from the operation information that distribution power automation terminal is uploaded to distribution main website by the present invention
Sign amount, therefore all state characteristic quantities are all extracted from terminal on-line operation information, are advantageously implemented automated diagnostic, energy
Enough on-line real-time measuremens realized to distribution power automation terminal state.
2, the present invention is classified by distribution power automation terminal state, and structural regime characteristic quantity corresponds to different power distribution automations
On the basis of the fuzzy membership function of the SOT state of termination, using distribution power automation terminal state classification results as single element proposition
Ai, based on fuzzy membership function to single element proposition AiWith by single element proposition AiThe framework of identification Ω of composition calculates substantially general
Rate partition function, and the basic probability assignment after D-S evidence fusion is calculated as D-S evidence theory evidence fusion as a result, and will
D-S evidence theory evidence fusion result and preset SOT state of termination diagnosis decision rule are matched, and are obtained in power distribution automation
Corresponding distribution power automation terminal state in SOT state of termination classification merges the shape from different characteristic amount using D-S evidence theory
State information can accurately judge which kind of state is distribution power automation terminal device noumenon be in using operation information, have inspection
The advantage that result is accurate and reliable, diagnosis is convenient and efficient is surveyed, and has higher operability.
3, the present invention includes that both can according to need finger the step of determining every degree of membership parameter of fuzzy membership function
The every degree of membership parameter for determining fuzzy membership function also can according to need and introduce expert group decision to integrate fuzzy person in servitude
Every degree of membership parameter of category degree function, to guarantee the professional and fairness of diagnosis process.
Detailed description of the invention
Fig. 1 is the basic procedure schematic diagram of present invention method.
Fig. 2 is the basic principle schematic of present invention method.
Fig. 3 is the fuzzy membership function schematic diagram of the embodiment of the present invention.
Specific embodiment
As shown in Figure 1, the present embodiment based on D-S evidence theory distribution power automation terminal method for diagnosing status the step of wrap
It includes:
1) specified state characteristic quantity is counted from the operation information that distribution power automation terminal is uploaded to distribution main website；
2) distribution power automation terminal state is classified, structural regime characteristic quantity corresponds to different distribution power automation terminal states
Fuzzy membership function；
3) every degree of membership parameter of fuzzy membership function is determined；
4) it is directed to the corresponding evidence of each state characteristic quantity, different distribution power automation terminals is corresponded to according to state characteristic quantity
The fuzzy membership of state calculates corresponding each unit element proposition A under each evidenceiAnd by single element proposition AiIt constitutes
The Basic probability assignment function of framework of identification Ω；
5) calculate Basic probability assignment function on evidence evidence theory fusion result；
6) by evidence theory fusion result and the preset SOT state of termination diagnosis decision rule match, obtain distribution from
Corresponding distribution power automation terminal state in the classification of the dynamicization SOT state of termination.
In the present embodiment, the state characteristic quantity specified in step 1) includes exception reporting frequency F1, contradiction report frequency F2、
The offline frequency F of terminal3, the exception reporting frequency F1Signified exception reporting specifically refers to the announcement of distribution power automation terminal upload
The record of distribution power automation terminal ontology exception is described, the exception reporting includes that encrypted authentication fails, battery is lived in alert event
Change exception, key pair updates failed database, access encryption equipment fails, device is abnormal, low six class of cell voltage is reported；The lance
Shield reports frequency F2Signified contradiction report refers to illogical or mutual punching in the alarm event and data information of terminal upload
Prominent record, contradiction report include remote signalling report and event sequence report not in pairs, remote signalling state and telemetry not
Match, the report of terminal power supply line fault trip is reported with power loss report mismatch three classes are exchanged；The offline frequency F of terminal3Institute
The terminal of finger refers to that terminal loses with distribution main website offline and writes to each other.
In the present embodiment, the exception reporting frequency F1Calculation expression such as formula (1) shown in, contradiction report frequency F2's
Shown in calculation expression such as formula (2), the offline frequency F of terminal3Calculation expression such as formula (3) shown in；
F1=H/T (1)
In formula (1), F1Indicate exception reporting frequency, unit be times/day, H indicate statistics duration in exception reporting number,
T indicates statistics duration；
F2=S/T (2)
In formula (2), F2Indicate contradiction report frequency, unit be times/day, S indicate statistics duration in contradiction report number,
T indicates statistics duration；
F3=M/T (3)
In formula (3), F3Indicate that the offline frequency of terminal, unit are times/day, M indicates terminal disconnection number in statistics duration T, T
Indicate statistics duration.
In the present embodiment, through counting, certain characteristic quantity data of ring network cabinet terminal in 5 days are as follows: exception reporting frequency F1=
1.6 times/day, contradiction reports frequency F2=2.8 times/day, the offline frequency F of terminal3=7.5 times/day.
In the present embodiment, when distribution power automation terminal state is classified by step 2), distribution power automation terminal state is graded
For good, general, early warning three classes, and trapezoidal membership function shown in formula (4)~(6) is respectively adopted as fuzzy membership letter
Number；
In formula (4)~(6), μ1(x) indicate that distribution power automation terminal state is good fuzzy membership function value, μ2(x)
Expression distribution power automation terminal state is general fuzzy membership function value, μ3(x) indicate that distribution power automation terminal state is
The fuzzy membership function value of early warning, t1~t4For every degree of membership parameter of fuzzy membership function.
The SOT state of termination is divided into good, general, early warning three classes in the present embodiment, when the SOT state of termination is good, show without into
Row maintenance；When the SOT state of termination is general, expression should be taken the circumstances into consideration to arrange maintenance；When the SOT state of termination is early warning, expression should arrange to overhaul immediately.
Trapezoidal membership function shown in formula (4)~(6) is as shown in figure 3, the trapezoidal membership function Expressive Features numerical quantity and terminal
Fuzzy relation between state, wherein t1~t4For degree of membership parameter, x GC group connector state characteristic quantity, μ1、μ2And μ3It respectively indicates
This feature amount corresponds to that distribution terminal is good, general and early warning subordinating degree function.
As shown in Fig. 2, being directed to exception reporting frequency F in the present embodiment1, contradiction report frequency F2, the offline frequency F of terminal3Three
The process that kind state characteristic quantity carries out data mart modeling respectively includes calculating exception reporting frequency F1, contradiction report frequency F2, terminal from
Line frequency F3Belong to good, general, early warning three classes state modulus degree of membership and calculate basic probability assignment, obtains three kinds of shapes
On the basis of the basic probability assignment of state characteristic quantity, D-S evidence theory composition rule is recycled to carry out fusion and according to state
Diagnostic rule is diagnosed, to obtain diagnostic result.
In the present embodiment, multiple groups degree of membership initial parameter value is integrated using iteration Weighted Average Algorithm.Step 3)
Detailed step include:
3.1) the multiple groups degree of membership initial parameter value of fuzzy membership function is inputted；In the present embodiment, multiple groups degree of membership ginseng
Number initial value is determined by the group decision-making of 5 experts, that is, includes 5 groups of degree of membership initial parameter values；
3.2) initial weight of each group degree of membership initial parameter value is determined；
3.3) traversal selects a degree of membership parameter as current degree of membership parameter item；
3.4) weighted average of current degree of membership parameter item is calculated；
3.5) it is directed to current degree of membership parameter item, the deviation judged whether there is between initial value and weighted average is less than
Preset threshold value ψ is jumped and if so, being worth weighted average as final determine of current degree of membership parameter item and is executed step
It is rapid 3.7)；Step 3.6) is executed if it does not exist, then jumping；
3.6) weight that each group degree of membership initial parameter value is updated according to the deviation between initial value and weighted average, is jumped
Turn to execute step 3.4)；
3.7) judge whether that all degree of membership parameter traversals finish, if traversal finishes, jump and execute step 4)；It is no
Then, it jumps and executes step 3.3).
In the present embodiment, step 3.2) determines the expression formula such as formula (7) of the initial weight of each group degree of membership initial parameter value
Shown, step 3.4) calculates shown in the expression formula such as formula (8) of the weighted average of current degree of membership parameter item；
Gs(k)=1/W (7)
In formula (7), Gs(k)Indicate the weight of s degree of membership parameters in kth group degree of membership parameter, W is affiliated degree of membership
The group number total amount of parameter；It is determined in the present embodiment by the group decision-making of 5 experts, includes 5 groups of degree of membership initial parameter values,
Therefore in kth group degree of membership parameter s degree of membership parameters weight Gs(k)Value is 1/5, i.e., value is 0.2；
In formula (8), tGsIndicate the weighted average of s degree of membership parameters, Gs(k)It indicates the in kth group degree of membership parameter
The weight of s degree of membership parameters, ts(k)Indicate the value of s degree of membership parameters in kth group degree of membership parameter, W is affiliated is subordinate to
Spend the group number total amount of parameter.
In the present embodiment, step 3.6) updates shown in the expression formula such as formula (9) of the weight of each group degree of membership initial parameter value；
In formula (9), Gs(k)Indicate the weight of s degree of membership parameters in kth group degree of membership parameter, ts(k)Indicate that kth group is subordinate to
The value of s degree of membership parameters, t in category degree parameterGsIndicate that the weighted average of s degree of membership parameters, W are affiliated degree of membership
The group number total amount of parameter.
It is as shown in table 1 in the degree of membership initial parameter value that 5 experts provide in the present embodiment.If threshold value ψ is equal to 0.01,
The definite value that each parameter is obtained after iteration Weighted Average Algorithm is as shown in table 2.
Table 1: the SOT state of termination amount fuzzy membership parameter based on expertise.
Table 2: degree of membership parameter definite value.
| t1 | t2 | t3 | t4 | |
| F1 | 1.5 | 2.0 | 3.0 | 4.5 |
| F2 | 0.7 | 1.5 | 2.5 | 3.6 |
| F3 | 6.0 | 9.0 | 11.0 | 18.0 |
In the present embodiment, using distribution power automation terminal state classification results as single element proposition Ai, framework of identification Ω is
It is { good: A1, general: A2, early warning: A3, the basic probability assignment that its complementary subset of framework of identification Ω corresponds to proposition is all set to
Zero.Corresponding each unit element proposition A under each evidence is calculated in step 4)iAnd by single element proposition AiThe identification frame of composition
Shown in the expression formula of the Basic probability assignment function of frame Ω such as formula (10)；
In formula (10), m (Ai) indicate single element proposition AiBasic probability assignment function, m (Ω) indicates framework of identification Ω
Basic probability assignment function, single element proposition AiIt is corresponded with distribution power automation terminal state, wherein i=1,2 ..., P, P are
The classification total quantity of distribution power automation terminal state, μiIt (x) is characteristic quantity x to proposition { AiFuzzy membership, ω is evidence
Weight；Shown in the expression formula of intermediate variable α such as formula (11), shown in the expression formula of intermediate variable β such as formula (12)；
In formula (11) and formula (12), μiIt (x) is characteristic quantity x to proposition { AiFuzzy membership, μm(x) characteristic quantity x is indicated
To the maximum value in the fuzzy membership of each proposition, wherein i=1,2 ..., P, P are that the classification of distribution power automation terminal state is total
Quantity.
In the present embodiment, characteristic quantity F1~F3 evidence generated is denoted as E1~E3.Consider each characteristic quantity and terminal body shape
The degree of correlation of state sets E1~E3Weight be respectively as follows: ω1=0.6, ω2=0.6, ω3=0.5.By the degree of membership in table 3
It is updated in formula (10) with evidence weight, each proposition basic probability assignment under different evidences can be calculated, as a result such as 4 institute of table
Show.
Table 4: the basic probability assignment of each proposition under different evidences.
| m(A1) | m(A2) | m(A3) | m(Ω) | |
| E1 | 0.70 | 0.17 | 0 | 0.13 |
| E2 | 0 | 0.62 | 0.23 | 0.15 |
| E3 | 0.29 | 0.48 | 0 | 0.23 |
In the present embodiment, step 5) is calculated shown in the expression formula such as formula (13) of the basic probability assignment after D-S evidence fusion；
In formula (13), m (A) indicates that the basic probability assignment after D-S evidence fusion, A indicate proposition to be assessed, and Φ is indicated
Empty set, m1、m2For the Basic probability assignment function of two evidence bodies on framework of identification Ω, m1The burnt member of evidence be respectively X1,
X2,…,XN, m2Coke member be respectively Y1,Y2,…,YM, XgIndicate the burnt member of g-th of evidence of first evidence, YhIndicate second
The burnt member of h-th of evidence of evidence, m1(Xg) indicate first evidence to XgBasic probability assignment, m2(Yh) indicate second evidence
To YhBasic probability assignment, g=1,2 ..., N, h=1,2 ..., Q, N indicate the burnt first number of the evidence of first evidence, Q table
Show the burnt first number of the evidence of second evidence, conflict spectrum of the K between evidence, shown in the expression formula of K such as formula (14)；
In formula (14), Φ indicates empty set, m1、m2For the Basic probability assignment function of two evidence bodies on framework of identification Ω,
m1The burnt member of evidence be respectively X1,X2,…,XN, m2Coke member be respectively Y1,Y2,…,YQ, XgIndicate g-th of first evidence
The burnt member of evidence, YhIndicate the burnt member of h-th of evidence of second evidence, m1(Xg) indicate first evidence to XgElementary probability point
Match, m2(Yh) indicate second evidence to YhBasic probability assignment, g=1,2 ..., N, h=1,2 ..., Q, N indicate first
The burnt first number of the evidence of evidence, Q indicate the burnt first number of the evidence of second evidence.
In the present embodiment, the basic probability assignment after obtained D-S evidence fusion is as shown in table 5.
Basic probability assignment table after table 5:D-S evidence fusion.
| m(A1) | m(A2) | m(A3) | m(Ω) | |
| E1&E2&E3 | 0.26 | 0.69 | 0.03 | 0.02 |
Referring to table 5, finally by the basic probability assignment E after obtained D-S evidence fusion in the present embodiment1~E3As most
The D-S evidence theory evidence fusion result obtained eventually.
In the present embodiment, the detailed step of step 6) includes:
6.1) first determine whether D-S evidence theory evidence fusion result whether and meanwhile meet three SOT state of termination shown in formula (15)
Decision rule is diagnosed, if there is single element proposition AmMeet three SOT state of termination diagnosis decision rules shown in formula (15) simultaneously,
Then judging unit element proposition AmAs final distribution power automation terminal state output, exit；Otherwise, it jumps and performs the next step；
In formula (15), rule1~rule3 respectively indicates three SOT state of termination diagnosis decision rules, m (Am) indicate single element
Proposition AmBasic probability assignment function, m (Ω) indicate framework of identification Ω Basic probability assignment function, m (Ai) indicate single element
Proposition AiBasic probability assignment function, m (Aj) indicate single element proposition AjBasic probability assignment function, ε and λ are default
Be greater than zero real number；
6.2) judge m (A3Whether) >=λ is true, wherein m (A3) indicate single element proposition A3Basic probability assignment function, λ
For it is preset be greater than zero real number, if set up if determine that final distribution power automation terminal state is alert status；Otherwise, it jumps
Turn to perform the next step；
6.3) judge m (A3Whether) < λ is true, wherein m (A3) indicate single element proposition A3Basic probability assignment function, λ
For it is preset be greater than zero real number, if set up if determine that final distribution power automation terminal state is general state.
In the present embodiment, setting ε is equal to 0.25, λ and is equal to 0.2, the D-S evidence theory evidence fusion knot in conjunction with shown in table 5
Fruit E1~E3, can determine that out that final distribution power automation terminal state is general state.
In conclusion the present embodiment passes through analysis based on the distribution power automation terminal method for diagnosing status of D-S evidence theory
Terminal operating information establishes the characteristic quantity system of reflection terminal body state；Determine that the SOT state of termination is classified, construction feature amount is not to
With the fuzzy membership function of state；Expert group decision is carried out, determines subordinating degree function using iteration Weighted Average Algorithm
Parameters；Basic probability assignment is calculated, merges different characteristic amount information using D-S evidence theory；Diagnosis decision rule is formulated,
It compares evidence fusion result and obtains SOT state of termination diagnosis.Power distribution automation using the present embodiment based on D-S evidence theory
SOT state of termination diagnostic method can in time, effectively grasp the hardware state variation of distribution power automation terminal, so as to reasonable arrangement
Service work.The present embodiment utilizes D-S evidence theory pair based on the distribution power automation terminal method for diagnosing status of D-S evidence theory
Status information entrained by different characteristic amount is merged, diagnostic result reliability with higher and accuracy.
The above is only a preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art
Those of ordinary skill for, several improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (9)
1. a kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory, it is characterised in that step includes:
1) specified state characteristic quantity is counted from the operation information that distribution power automation terminal is uploaded to distribution main website；The shape
State characteristic quantity includes exception reporting frequency F1, contradiction report frequency F2, the offline frequency F of terminal3, the exception reporting frequency F1Institute
The exception reporting of finger specifically refers to describe distribution power automation terminal ontology exception in the alarm event that distribution power automation terminal uploads
Record, the exception reporting include encrypted authentication failure, cell activation be abnormal, key pair updates failed database, access plus
Close machine failure, device exception, the low six classes report of cell voltage；The contradiction reports frequency F2Signified contradiction report refers to terminal
Illogical or mutual conflicting record in the alarm event and data information of upload, the contradiction report include remote signalling report and
Event sequence report is not pairs of, remote signalling state is mismatched with telemetry, terminal power supply line fault trip is reported and exchanged and loses
Telegram, which is accused, mismatches three classes report；The offline frequency F of terminal3It is logical that signified terminal refers to that terminal loses with distribution main website offline
Letter connection；
2) distribution power automation terminal state is classified, structural regime characteristic quantity corresponds to the mould of different distribution power automation terminal states
Paste subordinating degree function；
3) every degree of membership parameter of fuzzy membership function is determined；
4) it is directed to the corresponding evidence of each state characteristic quantity, different distribution power automation terminal states is corresponded to according to state characteristic quantity
Fuzzy membership, calculate corresponding each unit element proposition A under each evidenceiAnd by single element proposition AiThe identification of composition
The Basic probability assignment function of frame Ω,
5) calculate Basic probability assignment function on evidence evidence theory fusion result；
6) evidence theory fusion result and preset SOT state of termination diagnosis decision rule are matched, is obtained in power distribution automation
Corresponding distribution power automation terminal state in SOT state of termination classification.
2. the distribution power automation terminal method for diagnosing status according to claim 1 based on D-S evidence theory, feature exist
In the exception reporting frequency F1Calculation expression such as formula (1) shown in, contradiction report frequency F2Calculation expression such as formula (2)
Shown, the offline frequency F of terminal3Calculation expression such as formula (3) shown in；
F1=H/T (1)
In formula (1), F1Indicate exception reporting frequency, unit be times/day, H indicate statistics duration in exception reporting number, T indicate
Count duration；
F2=S/T (2)
In formula (2), F2Indicate contradiction report frequency, unit be times/day, S indicate statistics duration in contradiction report number, T indicate
Count duration；
F3=M/T (3)
In formula (3), F3Indicate that the offline frequency of terminal, unit are times/day, M indicates that terminal disconnection number in statistics duration T, T indicate
Count duration.
3. the distribution power automation terminal method for diagnosing status according to claim 1 or 2 based on D-S evidence theory, special
Sign is, when distribution power automation terminal state is classified by step 2), distribution power automation terminal state be classified to it is good, general,
Early warning three classes, and trapezoidal membership function shown in formula (4)~(6) is respectively adopted as fuzzy membership function；
In formula (4)~(6), μ1(x) indicate that distribution power automation terminal state is good fuzzy membership function value, μ2(x) it indicates
Distribution power automation terminal state is general fuzzy membership function value, μ3(x) indicate that distribution power automation terminal state is early warning
Fuzzy membership function value, t1~t4For every degree of membership parameter of fuzzy membership function.
4. the distribution power automation terminal method for diagnosing status according to claim 3 based on D-S evidence theory, feature exist
In the detailed step of step 3) includes:
3.1) the multiple groups degree of membership initial parameter value of fuzzy membership function is inputted；
3.2) initial weight of each group degree of membership initial parameter value is determined；
3.3) traversal selects a degree of membership parameter as current degree of membership parameter item；
3.4) weighted average of current degree of membership parameter item is calculated；
3.5) it is directed to current degree of membership parameter item, judges whether there is the deviation between initial value and weighted average less than default
Threshold value ψ, and if so, using weighted average as current degree of membership parameter item it is final determine be worth, jump execution step
3.7)；Step 3.6) is executed if it does not exist, then jumping；
3.6) weight that each group degree of membership initial parameter value is updated according to the deviation between initial value and weighted average, jumps and holds
Row step 3.4)；
3.7) judge whether that all degree of membership parameter traversals finish, if traversal finishes, jump and execute step 4)；Otherwise, it jumps
Turn to execute step 3.3).
5. the distribution power automation terminal method for diagnosing status according to claim 4 based on D-S evidence theory, feature exist
In step 3.2) determines that shown in the expression formula such as formula (7) of the initial weight of each group degree of membership initial parameter value, step 3.4) is calculated
Shown in the expression formula such as formula (8) of the weighted average of current degree of membership parameter item；
Gs(k)=1/W (7)
In formula (7), Gs(k)Indicate the weight of s degree of membership parameters in kth group degree of membership parameter, W is affiliated degree of membership parameter
Group number total amount；
In formula (8), tGsIndicate the weighted average of s degree of membership parameters, Gs(k)S are indicated in kth group degree of membership parameter
The weight of degree of membership parameter, ts(k)Indicate the value of s degree of membership parameters in kth group degree of membership parameter, W is affiliated degree of membership ginseng
Several group number total amounts.
6. the distribution power automation terminal method for diagnosing status according to claim 4 based on D-S evidence theory, feature exist
In step 3.6) updates shown in the expression formula such as formula (9) of the weight of each group degree of membership initial parameter value；
In formula (9), Gs(k)Indicate the weight of s degree of membership parameters in kth group degree of membership parameter, ts(k)Indicate kth group degree of membership
The value of s degree of membership parameters in parameter, tGsIndicate that the weighted average of s degree of membership parameters, W are affiliated degree of membership parameter
Group number total amount.
7. the distribution power automation terminal method for diagnosing status according to claim 3 based on D-S evidence theory, feature exist
In corresponding each unit element proposition A under each evidence of calculating in step 4)iAnd by single element proposition AiThe identification frame of composition
Shown in the expression formula of the Basic probability assignment function of frame Ω such as formula (10)；
In formula (10), m (Ai) indicate single element proposition AiBasic probability assignment function, m (Ω) indicate framework of identification Ω it is basic
Probability distribution function, single element proposition AiIt is corresponded with distribution power automation terminal state, wherein i=1,2 ..., P, P are distribution
The classification total quantity of automatization terminal state, μiIt (x) is characteristic quantity x to proposition { AiFuzzy membership, ω be evidence power
Value；Shown in the expression formula of intermediate variable α such as formula (11), shown in the expression formula of intermediate variable β such as formula (12)；
In formula (11) and formula (12), μiIt (x) is characteristic quantity x to proposition { AiFuzzy membership, μm(x) indicate characteristic quantity x to each
Maximum value in the fuzzy membership of proposition, wherein i=1,2 ..., P, P are the classification total quantity of distribution power automation terminal state.
8. the distribution power automation terminal method for diagnosing status according to claim 3 based on D-S evidence theory, feature exist
In step 5) calculates shown in the expression formula such as formula (13) of the basic probability assignment after D-S evidence fusion；
In formula (13), m (A) indicates that the basic probability assignment after D-S evidence fusion, A indicate proposition to be assessed, and Φ indicates empty
Collection, m1、m2For the Basic probability assignment function of two evidence bodies on framework of identification Ω, m1The burnt member of evidence be respectively X1,
X2,…,XN, m2Coke member be respectively Y1,Y2,…,YQ, XgIndicate the burnt member of g-th of evidence of first evidence, YhIndicate second
The burnt member of h-th of evidence of evidence, m1(Xg) indicate first evidence to XgBasic probability assignment, m2(Yh) indicate second evidence
To YhBasic probability assignment, g=1,2 ..., N, h=1,2 ..., Q, N indicate the burnt first number of the evidence of first evidence, Q table
Show the burnt first number of the evidence of second evidence, conflict spectrum of the K between evidence, shown in the expression formula of K such as formula (14)；
In formula (14), Φ indicates empty set, m1、m2For the Basic probability assignment function of two evidence bodies on framework of identification Ω, m1's
The burnt member of evidence is respectively X1,X2,…,XN, m2Coke member be respectively Y1,Y2,…,YQ, XgIndicate g-th of evidence of first evidence
Jiao Yuan, YhIndicate the burnt member of h-th of evidence of second evidence, m1(Xg) indicate first evidence to XgBasic probability assignment, m2
(Yh) indicate second evidence to YhBasic probability assignment, g=1,2 ..., N, h=1,2 ..., Q, N indicate first evidence
The burnt first number of evidence, Q indicate the burnt first number of the evidence of second evidence.
9. the distribution power automation terminal method for diagnosing status according to claim 3 based on D-S evidence theory, feature exist
In the detailed step of step 6) includes:
6.1) first determine whether D-S evidence theory evidence fusion result whether and meanwhile meet shown in formula (15) three SOT state of termination diagnosis
Decision rule, if there is single element proposition AmMeet three SOT state of termination diagnosis decision rules shown in formula (15) simultaneously, then sentences
Order element proposition AmAs final distribution power automation terminal state output, exit；Otherwise, it jumps and performs the next step；
In formula (15), rule1~rule3 respectively indicates three SOT state of termination diagnosis decision rules, m (Am) indicate single element proposition
AmBasic probability assignment function, m (Ω) indicate framework of identification Ω Basic probability assignment function, m (Ai) indicate single element proposition
AiBasic probability assignment function, m (Aj) indicate single element proposition AjBasic probability assignment function, ε and λ are preset big
In zero real number；
6.2) judge m (A3Whether) >=λ is true, wherein m (A3) indicate single element proposition A3Basic probability assignment function, λ is pre-
If be greater than zero real number, if set up if determine that final distribution power automation terminal state is alert status；Otherwise, it jumps and holds
Row is in next step；
6.3) judge m (A3Whether) < λ is true, wherein m (A3) indicate single element proposition A3Basic probability assignment function, λ is pre-
If be greater than zero real number, if set up if determine that final distribution power automation terminal state is general state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710069321.0A CN106932670B (en) | 2017-02-08 | 2017-02-08 | A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710069321.0A CN106932670B (en) | 2017-02-08 | 2017-02-08 | A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106932670A CN106932670A (en) | 2017-07-07 |
| CN106932670B true CN106932670B (en) | 2019-05-14 |
Family
ID=59422955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710069321.0A Active CN106932670B (en) | 2017-02-08 | 2017-02-08 | A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106932670B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107957535B (en) * | 2018-01-17 | 2019-11-19 | 国网山东省电力公司德州供电公司 | A kind of small current system single-phase earth fault route selecting method and apparatus based on power distribution automation data |
| CN108056770A (en) * | 2018-02-02 | 2018-05-22 | 合肥芯福传感器技术有限公司 | A kind of heart rate detection method based on artificial intelligence |
| CN108680808A (en) * | 2018-05-18 | 2018-10-19 | 浙江新能量科技股份有限公司 | Fault diagnosis method and device |
| CN111366884B (en) * | 2018-12-26 | 2023-05-16 | 西安西电高压开关有限责任公司 | Active electronic current transformer and laser life evaluation method and device thereof |
| CN110796377B (en) * | 2019-10-31 | 2022-03-29 | 云南电网有限责任公司信息中心 | Power grid service system monitoring method supporting fuzzy theory |
| CN110825602B (en) * | 2019-10-31 | 2023-02-21 | 云南电网有限责任公司信息中心 | Client-oriented service system performance monitoring method |
| CN111985820B (en) * | 2020-08-24 | 2022-06-14 | 深圳市加码能源科技有限公司 | FNN and DS fusion-based fault identification method for charging operation management system |
| CN112561117A (en) * | 2020-09-27 | 2021-03-26 | 中国电力科学研究院有限公司 | Cable line front-end multi-state fusion prediction method and device |
| CN112636395B (en) * | 2020-12-11 | 2021-08-20 | 珠海市中力电力设备有限公司 | Interactive implementation method for intelligent distributed distribution network automation terminal |
| CN112924812B (en) * | 2021-01-28 | 2023-03-14 | 深圳供电局有限公司 | Evidence theory-based power terminal error data identification method |
| CN113869241B (en) * | 2021-09-30 | 2022-09-27 | 西安理工大学 | Online learning state analysis and alarm method integrating human face multiple attributes |
| CN115951263B (en) * | 2023-03-13 | 2023-06-16 | 广东工业大学 | Traction system main loop ground fault diagnosis method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920511A (en) * | 2006-08-01 | 2007-02-28 | 东北电力大学 | Fusion diagnosing method of centrifugal pump vibration accidents and vibration signals sampling device |
| CN101403676A (en) * | 2008-10-28 | 2009-04-08 | 华北电力大学 | Insulator hydrophobicity rank amalgamation judging method based on D-S evidence theory |
| CN103592374A (en) * | 2013-11-18 | 2014-02-19 | 国家电网公司 | Transformer oil chromatographic data forecasting method based on D-S evidence theory |
| CN106096830A (en) * | 2016-06-07 | 2016-11-09 | 武汉大学 | Relay protection method for evaluating state based on broad sense evidence theory and system |
-
2017
- 2017-02-08 CN CN201710069321.0A patent/CN106932670B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920511A (en) * | 2006-08-01 | 2007-02-28 | 东北电力大学 | Fusion diagnosing method of centrifugal pump vibration accidents and vibration signals sampling device |
| CN101403676A (en) * | 2008-10-28 | 2009-04-08 | 华北电力大学 | Insulator hydrophobicity rank amalgamation judging method based on D-S evidence theory |
| CN103592374A (en) * | 2013-11-18 | 2014-02-19 | 国家电网公司 | Transformer oil chromatographic data forecasting method based on D-S evidence theory |
| CN106096830A (en) * | 2016-06-07 | 2016-11-09 | 武汉大学 | Relay protection method for evaluating state based on broad sense evidence theory and system |
Non-Patent Citations (2)
| Title |
|---|
| "基于模糊逻辑和证据理论的故障诊断方法";吴晓平等;《海军工程大学学报》;20120226;第24卷(第1期);全文 |
| "证据理论与模糊理论集成的XLPE电缆绝缘状态评估研究";夏向阳等;《电力系统保护与控制》;20141016;第42卷(第20期);全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106932670A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106932670B (en) | A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory | |
| CN109086889B (en) | Terminal fault diagnosis method, device and system based on neural network | |
| CN103001328B (en) | Fault diagnosis and assessment method of intelligent substation | |
| CN102779230B (en) | State analysis and maintenance decision judging method of power transformer system | |
| CN112910089A (en) | Transformer substation secondary equipment fault logic visualization method and system | |
| CN112749509B (en) | Intelligent substation fault diagnosis method based on LSTM neural network | |
| CN110941918B (en) | Intelligent substation fault analysis system | |
| CN116345696B (en) | Anomaly information analysis management system and method based on global monitoring | |
| CN103926490B (en) | A kind of power transformer error comprehensive diagnosis method with self-learning function | |
| CN107016507A (en) | Electric network fault method for tracing based on data mining technology | |
| CN107656176A (en) | A kind of electric network failure diagnosis method based on improvement Bayes's Petri network | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN103296757A (en) | Multi-parameter identification based secondary system fault diagnosing method for intelligent substation | |
| CN106447210A (en) | Distribution network equipment health degree dynamic diagnosis method involving credibility evaluation | |
| CN104615122B (en) | A kind of industry control signal detection system and detection method | |
| CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
| CN107219453B (en) | A kind of substation relay protection hidden failure diagnostic method based on Multidimensional and Hybrid amount | |
| CN106646068A (en) | Method for diagnosing defects of intelligent substation secondary system based on multi-parameter information fusion | |
| Cui et al. | Power system fault reasoning and diagnosis based on the improved temporal constraint network | |
| CN113468022B (en) | Automatic operation and maintenance method for centralized monitoring of products | |
| CN114666117A (en) | Network security situation measuring and predicting method for power internet | |
| CN102006613B (en) | Dual combined linear discrimination method of mobile core network failure data | |
| Barco et al. | Knowledge acquisition for diagnosis model in wireless networks | |
| CN106569095A (en) | Power grid fault diagnosis system based on weighted average dependence classifier | |
| CN115270982A (en) | Switch cabinet fault prediction method based on multi-data neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |