CN111428386B

CN111428386B - Elevator traction machine rotor fault diagnosis information fusion method based on complex network

Info

Publication number: CN111428386B
Application number: CN202010320015.1A
Authority: CN
Inventors: 徐晓滨; 胡家豪; 章振杰; 王琪冰; 茹晓英; 侯平智
Original assignee: Hangzhou Dianzi University
Current assignee: Hangzhou Dianzi University
Priority date: 2020-04-22
Filing date: 2020-04-22
Publication date: 2023-04-18
Anticipated expiration: 2040-04-22
Also published as: CN111428386A

Abstract

The invention relates to an elevator traction machine rotor fault diagnosis information fusion method based on a complex network. The correlation of the characteristic parameters is obtained by calculating the Pearson coefficients among the characteristic parameters, and the characteristic parameters are grouped according to the strength of the correlation; respectively calculating the similarity between sample data vectors according to the fault sample data of each group, and constructing a fault data complex network; acquiring a likelihood belief table and a reference center vector of each group by using a complex network community division method, and further acquiring corresponding reference evidence; and respectively activating the diagnostic evidences of each group aiming at the fault characteristic vector acquired on line, carrying out evidence fusion by using a Dempster combination rule, and making a fault decision by using the fused evidences to obtain a fault type corresponding to the on-line fault characteristic data. The invention carries out fusion reasoning of fault diagnosis evidence on the basis of a complex network and effectively improves the fault diagnosis precision of the elevator traction machine rotor by utilizing multi-source diagnosis information.

Description

Elevator traction machine rotor fault diagnosis information fusion method based on complex network

Technical Field

The invention relates to a complex network-based elevator traction machine rotor fault diagnosis information fusion method, and belongs to the technical field of elevator equipment state monitoring and fault diagnosis.

Background

The tractor is the power equipment of the elevator, is composed of a motor, a brake, a coupling, a reduction gearbox, a traction sheave, a frame and the like, and has the function of conveying and transmitting power to enable the elevator to normally run. Because the running working conditions of the elevator are complex and changeable, and uncertain factors in the installation, operation and maintenance processes are added, the traction machine serving as an elevator heart has frequent faults, the safe running of the elevator is influenced, even safety accidents are caused, and casualties and economic losses are caused. Therefore, it is imperative to monitor the state of the hoisting machine and accurately and efficiently diagnose the root cause of the failure.

The existing elevator traction machine mostly adopts a permanent magnet synchronous gearless traction machine, which comprises a machine base, a stator, a rotor body, a brake and the like, wherein the permanent magnet is fixed on the inner wall of the rotor body, the rotor body is arranged on a shaft through a key, and the shaft is arranged on a bilateral sealing deep groove ball bearing on a rear machine base and a self-aligning roller bearing on a front machine base. Identifying faults by vibration signals is a common mechanical equipment diagnosis strategy. During the operation of the traction machine, a plurality of components vibrate, and how to effectively utilize the vibration signals is the key for realizing accurate fault diagnosis. Considering the relevance and diversity among the collected vibration signal sample data, if such characteristics of the data can be deeply mined and utilized, the effectiveness of the diagnosis result must be improved.

As an emerging theoretical tool, the complex network can effectively model and analyze the incidence relation between entities (data), and provides support for solving the problem of data incidence analysis. Meanwhile, the information fusion method can properly dispose diversified data through integration of multi-source diagnosis data. Therefore, the invention provides an elevator traction machine rotor fault diagnosis information fusion method based on a complex network.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides an elevator traction machine rotor fault diagnosis information fusion method based on a complex network.

The correlation of the characteristic parameters is obtained by calculating the Pearson coefficients among the characteristic parameters, and the characteristic parameters are grouped according to the strength of the correlation; respectively calculating the similarity among sample data vectors according to the fault sample data of each group, and constructing a fault data complex network; acquiring a likelihood belief table and a reference center vector of each group by using a complex network community division method, and further acquiring corresponding reference evidence; the method comprises the steps of respectively activating diagnosis evidences of all groups aiming at fault feature vectors acquired on line, carrying out evidence fusion by using Dempster combination rules, making a fault decision by using the fused evidences, and obtaining a fault type corresponding to the on-line fault feature data.

The invention provides an elevator traction machine rotor fault diagnosis information fusion method based on a complex network, which comprises the following steps:

(1) Setting a fault set theta = { F) of an elevator tractor rotor ₁ ,…,F _i ,…,F _N |i＝1,2,…,N}，F _i And (3) representing the ith fault in the fault set theta, wherein N is the number of the fault modes contained in the elevator traction machine rotor.

(2) Let f _1,i ，f _2,i And f _3,i To reflect each fault F in the set of faults Θ _i The characteristic parameters are acceleration signals and are respectively provided by acceleration sensors at the fan end, the motor base and the motor shell driving end;

will f is _1,i ，f _2,i ，f _3,i And F _i Expressed as a set of samples M _i ＝{[f _1,i ,f _2,i ,f _3,i F _i ]|t＝1,2,3,…,S _i In which [ f ] _1,i (t),f _2,i (t),f _3,i (t),F _i ]Is a sample vector, S _i Denotes that the fault is F _i Sample data in the State, and denoted F _i Number of samples in state, take S _i Not less than 100; respectively sampling sample data under each fault state and representing the sample data in a set form

The total number of delta samples can be obtained>

| M | represents the number in the set M.

(3) Will fail F _i Sample data f acquired in state _1,i (t)、f _2,i (t) and f _3,i (t) is expressed as a sample set M _i ′＝{[f _1,i (t),f _2,i (t),f _3,i (t)]|t＝1,2,…,S _i Respectively sampling sample data in each fault state, and expressing the sample data in a set form

Satisfy delta = | M | = | M _i ′|，|M _i ' | denotes the set M _i ' the number of elements in the list.

(4) Carrying out correlation analysis on the sample fault characteristic parameters, and specifically calculating as follows:

two characteristic parameters with larger Pearson coefficients are grouped into the same group and marked as G _A The characteristic parameters with less correlation are classified into another group, denoted as G _B 。

(5) For two groups of characteristic data G obtained in the step (4) _A And G _B Respectively constructing data complex network Net ^A And Net ^B Described in similarity matrices A and B, a _i,j ，b _i,j Are elements in the matrices A and B, respectively, representing the sample x in each set of feature data _i And x _j Distance d between _i,j Is defined as formula (2):

a _i,j ＝exp(-15×d _i,j )，b _i,j ＝exp(-15×d _i,j ) (2)

in the formula (d) _i,j With the euclidean distance metric, the similarity of the sample itself is defined as 0, i.e. a when i = j _i,j ＝0，b _i,j ＝0。

(6) The complex network Net of data is divided by using the complex network community division principle ^A And Net ^B Is divided into K ₁ And K ₂ Class, is marked as

Grouping M sample vectors into>

To obtain K ₁ Class-corresponding sample Q _k1 ＝{[f _1,k1 (u _k1 ),f _2,k1 (u _k1 ),f _3,k1 (u _k1 ),F _k1 (u _k1 )]|u _k1 ＝1,2,…,U _k1 }，U _k1 Represents T _k1 Number of sample vectors in class, with Q _k1 ∈M，/>

F _k1 (u _k1 ) E.g. theta, and can be represented by K ₁ Obtaining K corresponding to the sample set M by taking the mean value of each sample-like vector ₁ A reference center vector, which may be denoted as C _k1 ＝[c _k1,1 ,c _k1,2 ,c _k1,3 ]Where K1=1,2, …, K ₁ 。

The same can put the sample vector in M into

In order to obtain K ₂ Class correspondence sample Q _k2 ＝{[f _2,k2 (u _k2 ),f _2,k2 (u _k2 ),f _3,k2 (u _k2 ),F _k2 (u _k2 )]|u _k2 ＝1,2,…,U _k2 }，U _k2 Represents T _k2 Number of sample vectors in class, with Q _k2 ∈M，/>

F _k2 (u _k2 ) E.g. theta, and can be represented by K ₂ Obtaining K corresponding to the sample set M by taking the mean value of each sample-like vector ₂ A reference center vector, which may be denoted as C _k2 ＝[c _k2,1 ,c _k2,2 ,c _k2,3 ]Where K2=1,2, …, K ₂ 。

(7) F obtained according to the step (2), the step (3), the step (5) and the step (6) _i And T _k1 、T _k2 The relational table shown in Table 1 and Table 2 is constructed to show F _i And T _k1 、F _i And T _k2 The corresponding relation between the two; n is a radical of _k1,i 、N _k2,i Respectively represents T _k1 、T _k2 The sample set corresponding to the class has a fault F _i In combination with

And &>

And

wherein N is more than or equal to 0 _k1,i 、N _k2,i ≤S _i 。

TABLE 1F _i And T _k1 Table of corresponding relationship between

TABLE 2F _i And T _k2 Table of corresponding relationship between

(8) According to the corresponding relation table obtained in the step (7), when the fault is F _i When the sample data is classified into the k1 and k2 likelihood functions, the likelihood functions are as follows:

and is provided with

Then the reference evidence of the i-th type fault corresponding to the k 1-th and k 2-th types can be defined as:

obtaining two parts of fault diagnosis reference evidence as

e _p1 ＝[e _p1,1 ,e _p1,2 ,…,e _p1,N ]，e _p2 ＝[e _p2,1 ,e _p2,2 ,…,e _p2,N ] (5)

Constructing likelihood confidence tables as shown in tables 3 and 4 to describe T _k1 、T _k2 And F _i The relationship between them.

TABLE 3T _k1 Similar confidence table

TABLE 4T _k2 Similar confidence table

(9) When the online monitoring obtains a fault characteristic parameter vector X (t) = [ f ] at t moment _1,i (t),f _2,i (t),f _3,i (t)]Thereafter, an importance weight w of the evidence is defined _k Description of evidence e _k Respectively solving the fault characteristic parameter vector and K according to the relative importance of the fault characteristic parameter vector and other evidences ₁ 、K ₂ A reference central vector

Euclidean distance between them and normalizing them to obtain Dis _k1 And Dis _k2 The calculation is as follows:

definition of w _k1 ＝Dis _k1 ，w _k2 ＝Dis _k2 。

(10) Using importance weights w of evidence _k To activate the reference evidence e _p The calculation is as follows:

e _{p_1} ＝w _k1 *e _p1 ＝[e _p1,1 ′,e _p1,2 ′,…,e _p1,N ′]，

e _{p_2} ＝w _k2 *e _p2 ＝[e _p2,1 ′,e _p2,2 ′,…,e _p2,N ′] (7)

e is to be _{p_1} 、e _{p_2} Respectively carrying out normalization to obtain diagnosis evidence e _p1 ′、e _p2 ′。

(11) Using Dempster combination rule pair e _p1 ′、e _p2 ' fusion is performed, and the fused diagnosis results are:

in the formula m ₁ 、m ₂ Let reference evidence m for two quality functions defined on Θ ₁ ＝e _p1 ′，m ₂ ＝e _p2 ' definition

Is a combined quality function>

Indicating that Dempster combination rules can act on two or more quality functions, and A, B, C are all fault type modes;

the diagnostic evidence after fusion was:

e _p ＝[m(1),m(2),…,m(N)] (9)

in the formula, m (1), m (2) and m (N) respectively represent the fault types which are normalized after fusion and are F ₁ 、F ₂ 、F _N And (5) reliability.

(12) Using the diagnostic evidence e obtained in step (11) _p And diagnosing the fault of the elevator traction machine rotor: e.g. of the type _p F corresponding to the maximum confidence value _i Is a faultThe characteristic parameter vector X (t) is the actual occurring failure mode.

In conclusion, the method comprises the steps of firstly determining a fault set and fault characteristic parameters of an elevator tractor rotor, and respectively sampling sample data in each fault state to obtain a fault characteristic data sample set; the correlation of the characteristic parameters is obtained by calculating Pearson coefficients among the characteristic parameters, and the characteristic parameters are grouped according to the strength of the correlation; respectively calculating the similarity between sample data vectors according to the fault sample data of each group, and constructing a fault data complex network; acquiring likelihood credibility tables and reference center vectors of all groups by using a complex network community division method, and further acquiring corresponding reference evidences; and respectively activating the diagnostic evidences of each group aiming at the fault characteristic vector acquired on line, carrying out evidence fusion by using a Dempster combination rule, and making a fault decision by using the fused evidences to obtain a fault type corresponding to the on-line fault characteristic data. The program (compiling environment Matlab) compiled by the method can run on a monitoring computer, and is combined with hardware such as a sensor, a data collector and the like to form an online monitoring system for carrying out real-time monitoring and fault diagnosis on the rotor state of the elevator traction machine.

The invention has the beneficial effects that: 1. grouping the characteristic data by calculating a Pearson coefficient, so that the constructed complex network community is more accurate; 2. the acquired reference center point is more accurate by using complex network community division, so that the acquisition of the reference evidence is more convenient and faster; 3. and defining the Euclidean distance from the sample vector to the community center as the evidence weight, thereby solving the defect of manually setting the evidence weight in the prior art.

Drawings

FIG. 1 is a block flow diagram of the method of the present invention.

Fig. 2 is a diagram of an elevator machine rotor fault diagnostic system.

Fig. 3 is a block diagram of an elevator traction machine rotor fault diagnosis system in an example of the method of the present invention.

Detailed Description

The invention relates to an elevator traction machine rotor fault diagnosis information fusion method based on a complex network, the flow chart of which is shown in figure 1, and the method comprises the following steps:

(1) Setting a fault set theta = { F) of an elevator traction machine rotor ₁ ,…,F _i ,…,F _N |i＝1,2,…,N}，F _i And (3) representing the ith fault in the fault set theta, wherein N is the number of the fault modes contained in the elevator traction machine rotor.

(2) Let f _1,i ，f _2,i And f _3,i To be able to reflect each fault F in the set of faults Θ _i The characteristic parameter is an acceleration signal, and the acceleration signals are respectively provided by acceleration sensors at the fan end, the motor base and the motor shell driving end, and f is measured by a sensor _1,i ，f _2,i ，f _3,i And F _i Expressed as a set of samples M _i ＝{[f _1,i ,f _2,i ,f _3,i F _i ]|t＝1,2,3,…,S _i In which [ f) _1,i (t),f _2,i (t),f _3,i (t),F _i ]Is a sample vector, S _i Indicates that the fault is F _i Sample data in the State, and denoted F _i Number of samples in state, take S _i Not less than 100; respectively sampling sample data under each fault state and representing the sample data in a set form

The total number of delta samples can be obtained>

| M | represents the number in the set M.

(3) Will fail F _i Sample data f acquired in state _1,i (t)、f _2,i (t) and f _3,i (t) is expressed as a sample set M _i ′＝{[f _1,i (t),f _2,i (t),f _3,i (t)]|t＝1,2,…,S _i And respectively sampling sample data in each fault state, and representing the sample data in a set form

Satisfy delta = | M | = | M _i ′|，|M _i ' | denotes the set M _i ' number of elements in.

two characteristic parameters with larger Pearson coefficients are classified into the same group and marked as G _A The characteristic parameters with less correlation are classified into another group, which is marked as G _B 。

a _i,j ＝exp(-15×d _i,j )，b _i,j ＝exp(-15×d _i,j ) (2)

Grouping M sample vectors into `>

The same can put the sample vector in M into

In order to obtain K ₂ Class-corresponding sample Q _k2 ＝{[f _2,k2 (u _k2 ),f _2,k2 (u _k2 ),f _3,k2 (u _k2 ),F _k2 (u _k2 )]|u _k2 ＝1,2,…,U _k2 }，U _k2 Represents T _k2 Number of sample vectors in class, with Q _k2 ∈M，/>

F _k2 (u _k2 ) E.g. theta, and can be represented by K ₂ Obtaining K corresponding to the sample set M by averaging the class sample vectors ₂ A reference center vector, which may be denoted as C _k2 ＝[c _k2,1 ,c _k2,2 ,c _k2,3 ]Wherein K2=1,2, …, K ₂ 。

And &>

And

wherein N is more than or equal to 0 _k1,i 、N _k2,i ≤S _i 。

TABLE 1F _i And T _k1 Table of corresponding relationship between

TABLE 2F _i And T _k2 Table of corresponding relationship between

For the convenience of understanding the correspondence table shown in table 1 and table 2, this is exemplified here. The elevator traction machine rotor shown in fig. 2 has N =3 failure modes F _i : eccentric F of tractor rotor ₁ Imbalance of the rotor of the traction machine F ₂ Loosening of parts of tractor rotor F ₃ Then the fault set Θ = { F ₁ ,F ₂ ,F ₃ Their common characteristic parameter f _1,i ，f _2,i And f _3,i And vibration signals are provided for acceleration sensors mounted at the fan end, the motor base and the motor housing drive end. Get S ₁ ＝600,S ₂ ＝300,S ₃ =120, sample data in each fault state is acquired through step (2), δ =1020 sample data are sampled in total, and f can be calculated through step (3) and step (4) ₁ 、f ₂ 、f ₃ Has a Pearson coefficient of r (f) ₁ ，f ₂ )＝0.0202，r(f ₁ ，f ₃ )＝-0.0907，r(f ₂ ，f ₃ ) = -0.1092, knows that f ₂ And f ₃ Has strong correlation, can convert f ₂ 、f ₃ Composition feature data G _A ，f ₁ Is another set of characteristic data G _B Obtaining Net through the calculation of the step (5) ^A And Net ^B Net is performed by the step (6) ^A Is divided into 4 communities with the community center of C ₁₁ ＝[0.0162，-0.115,0.0023],C ₁₂ ＝[-0.0256，0.0196,0.064],C ₁₃ ＝[0.0129，0.1764，-0.0044],C ₁₄ ＝[-0.0191，0.0358，-0.0324]The samples in M are classified as T in Table 1 in step (6) ₁ 、T ₂ 、T ₃ 、T ₄ Will Net ^B Is divided into 6 communities with the community center of C ₂₁ ＝[-0.0272,-0.0407,0.002],C ₂₂ ＝[-0.0695,0.0028,0.006],C ₂₃ ＝[0.0542,0.0286,0.008],C ₂₄ ＝[1.6053,0.0178,0.031],C ₂₅ ＝[-0.2823,0.0438,0.0023],C ₂₆ ＝[-0.6934,0.0225,0.0119]The samples in M are classified as T in Table 2 in step (6) ₁ 、T ₂ 、T ₃ 、T ₄ 、T ₅ 、T ₆ As follows:

TABLE 3F _i And T _k1 Table of corresponding relationship between

TABLE 4F _i And T _k2 Table of corresponding relationship between

and is provided with

obtaining two parts of fault diagnosis reference evidence as

TABLE 5T _k1 Similar confidence table

TABLE 6T _k2 Similar confidence table

For the convenience of understanding the correspondence table shown in table 5 and table 6, this example is given here. According to the corresponding relation table obtained in the step (7), when the fault state is F, the corresponding relation table is obtained through the formula (4) in the step (8) _i Hour is put into T in Table 5 ₁ 、T ₂ 、T ₃ 、T ₄ Likelihood function value of class

T in Table 6 ₁ 、T ₂ 、T ₃ 、T ₄ 、T ₅ 、T ₆ Likelihood function values of class are

Obtaining the fault F from the formula (4) in the step (8) ₁ Evidence e _p1,1 ＝[0.331,0.167,0.361,0.141] ^T ，e _p2,1 ＝[0.223,0.31,0.257,0,0.2083,0.0017] ^T Similarly, F can be obtained ₂ 、F ₃ Corresponding fault reference evidence e _p1,2 ＝[0.397,0.113,0.383,0.107] ^T ,e _p1,3 ＝[0.283,0.192,0.442,0.083] ^T ,e _p2,2 ＝[0.17,0.283,0.153,0.007,0.32,0.067] ^T ,e _p2,3 ＝[0.092,0.333,0.117,0.0167,0.283,0.158] ^T Meanwhile, likelihood confidence tables such as table 7 and table 8 can be constructed to describe class T _k1 、T _k2 And F _i The relationship between:

TABLE 7T _k1 Similar confidence table

TABLE 8T _k2 Similar confidence table

(9) When the online monitoring obtains a fault characteristic parameter vector X (t) = [ f ] at the moment t _1,i (t),f _2,i (t),f _3,i (t)]Thereafter, an importance weight w of the evidence is defined _k Description of evidence e _k Respectively solving the fault characteristic parameter vector and K according to the relative importance of the fault characteristic parameter vector and other evidences ₁ 、K ₂ A reference central vector

And normalizing the Euclidean distance to obtain the Dis _k1 And Dis _k2 CalculatingThe following were used:

definition of w _k1 ＝Dis _k1 ，w _k2 ＝Dis _k2 。

(11) Combining rule pairs e by Dempster _p1 ′、e _p2 ' fusion is performed, and the fused diagnosis results are:

Is a combined quality function>

Indicating that Dempster combination rules can act on two or more quality functions, and A, B, C are fault type modes;

the diagnostic evidence after fusion is:

e _p ＝[m(1),m(2),…,m(N)] (9)

in the formula, m (1), m (2) and m (N) respectively represent the fault type F subjected to normalization after fusion ₁ 、F ₂ 、F _N And (7) reliability.

(12) Using the diagnostic evidence e obtained in step (11) _p And diagnosing the fault of the elevator traction machine rotor: e.g. of the type _p F corresponding to the maximum confidence value _i Namely the fault mode of the real fault characteristic parameter vector X (t).

In order to deepen the importance weight w corresponding to the sample vector X (t) _k The understanding of (1) is that the fault characteristic parameter vector X (t) = [0.0421,0.1695, -0.0864 at the moment of online acquisition t =1]Substituting the obtained data into formula (6) in step (9) to obtain fault characteristic vectors X (t) and K at the time t =1 ₁ 、K ₂ The Euclidean distance between the central vectors is normalized to obtain the importance weight w _k1 ＝[0.2045,0.1139,0.2911,0.3905]，w _k2 ＝[0.2345,0.0884,0.4876,0.0527,0.0835,0.053]Obtaining the reference evidence e after activation through formula (7) in the step (10) _{p_1} ′＝[0.2471,0.2473,0.2409]，e _{p_2} ′＝[0.2225,0.1704,0.1409]. Normalized to obtain e _p1 ′＝[0.3362,0.3369,0.3269]，e _p2 ′＝[0.4168,0,3192,0.264]. E obtained in step (10) _p1 ' and e _p2 ' substitution of equation (8) into step (11) yields fused diagnostic evidence e _p ＝[0.4155,0.3230,0.2615]And diagnosing the fault of the elevator traction machine rotor: e.g. of a cylinder _p F corresponding to m (1) with maximum confidence coefficient value ₁ Namely the fault mode of the fault characteristic parameter vector X (t) which really occurs.

The embodiments of the present invention will be described in detail below with reference to the accompanying drawings:

the flow chart of the method of the invention is shown in figure 1, and the core part is as follows: calculating Pearson coefficients of the characteristic parameters to obtain the correlation of the characteristic parameters, and grouping the characteristic parameters according to the strength of the correlation; respectively calculating the similarity between sample data vectors according to the fault sample data of each group, and constructing a fault data complex network; acquiring a likelihood belief table and a reference center vector of each group by using a complex network community division method, and further acquiring corresponding reference evidence; and respectively activating the diagnostic evidence of each group aiming at the online acquired fault feature vector, carrying out evidence fusion by using a Dempster combination rule, and making a fault decision by using the fused evidence to obtain a fault type corresponding to the online fault feature data.

The steps of the method of the present invention will be described in detail below with reference to the preferred embodiment of the elevator machine rotor fault diagnosis system of fig. 2.

1. Example of setting up simulation experiment table of elevator traction device

As shown in the structure diagram of the elevator traction machine rotor fault diagnosis system in fig. 3, the vibration acceleration sensors are respectively installed at the drive end of the motor shell, the fan end and the motor base to collect vibration signals, the vibration signals collected by the three sensors are transmitted to the HG-8902 data collection box, processed by the signal conditioning circuit, and finally output to the monitoring computer through the a/D converter, and then the elevator traction machine rotor time domain vibration acceleration signals are obtained as fault characteristic signals by using HG-8902 data analysis software in the Labview environment.

2. Elevator traction machine rotor fault setting and fault characteristic parameter selection

According to the specific characteristics of the experiment table, 3 typical failure modes are respectively set on the experiment table: the tractor rotor is eccentric, the tractor rotor is unbalanced, and the tractor rotor part is not hard up. And collecting vibration signals as fault characteristic parameters by mounting the vibration signals at a motor shell driving end, a fan end and a motor base.

3. Correlation analysis, complex network community division and corresponding relation table construction

Get S ₁ ＝600,S ₂ ＝300,S ₃ =120, sample data in each fault state is acquired through step (2), δ =1020 sample data are sampled in total, and f can be calculated through step (3) and step (4) ₁ 、f ₂ 、f ₃ Has a Pearson coefficient of r (f) ₁ ，f ₂ )＝0.0202，r(f ₁ ，f ₃ )＝-0.0907，r(f ₂ ，f ₃ ) = -0.1092, see f ₂ And f ₃ Has strong correlation, can convert f ₂ 、f ₃ Composition feature data G _A ，f ₁ Is the characteristic data G _B Calculating to obtain Net through the step (5) ^A And Net ^B Through the step (6) willNet ^A Divided into 4 communities, community center C ₁₁ ＝[0.0162-0.115,0.0023],C ₁₂ ＝[-0.0256,0.0196,0.064],C ₁₃ ＝[0.0129,0.1764,-0.0044],C ₁₄ ＝[-0.0191,0.0358,-0.0324]. The samples in M are classified into T in Table 1 in step (6) in the same way ₁ 、T ₂ 、T ₃ 、T ₄ Will Net ^B Is divided into 6 communities with the community center of C ₂₁ ＝[-0.0272,-0.0407,0.002]，C ₂₂ ＝[-0.0695,0.0028,0.006]，C ₂₃ ＝[0.0542，0.0286,0.008]，C ₂₄ ＝[1.6053，0.0178,0.031],C ₂₅ ＝[-0.2823，0.0438,0.0023],C ₂₆ ＝[-0.6934,0.0225，0.0119]The samples in M are classified as T in Table 2 in step (6) ₁ 、T ₂ 、T ₃ 、T ₄ 、T ₅ 、T ₆ 。

As follows:

TABLE 9F _i And T _k1 Table of corresponding relationship between

TABLE 10F _i And T _k2 Table of corresponding relationship between

5. Constructing a likelihood belief table and obtaining diagnostic evidence

According to the corresponding relation table obtained in the step (7), when the fault state is F, the formula (4) in the step (8) can obtain _i Time is put in Table 5 ₁ 、T ₂ 、T ₃ 、T ₄ Likelihood function values of class are

T in Table 6 ₁ 、T ₂ 、T ₃ 、T ₄ 、T ₅ 、T ₆ The likelihood function value of a class is->

Obtaining corresponding F from the formula (4) in the step (8) ₁ Reference evidence of failure e _p1,1 ＝[0.331,0.167,0.361,0.141] ^T ，e _p2,1 ＝[0.223,0.31,0.257,0,0.2083,0.0017] ^T Similarly, F can be obtained ₂ 、F ₃ Corresponding fault reference evidence e _p1,2 ＝[0.397,0.113,0.383,0.107] ^T ，e _p1,3 ＝[0.0.283,0.192,0.442,0.083] ^T ，e _p2,2 ＝[0.17,0.283,0.153,0.007,0.32,0.067] ^T ，e _p2,3 ＝[0.092,0.333,0.117,0.0167,0.283,0.158] ^T Meanwhile, likelihood confidence tables such as table 7 and table 8 can be constructed to describe class T _k1 、T _k2 And F _i The relationship between:

TABLE 11T _k1 Similar confidence table

TABLE 12T _k2 Similar confidence table

Acquiring a fault characteristic parameter vector X (t) = [0.0421,0.1695 ] at the moment t =1 online,-0.0864]Substituting the above into formula (6) in step (8) to obtain fault feature vectors X (t) and K at time t =1 ₁ 、K ₂ The Euclidean distance between the central vectors is normalized to obtain the importance weight

w _k1 ＝[0.2045,0.1139,0.2911,0.3905]，

w _k2 ＝[0.2345,0.0884,0.4876,0.0527,0.0838,0.0530]，

Obtaining the activated reference evidence through the formula (7) in the step (9)

Normalized to obtain e _p1 ′＝[0.3362,0.3369,0.3269]，e _p2 ′＝[0.4168,0,3192,0.264]。

6. Fault diagnosis

E obtained in step (10) _p1 ' and e _p2 ' substitution of equation (8) into step (11) yields fused diagnostic evidence e _p ＝[0.4155,0.3230,0.2615]And diagnosing the fault of the elevator traction machine rotor: e.g. of a cylinder _p F corresponding to m (1) with maximum confidence value ₁ The fault mode of the fault characteristic parameter vector X (t) is consistent with the real fault mode set by the collected fault characteristic parameter vector, and the decision result is correct.

Claims

1. The elevator traction machine rotor fault diagnosis information fusion method based on the complex network is characterized by comprising the following steps:

(1) Setting a fault set theta = { F) of an elevator traction machine rotor ₁ ,…,F _i ,…,F _N |i＝1,2,…,N}，F _i The ith fault in the fault set theta is represented, and N is the number of fault modes contained in the elevator tractor rotor;

(2) Let f _1,i ，f _2,i And f _3,i To be able to reflect each fault F in the set of faults Θ _i The characteristic parameter is accelerationSignals are provided by acceleration sensors at a fan end, a motor base and a motor shell driving end respectively;

will f is _1,i ，f _2,i ，f _3,i And F _i Expressed as a set of samples M _i ＝{[f _1,i ,f _2,i ,f _3,i F _i ]|t＝1,2,3,…,S _i In which [ f) _1,i (t),f _2,i (t),f _3,i (t),F _i ]Is a sample vector, S _i Indicates that the fault is F _i Sample data in the State, and denoted F _i Sampling number in the state, taking S _i Not less than 100; respectively sampling sample data under each fault state and representing the sample data in a set form

The total number of delta samples can be obtained>

| M | represents the number in the set M;

(3) Will fail F _i F obtained under the state _1,i (t)、f _2,i (t) and f _3,i (t) is expressed as a sample set M _i ′＝{[f _1,i (t),f _2,i (t),f _3,i (t)]|t＝1,2,…,S _i And respectively sampling sample data in each fault state, and representing the sample data in a set form

Satisfy delta = | M | = | M _i ′|，|M _i ' | denotes the set M _i ' number of elements in;

(4) Carrying out correlation analysis on the sample fault characteristic parameters to obtain a Pearson coefficient; two characteristic parameters with larger Pearson coefficients are grouped into the same group and marked as G _A The characteristic parameters with less correlation are classified into another group, which is marked as G _B ；

(5) For two groups of characteristic data G obtained in the step (4) _A And G _B Respectively constructing data complex network Net ^A And Net ^B Described in similarity matrices A and B, a _i,j ，b _i,j Are elements in the matrices A and B, respectively, representing the sample x in each set of feature data _i And x _j Distance d between _i,j A function of (a);

Grouping M sample vectors into>

To obtain K ₁ Class correspondence sample Q _k1 ＝{[f _1,k1 (u _k1 ),f _2,k1 (u _k1 ),f _3,k1 (u _k1 ),F _k1 (u _k1 )]|u _k1 ＝1,2,…,U _k1 }，U _k1 Represents T _k1 Number of sample vectors in class, with Q _k1 ∈M，/>

F _k1 (u _k1 ) E.g. theta, and can be represented by K ₁ Obtaining K corresponding to the sample set M by taking the mean value of each sample-like vector ₁ A reference center vector, which may be denoted as C _k1 ＝[c _k1,1 ,c _k1,2 ,c _k1,3 ]Wherein K1=1,2, …, K ₁ ；

The same can put the sample vector in M into

In (b) to obtain K ₂ Class correspondence sample Q _k2 ＝{[f _2,k2 (u _k2 ),f _2,k2 (u _k2 ),f _3,k2 (u _k2 ),F _k2 (u _k2 )]|u _k2 ＝1,2,…,U _k2 }，U _k2 Represents T _k2 Number of sample vectors in class, with Q _k2 ∈M，/>

F _k2 (u _k2 ) E.g. theta, and can be represented by K ₂ Obtaining K corresponding to the sample set M by averaging the class sample vectors ₂ A reference center vector, which may be denoted as C _k2 ＝[c _k2,1 ,c _k2,2 ,c _k2,3 ]Wherein K2=1,2, …, K ₂ ；

(7) F obtained according to the step (2), the step (3), the step (5) and the step (6) _i And T _k1 、T _k2 The relational table shown in Table 1 and Table 2 is constructed to show F _i And T _k1 、F _i And T _k2 The corresponding relation between the two; n is a radical of _k1,i 、N _k2,i Respectively represents T _k1 、T _k2 The failure in the sample set corresponding to the class is F _i In combination with

And &>

And &>

Wherein N is more than or equal to 0 _k1,i 、N _k2,i ≤S _i ；

TABLE 1F _i And T _k1 Table of corresponding relationship between

TABLE 2F _i And T _k2 Table of corresponding relationship between

and is provided with

Defining the reference evidence of the ith type fault corresponding to the kth 1 and the kth 2 as follows:

obtaining two parts of fault diagnosis reference evidence as

e _p1 ＝[e _p1,1 ,e _p1,2 ,…,e _p1,N ]，e _p2 ＝[e _p2,1 ,e _p2,2 ,…,e _p2,N ]

Constructing likelihood confidence tables as shown in tables 3 and 4 to describe T _k1 、T _k2 And F _i The relationship between;

TABLE 3T _k1 Similar confidence table

TABLE 4T _k2 Similar confidence table

(9) When the online monitoring obtains a fault characteristic parameter vector X (t) = [ f ] at t moment _1,i (t),f _2,i (t),f _3,i (t)]Thereafter, an importance weight w of the evidence is defined _k Description of evidence e _k Respectively obtaining the fault characteristic parameter vector and K compared with the relative importance of other evidences ₁ 、K ₂ A reference center vector

And normalizing the Euclidean distance to obtain the Dis _k1 And Dis _k2 Definition of w _k1 ＝Dis _k1 ，w _k2 ＝Dis _k2 ；

(10) Using importance weights w of evidence _k To activate the reference evidence e _p To obtain e _{p_1} 、e _{p_2} A 1, e _{p_1} 、e _{p_2} Respectively carrying out normalization to obtain diagnosis evidence e _p1 ′、e _p2 ′；

(11) Combining rule pairs e by Dempster _p1 ′、e _p2 ' performing fusion to obtain fused diagnosis results as follows:

in the formula m ₁ 、m ₂ Let reference evidence m for two quality functions defined on Θ ₁ ＝e _p1 ′，m ₂ ＝e _p2 Definition m = m ₁ ⊕m ₂ For the combined quality function, the speed indicates that the Dempster combination rule can act on two or more quality functions, and A, B, C is a fault type mode;

the diagnostic evidence after fusion was:

e _p ＝[m(1),m(2),…,m(N)] (9)

in the formula, m (1), m (2) and m (N) respectively represent the fault type F subjected to normalization after fusion ₁ 、F ₂ 、F _N Reliability;

2. The elevator traction machine rotor fault diagnosis information fusion method based on the complex network as claimed in claim 1, characterized in that: in step (5), a _i,j ，b _i,j The definition is as follows:

a _i,j ＝exp(-15×d _i,j )，b _i,j ＝exp(-15×d _i,j )

3. The complex network-based elevator traction machine rotor fault diagnosis information fusion method according to claim 1, characterized in that: step (10) of e _{p_1} 、e _{p_2} Is calculated as follows:

e _{p_1} ＝w _k1 *e _p1 ＝[e _p1,1 ′,e _p1,2 ′,…,e _p1,N ′]，

e _{p_2} ＝w _k2 *e _p2 ＝[e _p2,1 ′,e _p2,2 ′,…,e _p2,N ′]。