CN107330521A - Unmanned vehicle state evaluating method and device - Google Patents
Unmanned vehicle state evaluating method and device Download PDFInfo
- Publication number
- CN107330521A CN107330521A CN201710526643.3A CN201710526643A CN107330521A CN 107330521 A CN107330521 A CN 107330521A CN 201710526643 A CN201710526643 A CN 201710526643A CN 107330521 A CN107330521 A CN 107330521A
- Authority
- CN
- China
- Prior art keywords
- mrow
- index
- fuzzy
- state estimation
- weight
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 239000011159 matrix material Substances 0.000 claims abstract description 134
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 239000013598 vector Substances 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 24
- 230000000295 complement effect Effects 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000013139 quantization Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 15
- 230000003862 health status Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 230000036541 health Effects 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 6
- 238000005183 dynamical system Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000010181 polygamy Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004335 scaling law Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
- G06N7/023—Learning or tuning the parameters of a fuzzy system
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is applied to unmanned vehicle technical field, and there is provided a kind of unmanned vehicle state evaluating method and device.This method includes:The state estimation index model of unmanned vehicle is set up, and distinguishing hierarchy is carried out to the state estimation index of unmanned vehicle;Fuzzy judgment matrix is set up according to each layer state evaluation index, and obtains according to fuzzy judgment matrix the normal power weight of each state estimation index;The degree of membership of each state estimation index is calculated according to the degree of membership model of state estimation index;According to the normal power weight and the relation of degree of membership and respective threshold of each state estimation index, the normal power weight to each state estimation index enters Mobile state adjustment;According to degree of membership and the variable weight weight of each state estimation index, the state estimation value of unmanned vehicle is determined.The present invention can make weight ask for process more objective reality, and obtained assessment result more conforms to reality, and can protrude the harmony of each index weights, can more objectively reflect actual conditions.
Description
Technical field
The invention belongs to unmanned vehicle technical field, more particularly to a kind of unmanned vehicle state evaluating method and dress
Put.
Background technology
Unmanned vehicle be on a kind of machine it is unmanned, automatic pilot or remote control equipment are installed, with small volume, make
Valency is low, the disguised advantage such as strong, easy to use, be widely used in image scouting, electronic interferences, communication relay, agricultural plant protection,
The every field such as take photo by plane, have broad application prospects.But, continuous improvement and system with unmanned vehicle performance are answered
Polygamy is continuously increased so that is increasingly protruded the problems such as its reliability, maintainability and maintenance support, is got up for a long time, in order to anti-
The only generation of unmanned vehicle failure or the degeneration of health status, unmanned vehicle often relies on the warp of operating personnel using unit
Test and carry out health status that is qualitative, broadly judging aircraft, the quantitative status monitoring evaluation measures of shortage, thus can not comprehensively,
The health status and its variation tendency of aircraft are held exactly, and the condition maintenarnce for being not suitable with high cost effectiveness at present ensures requirement.
Unmanned vehicle system composition is huge, complicated, and reliability requirement is high, but currently for unmanned vehicle
Health state evaluation research is not enough, it is impossible to ensures the reliability of aircraft, there is very big flight hidden danger.Fly currently for nobody
Capable maintenance support mainly uses correction maintenance mode, is only just repaired after aircraft breaks down, caused damage, no
Potential faults can be eliminated before day on board the aircraft, be easily caused unforeseen accident and occur.
The content of the invention
In view of this, it is existing to solve the embodiments of the invention provide a kind of unmanned vehicle state evaluating method and device
Have in technology only the problem of just being repaired after aircraft breaks down, caused damage.
The first aspect of the embodiment of the present invention there is provided a kind of unmanned vehicle state evaluating method, including:
The state estimation index model of unmanned vehicle is set up, and the state estimation index of the unmanned vehicle is carried out
Distinguishing hierarchy;
Fuzzy judgment matrix is set up according to each layer state evaluation index, and each institute is obtained according to the fuzzy judgment matrix
State the normal power weight of state estimation index;
The degree of membership of each state estimation index is calculated according to the degree of membership model of state estimation index;
According to the normal power weight and the relation of degree of membership and respective threshold of each state estimation index, to described in each
The normal power weight of state estimation index enters Mobile state adjustment, obtains the variable weight weight of each state estimation index;
According to the variable weight weight and degree of membership of each state estimation index, the state estimation of unmanned vehicle is determined
Value.
Optionally, it is described that fuzzy judgment matrix is set up according to each layer state evaluation index, and according to the fuzzy Judgment square
The normal power weight that battle array obtains each state estimation index includes:
By expert method, to each layer, each state estimation index is contrasted two-by-two, sets up the fuzzy judgment matrix;
Consistency check processing is carried out to the fuzzy judgment matrix, and according to after consistency check is handled
Module judgment matrix calculates the normal power weight of each state estimation index.
Optionally, the fuzzy judgment matrix is:
Wherein, expert's quantity is K, and the weight of k-th of expert is rk,Represent that the Triangular Fuzzy Number of k-th of expert judges
Matrix,It is Triangular Fuzzy Number,WithLower bound and the upper bound of fuzzy number are represented respectively;It is fuzzy numberIntermediate value.
Optionally, it is described that consistency check processing is carried out to the fuzzy judgment matrix, and according to passing through consistency check
The normal power weight that the fuzzy judgment matrix after processing calculates each state estimation index includes:
Calculate the Fuzzy Complementary Judgment Matrices of the fuzzy judgment matrix;
The Fuzzy Complementary Judgment Matrices are converted into fuzzy consistent matrix, and the fuzzy consistent matrix is carried out
Consistency check is handled;
When the fuzzy consistent matrix meets consistency check, judge that the fuzzy judgment matrix meets uniformity,
And fuzzy judgment matrix each described is solved, determine the normal power weight of each state estimation index.
Optionally, it is described to be specially to fuzzy consistent matrix progress consistency check processing:
The most probable estimate of multilevel iudge information two-by-two is extracted in the fuzzy judgment matrix A, obtains described fuzzy mutual
Mend judgment matrix M;Wherein, the element of the i-th row jth row of the Fuzzy Complementary Judgment Matrices M
Pass through formulaWith m 'ij=(m 'i-m′j)/[2 (n-1)]+0.5 by the Fuzzy Complementary Judgment Matrices M
The fuzzy consistent matrix M' is converted into, wherein, n is matrix M exponent number;
The fuzzy consistent matrix M' is examined whether to meet consistency check by calculating δ and σ, wherein δ=max |
m′ij-mij|,If δ<0.2,σ<0.1, then it represents that the fuzzy consistent matrix is met
Consistency check, judges that the fuzzy judgment matrix meets uniformity, otherwise performs and described is built according to each layer state evaluation index
Vertical fuzzy judgment matrix step.
Optionally, it is described that fuzzy judgment matrix each described is solved, determine each state estimation index
Often power weight is specially:
Triangular Fuzzy Number in fuzzy judgment matrix is converted into non-fuzzy number;Assuming that m possibility size be X times of l,
Y times of u, then the calculation formula that Triangular Fuzzy Number a=(l m u) is converted into non-fuzzy number is:
A=l/2 (1+X)+[m (X+2XY+Y)]/[2 (1+X) (1+Y)]+u/2 (1+Y)
Index weights are asked for according to the result of calculation that Triangular Fuzzy Number is converted into non-fuzzy number;Often weigh weight solution formula
For:
Wherein, aijRepresent that i-th of index and j-th of index compare obtained non-fuzzy number, w two-by-twoiRepresent i-th of index
The normal weight of synthesis.
Optionally, the degree of membership model according to state estimation index calculates being subordinate to for each state estimation index
Degree includes:
Each described state estimation index is divided into quantitative target and qualitative index, the quantitative target is characterized and can used
The index of digital quantization expression, the qualitative index, which is characterized, can not be expressed with digital quantization and use word or iamge description
Index;
The quantitative target is subjected to nondimensionalization processing, the degree of membership of each quantitative target is drawn;
By the word description or the corresponding relation of iamge description and degree of membership of the qualitative index set in advance, draw
The degree of membership of the qualitative index.
Optionally, the normal power weight and the pass of degree of membership and respective threshold according to each state estimation index
System, Mobile state adjustment is entered to the normal power weight of state estimation index each described to be included:
Assuming that evaluation index collection U=(A1,A2,A3,...,Am) in, the degree of membership of each state estimation index is X=(X1,X2,
X3,...,Xm) ∈ [0,1], definition:
For often power weight vectors, meet:
Given mapping S:[0,1]m→(0,∞)m, claim vector Sx=(S1(x),S2(x),S3(x),...,Sm(x)) to be local
State variable weight vector, is tried to achieve by local variable weight formula;
Given mapping w:[0,1]m→(0,∞)m, claim vector W (x)=(W1(x),W2(x),W3(x),…,Wm(x) it is) change
Weight vectors are weighed, wherein:Meet
Local variable weight formula is:
Normal power weight to state estimation index each described is adjusted;Wherein, m is monitoring index number, j=1,2,
3,…,m;A, b, c, d are the parameter in [0,1], and a<b<c;Vector is assessed for often power;E is sensitivity coefficient,For often power weight vectors, Wi 0For W0I-th of element.
Optionally, the state estimation value of the unmanned vehicle is
The second aspect of the embodiment of the present invention there is provided a kind of unmanned vehicle state evaluation device, including:
Model building module, the state estimation index model for setting up unmanned vehicle, and to the unmanned vehicle
State estimation index carry out distinguishing hierarchy;
Weight obtains module, for setting up fuzzy judgment matrix according to each layer state evaluation index, and according to described fuzzy
Judgment matrix obtains the normal power weight of each state estimation index;
Degree of membership computing module, refers to for calculating each described state estimation according to the degree of membership model of state estimation index
Target degree of membership;
Weight adjusting module, for the normal power weight and degree of membership and respective threshold according to each state estimation index
Relation, Mobile state adjustment is entered to the normal power weight of state estimation index each described, each state estimation index is obtained
Variable weight weight;
State determining module, for the variable weight weight and degree of membership according to each state estimation index, it is determined that nobody
The state estimation value of aircraft.
The third aspect of the embodiment of the present invention is described computer-readable to deposit there is provided a kind of computer-readable recording medium
Storage media is stored with computer program, realizes that nobody is winged as described in foregoing any one when the computer program is executed by processor
The step of row device state evaluating method.
The present invention relative to prior art have the advantage that for:The embodiment of the present invention, sets up unmanned vehicle
State estimation index model, and distinguishing hierarchy is carried out to the state estimation index of the unmanned vehicle, then according to each stratiform
State evaluation index sets up fuzzy judgment matrix, and obtains the normal of each state estimation index according to the fuzzy judgment matrix
Weight is weighed, the degree of membership of each state estimation index is calculated according to the degree of membership model of state estimation index, according to each
The normal power weight and the relation of degree of membership and respective threshold of state estimation index, the normal power weight to each state estimation index are entered
Mobile state is adjusted, and the variable weight weight of each state estimation index is obtained, according to the variable weight weight of each state estimation index and person in servitude
Category degree, determines the state estimation value of unmanned vehicle, to determine the state of unmanned vehicle, so as to make weight ask for process
More objective reality, obtained assessment result more conforms to reality, and can protrude the harmony of each index weights, can be more objective
Ground reflection actual conditions are seen, so as to be found before day on board the aircraft and eliminate potential faults.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In required for the accompanying drawing that uses be briefly described, it should be apparent that, drawings in the following description are only some of the present invention
Embodiment, for those of ordinary skill in the art, on the premise of not paying creative work, can also be attached according to these
Figure obtains other accompanying drawings.
Fig. 1 is the schematic flow sheet of unmanned vehicle state evaluating method provided in an embodiment of the present invention;
Fig. 2 is unmanned vehicle power subsystem evaluation index system provided in an embodiment of the present invention;
Fig. 3 is the implementation process figure of step S102 in Fig. 1;
Fig. 4 is the implementation process figure of step S202 in Fig. 2;
Fig. 5 is the implementation process figure of step S103 in Fig. 1;
Fig. 6 is the normal weights of index provided in an embodiment of the present invention with becoming weights comparison diagram;
Fig. 7 is that unmanned vehicle power subsystem provided in an embodiment of the present invention assesses interface;
Fig. 8 is fuzzy judgment matrix construction provided in an embodiment of the present invention with solving interface;
Fig. 9 is the structured flowchart of unmanned vehicle status assessing system provided in an embodiment of the present invention.
Embodiment
In describing below, in order to illustrate rather than in order to limit, it is proposed that such as tool of particular system structure, technology etc
Body details, thoroughly to understand the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, omit to well-known system, device, electricity
Road and the detailed description of method, in case unnecessary details hinders description of the invention.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Fig. 1 shows the implementation process of unmanned vehicle state evaluating method provided in an embodiment of the present invention, and details are as follows:
Step S101, sets up the state estimation index model of unmanned vehicle, and the state of the unmanned vehicle is commented
Estimate index and carry out distinguishing hierarchy.
Below by taking the power subsystem of unmanned vehicle as an example, the embodiment of the present invention is explained, but not with
This is limited.
Wherein, the power subsystem health state evaluation index system of unmanned vehicle can be divided into two levels:Shadow
Ring factor layer and monitoring index layer.The factor for influenceing unmanned vehicle power subsystem health status is divided into:Performance indications
Parameter, operator quality, ground handling equipment, flight storage environment, guarantee maintenance record, the class of time of flight data six, according to
This construction force subsystem health state evaluation index system, as shown in Figure 2.
Performance indications parameter D1 include rotating speed, cylinder temperature, oil consumption, startup situation, idling steady degree, igniting, vibration, exhaust,
The factors such as acceleration situation, installation, fixation.Operator quality D2 includes the factors such as degree, professional and proficiency of undergoing training.Ground
Ensure that equipment D3 includes the factors such as ground checkout equipment, maintenance ground equipment and maintenance and repair parts.Flight storage environment D4 includes holding
The factor such as row task environment and storage environment.Ensure maintenance record D5 include field maintenance, alternate maintenance and depot repair etc. because
Element.Time of flight data D6 includes the factors such as ground experiment and practical flight.
It is the premise being estimated that distinguishing hierarchy is carried out to the state estimation index of the unmanned vehicle power subsystem,
The health status grade classification of specification, not only improves the implementation of health state evaluation, is also beneficial to the health control of system.To institute
The state estimation index progress distinguishing hierarchy for stating unmanned vehicle power subsystem is as shown in table 1.
The power subsystem health status grade classification of table 1
Step S102, fuzzy judgment matrix is set up according to each layer state evaluation index, and according to the fuzzy judgment matrix
Obtain the normal power weight of each state estimation index.
Referring to Fig. 3, in one embodiment, step S102 can be realized by procedure below:
Step S201, by expert method, to each layer, each state estimation index is contrasted two-by-two, sets up the fuzzy Judgment square
Battle array.
Wherein, the fuzzy judgment matrix is:
Wherein, expert's quantity is K, and the weight of k-th of expert is rk,Represent that the Triangular Fuzzy Number of k-th of expert judges
Matrix,It is Triangular Fuzzy Number,WithLower bound and the upper bound of fuzzy number are represented respectively;It is fuzzy numberIntermediate value.The present embodiment replaces the concrete numerical value of judgment matrix in AHP using Triangle Fuzzy Sets.Expert will be each
Each index of level is contrasted two-by-two, obtains fuzzy judgment matrix.
Each element value of fuzzy judgment matrix characterizes significance level of the factor compared with another factor, judgment matrix
In element using can more effectively reflect expert's actual estimated 0.1~0.9 scaling law determine.Obtain the judgement square of each expert
Need to be further processed after battle array, to ask for often weighing weight.
Step S202, consistency check processing is carried out to the fuzzy judgment matrix, and according to by consistency check
The module judgment matrix after reason calculates the normal power weight of each state estimation index.
Referring to Fig. 4, in one embodiment, step S202 can be realized by procedure below:
Step S301, calculates the Fuzzy Complementary Judgment Matrices of the fuzzy judgment matrix.
Wherein, the most probable estimate of multilevel iudge information two-by-two is extracted in fuzzy judgment matrix A, you can obtain fuzzy mutual
Mend judgment matrix M:
Wherein, the i-th row jth column element in the Fuzzy Complementary Judgment Matrices M is Mij。
The Fuzzy Complementary Judgment Matrices are converted into fuzzy consistent matrix by step S302, and to the fuzzy consensus
Property matrix carry out consistency check processing.
Specifically, step S302 can be realized by procedure below:
The most probable estimate of multilevel iudge information two-by-two is extracted in the fuzzy judgment matrix A, obtains described fuzzy mutual
Mend judgment matrix M;Wherein, the element of the i-th row jth row of the Fuzzy Complementary Judgment Matrices M
Pass through formulaWith m 'ij=(m 'i-m′j)/[2 (n-1)]+0.5 by the Fuzzy Complementary Judgment Matrices M
The fuzzy consistent matrix M' is converted into, wherein, n is matrix M exponent number;
The fuzzy consistent matrix M' is examined whether to meet consistency check by calculating δ and σ, wherein δ=max |
m′ij-mij|,If δ<0.2,σ<0.1, then it represents that the fuzzy consistent matrix is met
Consistency check, judges that the fuzzy judgment matrix meets uniformity, otherwise performs and described is built according to each layer state evaluation index
Vertical fuzzy judgment matrix step.
If specifically, M' meets the requirement of uniformity, fuzzy judgment matrix A can be approximately considered and also meet uniformity.It is right
The fuzzy consistent matrix M' for 0.1~0.9 scale taken in the present invention, in order to examine whether fuzzy complementary matrix meets reality
Situation, can be examined by calculating δ and σ.
Step S303, when the fuzzy consistent matrix meets consistency check, judges that the fuzzy judgment matrix expires
Sufficient uniformity, is then solved to fuzzy judgment matrix each described, determines the Chang Quanquan of each state estimation index
Weight.
Wherein, being solved to fuzzy judgment matrix each described described in step S303, determines each state
The normal power weight of evaluation index, can specifically be realized by procedure below:
For ease of later data processing and analysis, the Triangular Fuzzy Number in fuzzy judgment matrix is converted into non-fuzzy number.
Assuming that m possibility size is X times of l, Y times of u, then Triangular Fuzzy Number a=(l m u) is converted into the calculating public affairs of non-fuzzy number
Formula is:
A=l/2 (1+X)+[m (X+2XY+Y)]/[2 (1+X) (1+Y)]+u/2 (1+Y) (3)
The result of calculation for being converted into non-fuzzy number according to Triangular Fuzzy Number asks for the normal power weight of each fuzzy judgment matrix;
Often power weight solution formula is:
Wherein, aijRepresent that i-th of index and j-th of index compare obtained non-fuzzy number, w two-by-twoiRepresent i-th of index
The normal weight of synthesis.
Step S103, being subordinate to for each state estimation index is calculated according to the degree of membership model of state estimation index
Degree.
Referring to Fig. 5, in one embodiment, step S103 can be realized by procedure below:
Step S401, mark is divided into quantitative target and qualitative index, and the quantitative target, which is characterized, can use digital quantization table
The index reached, the qualitative index, which is characterized, can not express and use the index of word or iamge description with digital quantization.
Wherein, in multi-objective synthetic evaluation, the index difinite quality index of the bottom also has quantitative target.Quantitative target
Directly it can be expressed with digital quantization, the index such as the cylinder temperature in dynamical system, rotating speed;Qualitative index refers to the amount of being difficult to
Change and assess, it is necessary to use the index of its health status of word or iamge description, for example aircraft landing gear whether in health status,
The index such as whether outward appearance intact, its health degree needs to be described with the word such as good, qualified or poor.
Step S402, carries out nondimensionalization processing by the quantitative target, draws the degree of membership of each quantitative target.
Wherein, carry out comprehensive assessment to comprehensively utilize qualitative index and quantitative target, it is necessary first to by quantitative target without
Dimension, that is, ask for index degree of membership, and the word description of qualitative index then is converted into quantitative description.
Indices non-dimension method mainly has three types:Linear pattern, broken line type and shaped form nondimensionalization method.This reality
Apply and carry out nondimensionalization (asking for index degree of membership) in example to aircraft quantitative target with linear pattern nondimensionalization method.
The corresponding relation of step S403, the word description of the qualitative index or iamge description and degree of membership, draws described
The degree of membership of qualitative index.
After quantitative target nondimensionalization, in addition it is also necessary to which the description of qualitative index is converted into quantitative description.The present embodiment
It is middle to be converted according to unmanned vehicle feature using the method for qualitative description correspondence numerical value, degree of membership is directly given, such as the institute of table 2
Show.
The corresponding numerical value conversion of the index qualitative description of table 2
Qualitative description | Brand-new state | Kilter | Eligible state | Hidden danger state | Alarm condition | Malfunction |
Degree of membership | 1 | 0.8 | 0.6 | 0.4 | 0.2 | 0 |
The fuzzy judgment matrix of the power subsystem of unmanned vehicle sets up process and can be:Set the power of each expert
Heavy phase etc., each expertise is integrated, so that power subsystem influence factor layer fuzzy Judgment square after being integrated
Battle array is as shown in table 3.
Power subsystem influence factor layer fuzzy judgment matrix after table 3 is integrated
Each factor most probable estimate in table 3 is extracted, matrix M is obtained, as shown in table 4.
The fuzzy judgment matrix M of table 4
Power subsystem | D1 | D2 | D3 | D4 | D5 | D6 |
D1 | 0.5 | 0.7 | 0.6 | 0.733 | 0.6 | 0.667 |
D2 | 0.3 | 0.5 | 0.4 | 0.533 | 0.4 | 0.5 |
D3 | 0.334 | 0.6 | 0.5 | 0.633 | 0.5 | 0.5667 |
D4 | 0.3 | 0.4667 | 0.3667 | 0.5 | 0.4 | 0.4667 |
D5 | 0.4 | 0.6 | 0.5 | 0.6 | 0.5 | 0.5667 |
D6 | 0.33 | 0.5 | 0.433 | 0.533 | 0.433 | 0.5 |
Matrix M is adjusted, is M ' after adjustment, as shown in table 5.
The fuzzy judgment matrix M ' of table 5
Consistency check is carried out to M ', δ=0.1190 is calculated according to the calculation formula of δ and σ formulas<0.2, σ=0.0628<
0.1, judgment matrix meets consistency check, therefore judgment matrix is without being adjusted.
X=2, Y=2 in modus ponens (3), you can obtain non-fuzzy number judgment matrix, as shown in table 6.
The non-fuzzy number judgment matrix of table 6
By calculate, obtain influence factor layer each index weight vectors it is as shown in table 7.
The influence factor of table 7 layer index weights
Similarly, weight vectors of the bottom monitoring index to influence factor layer can be obtained, as shown in table 8.
Weight of the monitoring index of table 8 to influence factor layer
Step S104, according to the normal power weight and the relation of degree of membership and respective threshold of each state estimation index,
Normal power weight to state estimation index each described is adjusted, and obtains the variable weight weight of each state estimation index.
Whether unmanned vehicle, which is in a good state of health, depends not only on the height of system comprehensive assessment value, additionally depends on wherein
The height of local single index assessed value.If a certain item index evaluation value is very low, it will the health status of whole system is beaten greatly
Discount, but the analytic hierarchy process (AHP) of fixed weights (being often to weigh weights) can not reflect this point.In order to be able to more objectively and accurately
Reflect actual conditions, the embodiment of the present invention introduces health status of the dynamic variable weight method with excitation and punitive function to unmanned plane
Carry out comprehensive assessment.
Assuming that evaluation index collection U=(A1,A2,A3,...,Am) in, the degree of membership of each index is X=(X1,X2,X3,...,
Xm)∈[0,1]。
Provide and be defined as below first:
Define 1:ClaimFor normal weight vector, meet:
Define 2:Given mapping S:[0,1]m→(0,∞)m, claim vector Sx=(S1(x),S2(x),S3(x),...,Sm(x))
For local state variable weight vector, tried to achieve by local variable weight formula.
Define 3:Given mapping w:[0,1]m→(0,∞)m, claim vector W (x)=(W1(x),W2(x),W3(x),…,Wm
(x)) it is variable weight vector, wherein:
Meet:
Wherein, the general type of local variable weight formula is:
When index degree of membership is in 0≤Xj≤ a and b<XjWhen between≤c, local variable weight vector is definite value;When index degree of membership
In a<Xj≤ b or c<XjWhen between≤1, local variable weight vector declines or increased in ratio with X increase.The general type is not
Can according to index number and index Chang Quan distribution situation enter Mobile state adjustment, there is certain limitation.Therefore, the present invention is logical
Introducing variable weight sensitivity coefficient is crossed dynamically to adjust weight.Local variable weight formula after improvement is as follows:
M is monitoring index number j=1,2,3 in formula ..., m;A, b, c, d are the parameter in [0,1], and a<b<c;For
Often power assesses vector;E is sensitivity coefficient.
As 0≤XjDuring≤a, i.e., when index state is poor, punishment degree is maximum;Work as a<XjDuring≤b, punishment degree is with Xj's
Increase and reduce;Work as b<XjDuring≤c, neither punish nor encourage;Work as c<XjWhen≤1, incentive degree is with XjIncrease and increase
Greatly.Variable weight formula can be characterized to overall punishment and dynamical encourage by adjusting horizontal d, and d is bigger, and total punishment is got over incentive degree
Greatly.
Step S105, according to degree of membership and the variable weight weight of each state estimation index, determines unmanned vehicle
State estimation value.
Wherein, the comprehensive assessment value of each state estimation index of unmanned vehicle is:
If a=0.4, b=0.7, c=0.9, d=0.2, sensitivity coefficient e=0.2, the variable weight evaluation part result such as institute of table 9
Show (while being contrasted with often power assessment result).
The power subsystem of table 9 is often weighed assessment and contrasted with variable weight assessment result
Variable weight assessed value in table 9 often weighs assessed value with unmanned vehicle it can be seen from the often contrast of power assessed value and is
0.7329, but index 22 with 23 single index assessed value it is relatively low, higher comprehensive assessment value masks dynamical system may be because
For the potential faults caused by the relatively low index of two assessed values, it is impossible to reflect to objective reality the reality of unmanned plane dynamical system
Health status.Weight to dynamical system evaluation index is carried out after variable weight processing, from fig. 6 it can be seen that the power of each index
Value there occurs either large or small change.Wherein the 22nd, 23 often power weights be significantly improved, reached the purpose of punishment;
Normal power weight of the assessed value between 0.7-0.9 has declined, and normal power weight of the assessed value higher than 0.9 is basically unchanged (the
14th, 15,18 indexs), reach the purpose of excitation.As can be seen from Table 9, the comprehensive assessment value after variable weight is substantially reduced, comprehensive
Close assessment result and be down to 0.5986 by 0.7329, it is possible thereby to remind attendant to find index and the progress of hydraulic performance decline in time
Processing, it is to avoid the generation of failure.
For the validity of more effective checking institute's extracting method of the present invention, unmanned vehicle health state evaluation device is devised,
Power subsystem assesses interface and certain assessment result is shown as shown in Figure 7.
The health state evaluation result of power subsystem can be intuitively obtained by Fig. 7:Often power assessment result is
0.861383, variable weight assessment result is 0.689869, comprehensive to understand that power subsystem integrality is general;Assessed relative to normal power
As a result, variable weight assessment result down ratio is 0.199115, therefore system prompt there may be the relatively low index of assessed value.Through reality
Border verifies that the assessment result tallies with the actual situation, and demonstrates the feasibility of the subsystem function.
Especially, when carrying out state estimation to power subsystem, Judgement Matricies and the solution to judgment matrix are
It is crucial.Therefore the construction of judgment matrix is devised with solving interface, as shown in Figure 8.
The embodiment of the present invention, sets up the state estimation index model of unmanned vehicle, and to the shape of the unmanned vehicle
State evaluation index carries out distinguishing hierarchy, then sets up fuzzy judgment matrix according to each layer state evaluation index, and according to the mould
Paste judgment matrix obtains the normal power weight of each state estimation index, is calculated according to the degree of membership model of state estimation index
The degree of membership of each state estimation index, according to the normal power weight and degree of membership of each state estimation index and accordingly
The relation of threshold value, the normal power weight to each state estimation index enters Mobile state adjustment, obtains the change of each state estimation index
Weight is weighed, according to the variable weight weight and degree of membership of each state estimation index, the state estimation value of unmanned vehicle is determined, with true
Determine the state of unmanned vehicle, so as to make weight ask for process more objective reality, obtained assessment result is more conformed to
It is actual, and the harmony of each index weights can be protruded, it can more objectively reflect actual conditions, so as on board the aircraft
Found before it and eliminate potential faults.
The embodiment of the present invention, it is more objective that the normal power Weight Determination based on Triangular Fuzzy Number can make weight ask for process
See truly, obtained assessment result more conforms to reality;Introducing has excitation and the local variable weight method of punitive function to protrude respectively
The harmony of index weights, it can more objectively reflect actual conditions.
It should be understood that the size of the sequence number of each step is not meant to the priority of execution sequence, each process in above-described embodiment
Execution sequence should determine that the implementation process without tackling the embodiment of the present invention constitutes any limit with its function and internal logic
It is fixed.
Corresponding to the unmanned vehicle state evaluating method described in foregoing embodiments, Fig. 9 shows that the embodiment of the present invention is carried
The structured flowchart of the unmanned vehicle state evaluation device of confession.For convenience of description, it illustrate only portion related to the present embodiment
Point.
Reference picture 9, the device include model building module 101, weight obtain module 102, degree of membership computing module 103,
Weight adjusting module 104 and state determining module 105.
Model building module 101, the state estimation index model for setting up unmanned vehicle, and to the unmanned flight
The state estimation index of device carries out distinguishing hierarchy.Weight obtains module 102, for setting up fuzzy according to each layer state evaluation index
Judgment matrix, and obtain according to the fuzzy judgment matrix the normal power weight of each state estimation index.Degree of membership is calculated
Module 103, the degree of membership for calculating each state estimation index according to the degree of membership model of state estimation index.Weight
Adjusting module 104, it is right for the normal power weight and the relation of degree of membership and respective threshold according to each state estimation index
The normal power weight of each state estimation index enters Mobile state adjustment, obtains the variable weight power of each state estimation index
Weight.State determining module 105, for the variable weight weight and degree of membership according to each state estimation index, it is determined that nobody flies
The state estimation value of row device.
Optionally, weight obtains module 102 and sets up unit and weight calculation unit including matrix.Matrix sets up unit, uses
In each state estimation index is contrasted two-by-two to each layer by expert method, the fuzzy judgment matrix is set up.Weight calculation unit,
For carrying out consistency check processing to the fuzzy judgment matrix, and according to described fuzzy after consistency check is handled
Judgment matrix calculates the normal power weight of each state estimation index.
Optionally, the fuzzy judgment matrix is:
Wherein, expert's quantity is K, and the weight of k-th of expert is rk,Represent that the Triangular Fuzzy Number of k-th of expert judges
Matrix,It is Triangular Fuzzy Number,WithLower bound and the upper bound of fuzzy number are represented respectively;It is fuzzy numberIntermediate value.
Optionally, weight calculation unit specifically for:Calculate the Fuzzy Complementary Judgment Matrices of the fuzzy judgment matrix;Will
The Fuzzy Complementary Judgment Matrices are converted into fuzzy consistent matrix, and carry out consistency check to the fuzzy consistent matrix
Processing;When the fuzzy consistent matrix meets consistency check, fuzzy judgment matrix each described is solved, it is determined that
The normal power weight of each state estimation index.
Optionally, weight calculation unit is specially to fuzzy consistent matrix progress consistency check processing:
Pass through formulaWithBy the fuzzy reciprocal judgment square
Battle array M is converted into the fuzzy consistent matrix M', wherein, n is matrix M exponent number;By extracting in the fuzzy judgment matrix A
The most probable estimate of multilevel iudge information, obtains the Fuzzy Complementary Judgment Matrices M, the Fuzzy Complementary Judgment Matrices two-by-two
The i-th row jth column element in M is
The fuzzy consistent matrix M' is examined whether to meet consistency check by calculating δ and σ, wherein δ=max |
m′ij-mij|,If δ<0.2,σ<0.1, then it represents that the fuzzy consistent matrix is met
Consistency check, otherwise performs and described sets up fuzzy judgment matrix step according to each layer state evaluation index.
Optionally, the weight calculation unit is when the fuzzy consistent matrix meets consistency check, to each institute
State fuzzy judgment matrix to be solved, the process for determining the normal power weight of each state estimation index is specially:
Triangular Fuzzy Number in fuzzy judgment matrix is converted into non-fuzzy number;Assuming that m possibility size be X times of l,
Y times of u, then the calculation formula that Triangular Fuzzy Number a=(l m u) is converted into non-fuzzy number is:
A=l/2 (1+X)+[m (X+2XY+Y)]/[2 (1+X) (1+Y)]+u/2 (1+Y)
Index weights are asked for according to the result of calculation that Triangular Fuzzy Number is converted into non-fuzzy number;Often weigh weight solution formula
For:
Wherein, aijRepresent that i-th of index and j-th of index compare obtained non-fuzzy number, w two-by-twoiRepresent i-th of index
The normal weight of synthesis.
Optionally, degree of membership computing module 103 includes division unit and processing unit.
Division unit, it is described quantitative for each described state estimation index to be divided into quantitative target and qualitative index
The index that index characterization can be expressed with digital quantization, the qualitative index, which is characterized, can not be expressed with digital quantization and use text
Word or the index of iamge description.
Processing unit, for by quantitative target nondimensionalization processing, drawing the degree of membership of each quantitative target;
By the word description or the corresponding relation of iamge description and degree of membership of the qualitative index set in advance, draw described qualitative
The degree of membership of index.
Optionally, weight adjusting module 104 specifically for:
Assuming that evaluation index collection U=(A1,A2,A3,...,Am) in, the degree of membership of each state estimation index is X=(X1,X2,
X3,...,Xm) ∈ [0,1], definition:
For often power weight vectors, meet:
Given mapping S:[0,1]m→(0,∞)m, claim vector Sx=(S1(x),S2(x),S3(x),...,Sm(x)) to be local
State variable weight vector, is tried to achieve by local variable weight formula;
Given mapping w:[0,1]m→(0,∞)m, claim vector W (x)=(W1(x),W2(x),W3(x),…,Wm(x) it is) change
Weight vectors are weighed, wherein:Meet
Local variable weight formula is:
Normal power weight to state estimation index each described is adjusted;Wherein, m is monitoring index number, j=1,2,
3,…,m;A, b, c, d are the parameter in [0,1], and a<b<c;Vector is assessed for often power;E is sensitivity coefficient,For often power weight vectors, Wi 0For W0I-th of element.
The state determining module 105 determines that the state estimation value of the unmanned vehicle is:
It is apparent to those skilled in the art that, for convenience of description and succinctly, only with above-mentioned each work(
Energy unit, the division progress of module are for example, in practical application, as needed can distribute above-mentioned functions by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.In addition, each function list
Member, the specific name of module are also only to facilitate mutually differentiation, is not limited to the protection domain of the application.Said system
The specific work process of middle unit, module, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed apparatus and method, others can be passed through
Mode is realized.For example, system embodiment described above is only schematical, for example, the division of the module or unit,
It is only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component can be with
With reference to or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed
Coupling each other or direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING of device or unit or
Communication connection, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, the present invention realizes above-described embodiment side
All or part of flow in method, can also control the hardware of correlation to complete, described computer by computer program
Program can be stored in a computer-readable recording medium, and the computer program can be achieved above-mentioned each when being executed by processor
The step of individual embodiment of the method.Wherein, the computer program includes computer program code, and the computer program code can
Think source code form, object identification code form, executable file or some intermediate forms etc..The computer-readable medium can be with
Including:Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disc, light of the computer program code can be carried
Disk, computer storage, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random
Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the computer
The content that computer-readable recording medium is included can carry out appropriate increase and decrease according to legislation in jurisdiction and the requirement of patent practice, for example
In some jurisdictions, according to legislation and patent practice, computer-readable medium does not include being electric carrier signal and telecommunications letter
Number.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those within the art that:It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic;And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should
Within protection scope of the present invention.
Claims (10)
1. a kind of unmanned vehicle state evaluating method, it is characterised in that including:
The state estimation index model of unmanned vehicle is set up, and level is carried out to the state estimation index of the unmanned vehicle
Divide;
Fuzzy judgment matrix is set up according to each layer state evaluation index, and each shape is obtained according to the fuzzy judgment matrix
The normal power weight of state evaluation index;
The degree of membership of each state estimation index is calculated according to the degree of membership model of state estimation index;
According to the normal power weight and the relation of degree of membership and respective threshold of each state estimation index, to state each described
The normal power weight of evaluation index enters Mobile state adjustment, obtains the variable weight weight of each state estimation index;
According to the variable weight weight and degree of membership of each state estimation index, the state estimation value of unmanned vehicle is determined.
2. unmanned vehicle state evaluating method according to claim 1, it is characterised in that described to be commented according to each layer state
Estimate Index Establishment fuzzy judgment matrix, and obtain according to the fuzzy judgment matrix Chang Quanquan of each state estimation index
Include again:
By expert method, to each layer, each state estimation index is contrasted two-by-two, sets up the fuzzy judgment matrix;
Consistency check processing is carried out to the fuzzy judgment matrix, and according to the module after consistency check is handled
Judgment matrix calculates the normal power weight of each state estimation index.
3. unmanned vehicle state evaluating method according to claim 2, it is characterised in that the fuzzy judgment matrix
For:
<mrow>
<mi>A</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</munderover>
<msub>
<mi>r</mi>
<mi>k</mi>
</msub>
<msup>
<mi>A</mi>
<mi>k</mi>
</msup>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</munderover>
<msub>
<mi>r</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
<mo>=</mo>
<mfenced open = "(" close = ")">
<mtable>
<mtr>
<mtd>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</munderover>
<msub>
<mi>r</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>l</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
</mrow>
</mtd>
<mtd>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</munderover>
<msub>
<mi>r</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>m</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
</mrow>
</mtd>
<mtd>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</munderover>
<msub>
<mi>r</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, expert's quantity is K, and the weight of k-th of expert is rk,The Triangular Fuzzy Number judgment matrix of k-th of expert is represented,It is Triangular Fuzzy Number,WithLower bound and the upper bound of fuzzy number are represented respectively;It is fuzzy numberIn
Value.
4. unmanned vehicle state evaluating method according to claim 2, it is characterised in that described to the fuzzy Judgment
Matrix carries out consistency check processing, and calculates each institute according to the fuzzy judgment matrix after consistency check is handled
Stating the normal power weight of state estimation index includes:
Calculate the Fuzzy Complementary Judgment Matrices of the fuzzy judgment matrix;
The Fuzzy Complementary Judgment Matrices are converted into fuzzy consistent matrix, and the fuzzy consistent matrix carried out consistent
Property inspection processing;
When the fuzzy consistent matrix meets consistency check, judge that the fuzzy judgment matrix meets uniformity, and it is right
Each described fuzzy judgment matrix is solved, and determines the normal power weight of each state estimation index.
5. unmanned vehicle state evaluating method according to claim 4, it is characterised in that described to the fuzzy consensus
Property matrix carry out consistency check processing be specially:
The most probable estimate of multilevel iudge information two-by-two is extracted in the fuzzy judgment matrix A, the Fuzzy Complementary is obtained and sentences
Disconnected matrix M;Wherein, the element of the i-th row jth row of the Fuzzy Complementary Judgment Matrices M
Pass through formulaWith m 'ij=(mi'-m'j)/[2 (n-1)]+0.5 by the Fuzzy Complementary Judgment Matrices M convert
For the fuzzy consistent matrix M', wherein, n is matrix M exponent number;
The fuzzy consistent matrix M' is examined whether to meet consistency check by calculating δ and σ, wherein δ=max | m 'ij-mij
|,If δ<0.2,σ<0.1, then it represents that the fuzzy consistent matrix meets uniformity
Examine, judge that the fuzzy judgment matrix meets uniformity, otherwise perform described set up according to each layer state evaluation index and obscure
Judgment matrix step.
6. unmanned vehicle state evaluating method according to claim 4, it is characterised in that described to being obscured each described
Judgment matrix is solved, and the normal power weight for determining each state estimation index is specially:
Triangular Fuzzy Number in fuzzy judgment matrix is converted into non-fuzzy number;Assuming that m possibility size is X times of l, u Y
Times, then the calculation formula that Triangular Fuzzy Number a=(l m u) is converted into non-fuzzy number is:
A=l/2 (1+X)+[m (X+2XY+Y)]/[2 (1+X) (1+Y)]+u/2 (1+Y)
Index weights are asked for according to the result of calculation that Triangular Fuzzy Number is converted into non-fuzzy number;Often power weight solution formula is:
<mrow>
<msub>
<mi>w</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>/</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
</mrow>
Wherein, aijRepresent that i-th of index and j-th of index compare obtained non-fuzzy number, w two-by-twoiRepresent the comprehensive of i-th index
Close often power weight.
7. unmanned vehicle state evaluating method according to claim 1, it is characterised in that described to be referred to according to state estimation
The degree of membership that target degree of membership model calculates each state estimation index includes:
Each described state estimation index is divided into quantitative target and qualitative index, the quantitative target, which is characterized, can use numeral
The index of quantitative expression, the qualitative index, which is characterized, can not be expressed with digital quantization and use word or the finger of iamge description
Mark;
The quantitative target is subjected to nondimensionalization processing, the degree of membership of each quantitative target is drawn;
By the word description or the corresponding relation of iamge description and degree of membership of the qualitative index set in advance, draw described
The degree of membership of qualitative index.
8. unmanned vehicle state evaluating method according to claim 1, it is characterised in that described according to each shape
The normal power weight and the relation of degree of membership and respective threshold of state evaluation index, to the normal power weight of state estimation index each described
Entering Mobile state adjustment includes:
Assuming that evaluation index collection U=(A1,A2,A3,...,Am) in, the degree of membership of each state estimation index is X=(X1,X2,
X3,...,Xm) ∈ [0,1], definition:
For often power weight vectors, meet:
Given mapping S:[0,1]m→(0,∞)m, claim vector Sx=(S1(x),S2(x),S3(x),...,Sm(x)) it is local state
Variable weight vector, is tried to achieve by local variable weight formula;
Given mapping w:[0,1]m→(0,∞)m, claim vector W (x)=(W1(x),W2(x),W3(x),…,Wm(x)) weighed for variable weight
Weight vector, wherein:Meet
Local variable weight formula is:
<mrow>
<msub>
<mi>S</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mfrac>
<mn>1</mn>
<mi>e</mi>
</mfrac>
<mo>&CenterDot;</mo>
<mrow>
<mo>(</mo>
<msup>
<mi>b</mi>
<mrow>
<mn>1</mn>
<mo>/</mo>
<msubsup>
<mi>mW</mi>
<mi>j</mi>
<mn>0</mn>
</msubsup>
</mrow>
</msup>
<mo>+</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>&le;</mo>
<mi>a</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mfrac>
<mn>1</mn>
<mi>e</mi>
</mfrac>
<mo>&CenterDot;</mo>
<mo>{</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mi>b</mi>
<mrow>
<mo>(</mo>
<mi>b</mi>
<mo>-</mo>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mi>b</mi>
<mo>-</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mrow>
<mn>1</mn>
<mo>/</mo>
<msubsup>
<mi>mW</mi>
<mi>j</mi>
<mn>0</mn>
</msubsup>
</mrow>
</msup>
<mo>+</mo>
<mi>d</mi>
<mo>}</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>a</mi>
<mo><</mo>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>&le;</mo>
<mi>b</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mfrac>
<mn>1</mn>
<mi>e</mi>
</mfrac>
<mo>&CenterDot;</mo>
<mi>d</mi>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>b</mi>
<mo><</mo>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>&le;</mo>
<mi>c</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mi>b</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mrow>
<mn>1</mn>
<mo>/</mo>
<msubsup>
<mi>mW</mi>
<mi>j</mi>
<mn>0</mn>
</msubsup>
</mrow>
</msup>
<mo>+</mo>
<mi>d</mi>
<mo>&CenterDot;</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>+</mo>
<mfrac>
<mn>1</mn>
<mi>e</mi>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo><</mo>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>&le;</mo>
<mn>1</mn>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Normal power weight to state estimation index each described is adjusted;Wherein, m is monitoring index number, j=1,2,
3,…,m;A, b, c, d are the parameter in [0,1], and a<b<c;Vector is assessed for often power;E is sensitivity coefficient,For often power weight vectors, Wi 0For W0I-th of element.
9. unmanned vehicle state evaluating method according to claim 1, it is characterised in that the shape of the unmanned vehicle
State assessed value is
10. a kind of unmanned vehicle state evaluation device, it is characterised in that including:
Model building module, the state estimation index model for setting up unmanned vehicle, and to the shape of the unmanned vehicle
State evaluation index carries out distinguishing hierarchy;
Weight obtains module, for setting up fuzzy judgment matrix according to each layer state evaluation index, and according to the fuzzy Judgment
Matrix obtains the normal power weight of each state estimation index;
Degree of membership computing module, for calculating each state estimation index according to the degree of membership model of state estimation index
Degree of membership;
Weight adjusting module, for the normal power weight according to each state estimation index and the pass of degree of membership and respective threshold
System, the normal power weight to state estimation index each described enters Mobile state adjustment, obtains the change of each state estimation index
Weigh weight;
State determining module, for the variable weight weight and degree of membership according to each state estimation index, determines unmanned flight
The state estimation value of device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710526643.3A CN107330521A (en) | 2017-06-30 | 2017-06-30 | Unmanned vehicle state evaluating method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710526643.3A CN107330521A (en) | 2017-06-30 | 2017-06-30 | Unmanned vehicle state evaluating method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107330521A true CN107330521A (en) | 2017-11-07 |
Family
ID=60198064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710526643.3A Pending CN107330521A (en) | 2017-06-30 | 2017-06-30 | Unmanned vehicle state evaluating method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107330521A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107703884A (en) * | 2017-11-15 | 2018-02-16 | 山东师范大学 | A kind of Digit Control Machine Tool availability improved method and device |
CN109978391A (en) * | 2019-03-29 | 2019-07-05 | 云南电网有限责任公司电力科学研究院 | A kind of non-through type needle pierces the appraisal procedure and assessment system of cable safety in operation under defect |
CN110472869A (en) * | 2019-08-15 | 2019-11-19 | 中国国际航空股份有限公司 | Flight operation risk calculation method, device, equipment and readable storage medium storing program for executing |
CN111929576A (en) * | 2020-09-27 | 2020-11-13 | 通号(长沙)轨道交通控制技术有限公司 | Vacuum circuit breaker health state assessment method based on combined empowerment method |
CN112559936A (en) * | 2020-12-16 | 2021-03-26 | 北京百度网讯科技有限公司 | Community content processing method and device, electronic equipment and storage medium |
CN114398769A (en) * | 2021-12-29 | 2022-04-26 | 中国人民解放军92728部队 | Automatic score obtaining method for unmanned helicopter flight control system |
CN117808212A (en) * | 2024-02-29 | 2024-04-02 | 山东金宇信息科技集团有限公司 | Automatic emergency processing method, equipment and medium for emergency unmanned equipment |
-
2017
- 2017-06-30 CN CN201710526643.3A patent/CN107330521A/en active Pending
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107703884A (en) * | 2017-11-15 | 2018-02-16 | 山东师范大学 | A kind of Digit Control Machine Tool availability improved method and device |
CN107703884B (en) * | 2017-11-15 | 2020-01-31 | 山东师范大学 | method and device for improving usability of numerical control machine tool |
CN109978391A (en) * | 2019-03-29 | 2019-07-05 | 云南电网有限责任公司电力科学研究院 | A kind of non-through type needle pierces the appraisal procedure and assessment system of cable safety in operation under defect |
CN110472869A (en) * | 2019-08-15 | 2019-11-19 | 中国国际航空股份有限公司 | Flight operation risk calculation method, device, equipment and readable storage medium storing program for executing |
CN111929576A (en) * | 2020-09-27 | 2020-11-13 | 通号(长沙)轨道交通控制技术有限公司 | Vacuum circuit breaker health state assessment method based on combined empowerment method |
CN112559936A (en) * | 2020-12-16 | 2021-03-26 | 北京百度网讯科技有限公司 | Community content processing method and device, electronic equipment and storage medium |
CN114398769A (en) * | 2021-12-29 | 2022-04-26 | 中国人民解放军92728部队 | Automatic score obtaining method for unmanned helicopter flight control system |
CN117808212A (en) * | 2024-02-29 | 2024-04-02 | 山东金宇信息科技集团有限公司 | Automatic emergency processing method, equipment and medium for emergency unmanned equipment |
CN117808212B (en) * | 2024-02-29 | 2024-05-24 | 山东金宇信息科技集团有限公司 | Automatic emergency processing method, equipment and medium for emergency unmanned equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107330521A (en) | Unmanned vehicle state evaluating method and device | |
CN102750411B (en) | Urban dynamic micro-simulation method based on multi-agent discrete choice model | |
CN107123982A (en) | A kind of distribution network reliability analysis method of economic benefit based on equipment alteration | |
CN108520357A (en) | A kind of method of discrimination, device and the server of line loss abnormal cause | |
CN106779129A (en) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor | |
CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
CN103971023B (en) | R&D process quality automatic evaluation system and method | |
CN108090613A (en) | A kind of approach control sector ATC controller workload Forecasting Methodology | |
CN102707256A (en) | Fault diagnosis method based on BP-Ada Boost nerve network for electric energy meter | |
CN107609754A (en) | A kind of grid information system performance monitoring system and method | |
CN107633030A (en) | Credit estimation method and device based on data model | |
CN107025503A (en) | Across company software failure prediction method based on transfer learning and defects count information | |
CN102663264A (en) | Semi-supervised synergistic evaluation method for static parameter of health monitoring of bridge structure | |
CN107633455A (en) | Credit estimation method and device based on data model | |
CN112016826A (en) | Method and device for determining corrosion degree of transformer substation equipment and computer equipment | |
CN104008433A (en) | Method for predicting medium-and-long-term power loads on basis of Bayes dynamic model | |
CN106651160A (en) | Second-hand vehicle quality assessment method and device | |
CN107527131A (en) | A kind of cluster electric system energy consumption level evaluation method and device | |
CN111639882A (en) | Deep learning-based power utilization risk judgment method | |
CN112288172A (en) | Prediction method and device for line loss rate of transformer area | |
CN108805471A (en) | Evaluation method for water resources carrying capacity based on the analysis of hybrid system interactively | |
CN103942251A (en) | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods | |
CN104517233A (en) | Spaceflight single-unit product maturity control method | |
CN104462787B (en) | Aeronautical maintenance human factor reliability assessment method based on rough set theory (RST)/interval analytic hierarchy process (IAHP) | |
CN110033165A (en) | The recommended method of overdue loaning bill collection mode, device, medium, electronic equipment |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20180329 Address after: 210001 post Camp Road, Qinhuai District, Nanjing, Jiangsu Province, No. 88 Applicant after: ARMY ENGINEERING University OF PLA Address before: 050003 Heping West Road, Hebei, Shijiazhuang, No. 97 Applicant before: Army Engineering University of PLA |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171107 |