CN103308855A - Wind turbine generator system fault diagnosis method and device based on gray correlation - Google Patents

Abstract

The invention discloses a wind turbine generator system fault diagnosis method and device based on gray correlation. The method comprises the following steps of supposing that m fault types exist, wherein each fault type can be represented by n fault character vectors; determining a character reference vector of each fault type, obtaining m*n dimensional character reference vector spaces of m fault types on the basis of all character reference vectors, and obtaining correlation coefficients of various character reference vectors in to-be-diagnosed vectors and character reference vector space according to a correlation coefficient calculation formula; obtaining total correlation degree of the to-be-diagnosed vectors to different faults of the m fault types by a correlation degree calculation formula, and performing normalized processing on the correlation degree to obtain a confidence value of the to-be-diagnosed vector in different faults; and performing Dempster combination rule fusion on multiple evidences according to a fusion formula to obtain the final diagnosis result. By adopting the method and the device provided by the invention, the confidence degree of the fault mode is greatly enhanced, thus the fault diagnosis can be carried out conveniently and effectively.

Description

Wind power generating set method for diagnosing faults and device based on grey correlation

Technical field

The present invention particularly relates to a kind of wind power generating set method for diagnosing faults and device based on grey correlation about a kind of wind power generating set method for diagnosing faults and device.

Background technology

Along with the wind power generating set installed capacity does not increase very much, its ratio in electrical network is also improving year by year, and therefore before fault causes the accident it being carried out fault diagnosis also becomes extremely important.Multi-source information is often diagnosed than single source information to have better practical function with its correlativity that has and complementarity.Yet the reasons such as imperfection owing to complicacy, sensor or the observer's of environment itself limitation, technology for information acquisition or method, these information show uncertain (Uncertain), unknown (Vague), non-accurately (Imprecise) and incomplete features such as (Incomplete) usually, can be referred to as them and be imperfection (Imperfection).The specific descriptions of information imperfection are important steps of main equipment fault diagnosis, also are the bases of the later stage merging judgement.

Based on the information fusion method of the evidence theory advantage with aspects such as its expression at uncertain information, tolerance and combinations, in fault diagnosis field, be used widely, be proved to be a kind of effective method, yet how never extract the difficult point that basic degree of confidence BPA (basic probability assignment) is the fault diagnosis in the integrity information, also do not have concrete grammar now.Therefore, be necessary to propose a kind of technological means in fact, with head it off.

Summary of the invention

For overcoming the deficiency that above-mentioned prior art exists, the present invention's purpose is to provide a kind of wind power generating set method for diagnosing faults and device based on grey correlation, it never obtains basic degree of confidence (BPA) in the integrity information based on the grey correlation theory, utilize the rule of combination of evidence theory to carry out the multi-source fusion then, the degree of confidence of fault mode is increased greatly, be convenient to carry out effectively fault and judge.

For reaching above-mentioned and other purpose, the present invention proposes a kind of wind power generating set method for diagnosing faults based on grey correlation, comprises the steps:

Step 1 supposes to have m fault type, and each fault type of this m fault exists n fault signature vector to characterize;

Step 2 is determined the feature reference vector of each fault type;

Step 3 on the basis of whole feature reference vectors, obtains the m * n dimensional feature reference vector space of m fault type, and obtains to wait to diagnose the correlation coefficient of each feature reference vector in vector and the feature reference vector space according to the correlation coefficient computing formula;

Step 4 is utilized degree of association computing formula to obtain to wait to diagnose vector to the total correlation degree of m fault type different faults, and the degree of association is carried out normalized, namely obtains this and waits to diagnose vector to the value of the confidence of different faults; And

Step 5 waits to diagnose vector to the value of the confidence of different faults according to this that obtains, and according to fusion formula many evidences is carried out the Dempster rule of combination and merges, and obtains final diagnostic result.

Further, this correlation coefficient computing formula is:

${\mathrm{\ϵ}}_i\left(k\right)=\frac{\underset{i}{\min }\underset{k}{\min }|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_0\left(k\right)-X_i\left(k\right)|}{|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_o\left(k\right)-X_i\left(k\right)|}$

Wherein, X ₀(k) be each feature reference vector, X _i(k) for treating the diagnosis vector, ρ ∈ [0 ,+∞] is resolution ratio, ε _i(k) for waiting to diagnose the correlation coefficient of vector and each feature reference vector.

Further, this degree of association computing formula is:

$r_i=\frac{1}{n}\underset{k=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{\ϵ}}_i\left(k\right)$

Wherein, r _iWait to diagnose vector to the total correlation degree of m different faults.

Further, in step 4, by the following method the degree of association is carried out normalized, obtains this and wait to diagnose vectorial the value of the confidence to different faults:

$m_1=\frac{{\mathrm{\ρ}}_1}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},m_2=\frac{{\mathrm{\ρ}}_2}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},...m_k=\frac{{\mathrm{\ρ}}_m}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i}.$

Wherein, m _iFor waiting to diagnose vector to the value of the confidence of different faults, { ρ ₁, ρ ₂..., ρ _mFor treating that the diagnosis vector is to m different faults { y ₁, y ₂..., y _mThe total correlation degree.

Further, this fusion formula is:

$m\left(A\right)=(m_1\⊕m_2)\left(A\right)=\frac{\underset{B\∩C=A}{\mathrm{\Σ}}{m}_1\left(B\right)m_2\left(C\right)}{1-k}$

Wherein

The conflict factor or the contradiction factor for evidence.

For reaching above-mentioned and other purpose, the present invention also provides a kind of wind power generating set trouble-shooter based on grey correlation, comprises at least:

Reference vector is confirmed module, supposes to have m fault type, and each fault type of this m fault type exists n fault signature vector to characterize, and confirms the feature reference vector of each fault type;

The correlation coefficient computing module on the basis of whole feature reference vectors, obtains the feature space of m fault type, utilizes the correlation coefficient computing formula to calculate and tries to achieve the correlation coefficient of waiting to diagnose each feature reference vector in vector and the feature space;

The degree of confidence acquisition module obtains to wait to diagnose vector to the total correlation degree of m fault type different faults according to degree of association computing formula, and this degree of association is carried out normalized, obtains this and waits to diagnose vector to the value of the confidence of different faults; And

The multi-source Fusion Module carries out the Dempster rule of combination according to fusion formula to the value of the confidence of a plurality of evidences and merges, and obtains final diagnostic result.

Further, this correlation coefficient computing formula is:

${\mathrm{\ϵ}}_i\left(k\right)=\frac{\underset{i}{\min }\underset{k}{\min }|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_0\left(k\right)-X_i\left(k\right)|}{|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_o\left(k\right)-X_i\left(k\right)|}$

Wherein, X ₀(k) be each feature reference vector, X _i(k) for treating the diagnosis vector, ρ ∈ [0 ,+∞] is resolution ratio, ε _i(k) for waiting to diagnose the correlation coefficient of vector and each feature reference vector.

Further, this degree of association computing formula is:

$r_i=\frac{1}{n}\underset{k=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{\ϵ}}_i\left(k\right)$

Wherein, r _iWait to diagnose vector to the total correlation degree of m different faults.

Further, the degree of confidence acquisition module carries out normalized to the degree of association by the following method, obtains this and waits to diagnose vectorial the value of the confidence to different faults:

$m_1=\frac{{\mathrm{\ρ}}_1}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},m_2=\frac{{\mathrm{\ρ}}_2}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},...m_k=\frac{{\mathrm{\ρ}}_m}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i}.$

Further, this fusion formula is:

$m\left(A\right)=(m_1\⊕m_2)\left(A\right)=\frac{\underset{B\∩C=A}{\mathrm{\Σ}}{m}_1\left(B\right)m_2\left(C\right)}{1-k}$

Wherein

The conflict factor or the contradiction factor for evidence.

Compared with prior art, a kind of wind power generating set method for diagnosing faults based on grey correlation of the present invention, utilize the grey correlation theory to obtain and wait to diagnose vector to the basic degree of confidence of different faults, utilize the rule of combination of evidence theory to carry out the multi-source fusion then, the degree of confidence of fault mode is increased greatly, be convenient to carry out effectively fault and judge.

Description of drawings

Fig. 1 is the flow chart of steps of a kind of wind power generating set method for diagnosing faults based on grey correlation of the present invention;

Fig. 2 obtains synoptic diagram for the BPA of pattern i to be checked in the preferred embodiment of the present invention;

Fig. 3 is M bar evidence fusion process synoptic diagram in the preferred embodiment of the present invention;

Fig. 4 is the system architecture diagram of a kind of wind power generating set trouble-shooter based on grey correlation of the present invention.

Embodiment

Below by specific instantiation and accompanying drawings embodiments of the present invention, those skilled in the art can understand other advantage of the present invention and effect easily by the content that this instructions discloses.The present invention also can be implemented or be used by other different instantiation, and the every details in this instructions also can be based on different viewpoints and application, carries out various modifications and change under the spirit of the present invention not deviating from.

Before introducing the present invention, introduce the related notion of grey correlation theory used herein and Dempster rule of combination earlier:

Define 2.1 correlation coefficients

Choose reference sequence: X ₀={ X ₀(k) | k=1,2 ..., n}={X ₀(1), X ₀(2) ... X ₀(n) }, wherein k represents constantly.Suppose to have m relatively ordered series of numbers:

X _i＝{X _i(k)｜k＝1，2，…，n}＝{X _i(1)，X _i(2)，…，X _i(n)}i＝1，2，…，m

Then claim:

${\mathrm{\ϵ}}_i\left(k\right)=\frac{\underset{i}{\min }\underset{k}{\min }|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_0\left(k\right)-X_i\left(k\right)|}{|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_o\left(k\right)-X_i\left(k\right)|}---\left(1\right)$

Be more vectorial X _iTo reference sequence X ₀At the correlation coefficient that k is ordered, wherein ρ ∈ [0 ,+∞] is resolution ratio.

In the title formula (1) Be the two-stage lowest difference,

Be two-stage maximum difference.Generally get resolution ratio ρ ∈ [0,1].By finding out easily in the formula (1) that ρ is more big, resolution is more big;

ρ is more little, and resolution is more little.Here generally get ρ=0.5.

Define 2.2 degrees of association

Formula (1) is to describe relatively ordered series of numbers and reference sequence in some points or index of correlation degree constantly, because each moment point has an incidence number, so information seems and too disperse, and is not easy to unified the comparison, provides a formula of total correlation degree at this:

$r_i=\frac{1}{n}\underset{k=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{\ϵ}}_i\left(k\right)---\left(2\right)$

r _iBe ordered series of numbers X _iTo reference sequence X ₀The degree of association.This degree of association has been gathered related size relatively more vectorial and the reference vector difference, therefore the research for this helps the relatively aggregate analysis of vector, in the present invention's BPA obtain manner, also mainly use the total correlation degree of fault vectors, pass judgment on the probability of happening of fault.

Definition 3.2Dempster rule of combination

Suppose m ₁And m ₂Be to be defined in 2 ^ΘOn 2 mass functions, its composite formula is

$m\left(A\right)=(m_1\⊕m_2)\left(A\right)=\frac{\underset{B\∩C=A}{\mathrm{\Σ}}{m}_1\left(B\right)m_2\left(C\right)}{1-k}---\left(3\right)$

$k=\underset{B\∩C=\mathrm{\φ}}{\mathrm{\Σ}}{m}_1\left(B\right)m_2\left(C\right)---\left(4\right)$

Wherein k is called the conflict factor or the contradiction factor of evidence, has reflected the conflict relationship between the evidence.Merging rule is that evidence theory is handled the many batches of methods that evidence acts on simultaneously at same framework of identification, also is the core of evidence theory.

Fig. 1 is the flow chart of steps of a kind of wind power generating set method for diagnosing faults based on grey correlation of the present invention.As shown in Figure 1, a kind of wind power generating set method for diagnosing faults based on grey correlation of the present invention comprises the steps:

Step 101 supposes to have m fault type { y ₁, y ₂..., y _m, there be n fault signature vector { x in each fault type of this m fault ₁, x ₂... x _nCharacterize;

Step 102 is determined each fault type { y ₁, y ₂..., y _mFeature reference vector { x _I1, x _I2... x _In| i=1,2 ..., for m fault, namely there be m reference vector in m}.This m reference vector formed the feature space of m * n dimension.For reference vector, can obtain by the reference historical experience or with the experimental data of obtaining;

Step 103 on the basis of whole proper vectors, obtains $\left[\begin{array}{c}{y}_1\\ y_2\\ .\\ .\\ .\\ y_m\end{array}\right]=\left[\begin{array}{cccccc}{x}_{11}& x_{12}& .& .& .& x_{1n}\\ x_{21}& x_{22}& .& .& .& x_{2n}\\ .& .& & & & .\\ .& .& .& .& .& .\\ .& .& & & & .\\ x_{m1}& x_{m2}& .& .& .& x_{\mathrm{mn}}\end{array}\right]$ Feature space.Correlation coefficient computing formula according to formula (1) can be tried to achieve vector x to be diagnosed _d={ x _D1, x _D2..., x _DnWith feature space in { x _I1, x _I2... x _In| i=1,2 ..., the correlation coefficient { ρ of m} _I1, ρ _I2... ρ _m| i=1,2 ..., m};

Step 104 treats that according to the degree of association computing formula acquisition of formula (2) the diagnosis vector is to { y ₁, y ₂..., y _mTotal correlation degree { the ρ of different faults ₁, ρ ₂..., ρ _m, this degree of association is carried out normalized, namely obtain this characteristic information to the value of the confidence BPA of different faults, as shown in Figure 2.

$m_1=\frac{{\mathrm{\ρ}}_1}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},m_2=\frac{{\mathrm{\ρ}}_2}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},...m_k=\frac{{\mathrm{\ρ}}_m}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i}.---\left(5\right)$

Step 105 after the BPA value of each fault of try to achieve, is carried out the Dempster rule of combination according to the fusion formula of formula (3) to many evidences and is merged, and takes into full account the independence of each evidence, and implementation is taken all factors into consideration, and obtains final diagnostic result, as shown in Figure 3.

Fig. 4 is the system architecture diagram of a kind of wind power generating set trouble-shooter based on grey correlation of the present invention.As shown in Figure 4, a kind of wind power generating set trouble-shooter based on grey correlation of the present invention comprises at least: reference vector is confirmed module 401, correlation coefficient computing module 402, degree of confidence acquisition module 403 and multi-source Fusion Module 404.

Wherein, reference vector is confirmed module 401, and at first hypothesis has m fault type { y ₁, y ₂..., y _m, there be n fault signature vector { x in each fault type of this m fault type ₁, x ₂... x _nCharacterize, confirm each fault type { y then ₁, y ₂..., y _mFeature reference vector { x _I1, x _I2... x _In| i=1,2 ..., m}.That is, for m fault, there be m reference vector.This m reference vector formed the feature space of m * n dimension.For reference vector, can obtain by the reference historical experience or with the experimental data of obtaining.

Correlation coefficient computing module 402 on the basis of whole feature reference vectors, obtains m fault type $\left[\begin{array}{c}{y}_1\\ y_2\\ .\\ .\\ .\\ y_m\end{array}\right]=\left[\begin{array}{cccccc}{x}_{11}& x_{12}& .& .& .& x_{1n}\\ x_{21}& x_{22}& .& .& .& x_{2n}\\ .& .& & & & .\\ .& .& .& .& .& .\\ .& .& & & & .\\ x_{m1}& x_{m2}& .& .& .& x_{\mathrm{mn}}\end{array}\right]$ Feature space utilizes the correlation coefficient computing formula calculating of formula (1) to try to achieve vector x to be diagnosed _d={ x _D1, x _D2..., x _DnWith feature space in { x _I1, x _I2... x _In| i=1,2 ..., the correlation coefficient { ρ of each feature reference vector of m} _I1, ρ _I2... ρ _In| i=1,2 ..., m}.

Degree of confidence acquisition module 403 treats that according to the degree of association computing formula acquisition of formula (2) the diagnosis vector is to m fault type { y ₁, y ₂..., y _mTotal correlation degree { the ρ of different faults ₁, ρ ₂..., ρ _m, and this degree of association carried out normalized, namely obtain this characteristic information to the value of the confidence BPA of different faults.

Multi-source Fusion Module 404 carries out the Dempster rule of combination according to the fusion formula of formula (3) to many evidences and merges, and takes into full account the independence of each evidence, and implementation is taken all factors into consideration, and obtains final diagnostic result

In sum, a kind of wind power generating set method for diagnosing faults based on grey correlation of the present invention, utilize the grey correlation theory to obtain and wait to diagnose vector to the basic degree of confidence of different faults, utilize the rule of combination of evidence theory to carry out the multi-source fusion then, the degree of confidence of fault mode is increased greatly, be convenient to carry out effectively fault and judge.

Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not is used for restriction the present invention.Any those skilled in the art all can be under spirit of the present invention and category, and above-described embodiment is modified and changed.Therefore, the scope of the present invention should be listed as claims.

Claims (10)

1. the wind power generating set method for diagnosing faults based on grey correlation comprises the steps:

Step 1 supposes to have m fault type, and each fault type of this m fault exists n fault signature vector to characterize;

Step 2 is determined the feature reference vector of each fault type;

Step 3 on the basis of whole feature reference vectors, obtains the m * n dimensional feature reference vector space of m fault type, and obtains to wait to diagnose the correlation coefficient of each feature reference vector in vector and the feature reference vector space according to the correlation coefficient computing formula;

Step 4 is utilized degree of association computing formula to obtain to wait to diagnose vector to the total correlation degree of m fault type different faults, and the degree of association is carried out normalized, namely obtains this and waits to diagnose vector to the value of the confidence of different faults; And

Step 5 waits to diagnose vector to the value of the confidence of different faults according to this that obtains, and according to fusion formula many evidences is carried out the Dempster rule of combination and merges, and obtains final diagnostic result.

2. a kind of wind power generating set method for diagnosing faults based on grey correlation as claimed in claim 1 is characterized in that this correlation coefficient computing formula is:

${\mathrm{\ϵ}}_i\left(k\right)=\frac{\underset{i}{\min }\underset{k}{\min }|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_0\left(k\right)-X_i\left(k\right)|}{|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_o\left(k\right)-X_i\left(k\right)|}$

Wherein, X ₀(k) be each feature reference vector, X _i(k) for treating the diagnosis vector, ρ ∈ [0 ,+∞] is resolution ratio, ε _i(k) for waiting to diagnose the correlation coefficient of vector and each feature reference vector.

3. a kind of wind power generating set method for diagnosing faults based on grey correlation as claimed in claim 2 is characterized in that this degree of association computing formula is:

$r_i=\frac{1}{n}\underset{k=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{\ϵ}}_i\left(k\right)$

Wherein, r _iWait to diagnose vector to the total correlation degree of m different faults.

4. a kind of wind power generating set method for diagnosing faults based on grey correlation as claimed in claim 1 is characterized in that, in step 4, by the following method the degree of association is carried out normalized, obtains this and waits to diagnose vectorial the value of the confidence to different faults:

$m_1=\frac{{\mathrm{\ρ}}_1}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},m_2=\frac{{\mathrm{\ρ}}_2}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},...m_k=\frac{{\mathrm{\ρ}}_m}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i}.$

Wherein, m _iFor waiting to diagnose vector to the value of the confidence of different faults, { ρ ₁, ρ ₂..., ρ _mFor treating that the diagnosis vector is to m different faults { y ₁, y ₂..., y _mThe total correlation degree.

5. a kind of wind power generating set method for diagnosing faults based on grey correlation as claimed in claim 4 is characterized in that this fusion formula is:

$m\left(A\right)=(m_1\⊕m_2)\left(A\right)=\frac{\underset{B\∩C=A}{\mathrm{\Σ}}{m}_1\left(B\right)m_2\left(C\right)}{1-k}$

Wherein

The conflict factor or the contradiction factor for evidence.

6. wind power generating set trouble-shooter based on grey correlation comprises at least:

Reference vector is confirmed module, supposes to have m fault type, and each fault type of this m fault type exists n fault signature vector to characterize, and confirms the feature reference vector of each fault type;

The correlation coefficient computing module on the basis of whole feature reference vectors, obtains the feature space of m fault type, utilizes the correlation coefficient computing formula to calculate and tries to achieve the correlation coefficient of waiting to diagnose each feature reference vector in vector and the feature space;

The degree of confidence acquisition module obtains to wait to diagnose vector to the total correlation degree of m fault type different faults according to degree of association computing formula, and this degree of association is carried out normalized, obtains this and waits to diagnose vector to the value of the confidence of different faults; And

The multi-source Fusion Module carries out the Dempster rule of combination according to fusion formula to the value of the confidence of a plurality of evidences and merges, and obtains final diagnostic result.

7. a kind of wind power generating set trouble-shooter based on grey correlation as claimed in claim 6 is characterized in that this correlation coefficient computing formula is:

${\mathrm{\ϵ}}_i\left(k\right)=\frac{\underset{i}{\min }\underset{k}{\min }|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_0\left(k\right)-X_i\left(k\right)|}{|X_0\left(k\right)-X_i\left(k\right)|+\mathrm{\ρ}\underset{i}{\max }\underset{k}{\max }|X_o\left(k\right)-X_i\left(k\right)|}$

Wherein, X ₀(k) be each feature reference vector, X _i(k) for treating the diagnosis vector, ρ ∈ [0 ,+∞] is resolution ratio, ε _i(k) for waiting to diagnose the correlation coefficient of vector and each feature reference vector.

8. a kind of wind power generating set trouble-shooter based on grey correlation as claimed in claim 7 is characterized in that this degree of association computing formula is:

$r_i=\frac{1}{n}\underset{k=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{\ϵ}}_i\left(k\right)$

Wherein, r _iWait to diagnose vector to the total correlation degree of m different faults.

9. a kind of wind power generating set trouble-shooter based on grey correlation as claimed in claim 6 is characterized in that the degree of confidence acquisition module carries out normalized to the degree of association by the following method, obtains this and waits to diagnose vectorial the value of the confidence to different faults:

$m_1=\frac{{\mathrm{\ρ}}_1}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},m_2=\frac{{\mathrm{\ρ}}_2}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i},...m_k=\frac{{\mathrm{\ρ}}_m}{\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{\ρ}}_i}.$

10. a kind of wind power generating set trouble-shooter based on grey correlation as claimed in claim 6 is characterized in that this fusion formula is:

$m\left(A\right)=(m_1\⊕m_2)\left(A\right)=\frac{\underset{B\∩C=A}{\mathrm{\Σ}}{m}_1\left(B\right)m_2\left(C\right)}{1-k}$

Wherein

The conflict factor or the contradiction factor for evidence.

Images