CN107192565B - A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation - Google Patents

A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation Download PDF

Info

Publication number
CN107192565B
CN107192565B CN201710378336.5A CN201710378336A CN107192565B CN 107192565 B CN107192565 B CN 107192565B CN 201710378336 A CN201710378336 A CN 201710378336A CN 107192565 B CN107192565 B CN 107192565B
Authority
CN
China
Prior art keywords
data
door system
point
degradation
component degradation
Prior art date
Application number
CN201710378336.5A
Other languages
Chinese (zh)
Other versions
CN107192565A (en
Inventor
韩光威
吕建华
陆宁云
曹劲然
许志兴
史翔
张伟
朱文明
Original Assignee
南京康尼机电股份有限公司
南京航空航天大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 南京康尼机电股份有限公司, 南京航空航天大学 filed Critical 南京康尼机电股份有限公司
Priority to CN201710378336.5A priority Critical patent/CN107192565B/en
Publication of CN107192565A publication Critical patent/CN107192565A/en
Application granted granted Critical
Publication of CN107192565B publication Critical patent/CN107192565B/en

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00Testing of vehicles
    • G01M17/08Railway vehicles

Abstract

The invention discloses the synchronization detecting methods of a kind of subway vehicle door system exception operating condition and component degradation, carry out pretreatment operation including the data to railcar door system;Based on MeanShift algorithm, to pretreated subway vehicle door system data, the calculating of the density center point of normal data and degraded data is carried out respectively;It is adaptive to choose density center neighborhood of a point radius, the cluster modeling of complete paired data, and detect abnormal Outlier Data;Obtaining widget degradation information, and carry out maintenance guidance.The invention avoids abnormal points caused by unusual service condition to adversely affect caused by Hierarchical Clustering, possibility is provided to construct accurately and reliably system unit degradation model, pass through component degradation characteristic matching matching degree, maintenance reference is provided to maintenance personal, reduce system maintenance cost, it is readily appreciated that, facilitates implementation, have a good application prospect.

Description

A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation

Technical field

The present invention relates to the synchronization detecting methods of a kind of subway vehicle door system exception operating condition and component degradation, belong to track Vehicle Detection technical field.

Background technique

With the fast development of urban track traffic, important component of the subway as urban transportation, it is to people's work The influence make, lived is also increasing, and key components of the railcar door system as subway, its high failure rate is over the ground The safe operation of iron constitutes serious threat, so needing to detect the degenerate case of door system component, event occurs in door system System can be carried out before barrier effectively, have and targetedly safeguard, avoid the generation of the system failure.Simultaneously as subway The unusual service conditions such as interference, the sporadic failure of system and the data acquisition abnormity of outside environmental elements such as artificially squeezed when operation Generation, will lead to the generation for having Outlier Data when carrying out the modeling analysis based on data, these abnormal operating conditions can be done again Door system modeling is disturbed, causes model to occur uncertain, and then lead to the degeneration for being difficult to detect door system component.So if The unusual service condition and component degradation that detection railcar door system can be synchronized, are examined while detecting door system component degradation The operating condition of system exception is measured, and feeds back to door system, avoids outlier interference system component degradation caused by unusual service condition Detection can improve the accuracy of component degradation model and the validity of component degradation detection.

Currently, the detection technique in terms of being still not based on the component degradation of railcar door system, existing other component Deterioration detecting passes through ratio if patent is used for the event-driven fault diagnosis framework (CN102200487A) of automotive system Fault code when occurring compared with event of failure, the identification of Lai Jinhang failure, it needs the diagnostic code and mark of predefined system Standard, process is complicated and needs to be arranged more parameter.And a kind of lithium battery degeneration discrimination method of patent and degeneration alarm system (CN106199443A), for the performance degradation of lithium battery, the indexs such as the electric current, voltage, temperature of battery are measured, whether it is surpassed Threshold value is detected as degradation criteria, and for the unusual service condition and component degradation of railcar door system out, is that two differences are general It reads, moreover, this method is inaccurate, and this kind of large scale system with complex component of railcar door system can not be fitted With.

Summary of the invention

It in the prior art can not be to the unusual service condition of synchronous detection railcar door system the invention aims to overcome And the problem of component degradation.The synchronization detecting method of subway vehicle door system exception operating condition and component degradation of the invention, is being examined While measuring system unit degeneration, the detection to system exception operating condition (abnormal Outlier Data) is completed, unusual service condition is avoided Caused by abnormal point adversely affected caused by Hierarchical Clustering, to construct, accurately and reliably provide can for system unit degradation model Can, by component degradation characteristic matching matching degree, maintenance reference is provided to maintenance personal, reduces system maintenance cost, is easy reason Solution, facilitates implementation, has a good application prospect.

In order to achieve the above object, the technical scheme adopted by the invention is that:

A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation, it is characterised in that: including with Lower step,

Step (A) carries out pretreatment operation, including temporal signatures extraction process, frequency to the data of railcar door system The standardization of characteristic of field extraction process, data;

Step (B) is based on MeanShift algorithm, to pretreated subway vehicle door system data, carries out respectively normal The calculating of the density center of data and degraded data point;

Step (C), it is adaptive to choose density center neighborhood of a point radius, the cluster modeling of complete paired data, and detect Abnormal Outlier Data;

Data set is divided into normal data, degraded data and abnormal Outlier Data, acquisition unit according to step (C) by step (D) Part degradation information, and carry out maintenance guidance.

The synchronization detecting method of subway vehicle door system exception operating condition and component degradation above-mentioned, it is characterised in that: step (A), temporal signatures extraction process includes the following steps,

(A11), the temporal signatures value of door system data, including reflection central tendency information are extracted with statistical analysis technique First order statistic, be expressed as mean value;The second-order statistic for reflecting dispersion tendency information, is expressed as standard deviation;Reflect statistical The high-order statistic of cloth shape is expressed as the degree of bias, kurtosis;

(A21), stage extraction is carried out to the temporal signatures value for extracting door system data, a switch gate process is divided into Raising speed, high speed, reduction of speed, jogging section and back segment in place, point five stages statistical analysis electric currents, revolving speed, position and acceleration Maximum value, minimum value, mean value, variance, the degree of bias, kurtosis.

The synchronization detecting method of subway vehicle door system exception operating condition and component degradation above-mentioned, it is characterised in that: step (A), frequency domain character extraction process includes the following steps,

(A12), the frequency domain character for extracting door system electric current extracts the energy of multiple frequency domains using the method for wavelet transformation Feature;

(A22), by WAVELET PACKET DECOMPOSITION, the energy of each frequency band is isolated, as one of the frequency domain character of extraction, is come Reflect the performance degradation situation of door system.

The synchronization detecting method of subway vehicle door system exception operating condition and component degradation above-mentioned, it is characterised in that: step (A), the standardization of data carries out data normalization using the similar standardized method of Z-score, makes different variable variances Normalizing realizes nondimensionalization.

The synchronization detecting method of subway vehicle door system exception operating condition and component degradation above-mentioned, it is characterised in that: step (B), it is based on MeanShift algorithm, to pretreated subway vehicle door system data, carries out normal data and degeneration number respectively According to density center point calculating, include the following steps,

(B1), using MeanShift algorithm, seek the density center point of normal data and degraded data, MeanShift to The formal definition of amount, as shown in formula (1),

Wherein, the statistical nature vector x that i-th switch gated data obtainsiIt indicates, x indicates the statistical nature of datum mark Vector, ShIt is the higher-dimension ball region that a radius is h;(xi- x) it is sample point xiOffset relative to datum mark x;MSh(x) It is to fall into region ShIn t sample point relative to point x offset vector mean value.

(B2), introduce gaussian kernel function G (x), monotonously between reflected sample point and datum mark distance and sample point power The relationship of weight, at this point, vector M Sh(x) it turns to, as shown in formula (2),

Wherein, x indicates that the statistical nature vector of datum mark, h are the bandwidth of kernel function, meets | | MSh(x) | | small Mr. Yu holds Perhaps error condition is to can be obtained the stable state cluster centre point most converged to;

(B3), the algorithm described by (B1) and (B2), respectively obtains the density center point of normal data and degraded data C1、C2

The synchronization detecting method of subway vehicle door system exception operating condition and component degradation above-mentioned, it is characterised in that: step (C), density center neighborhood of a point radius, the cluster modeling of complete paired data are adaptively chosen, and detects abnormal Outlier Data, Include the following steps,

(C1), expand search radius R, to data set from the density center of normal data and degraded data point respectively In point classify, define the minimum range d of data sampleminFor data sample point other sample points into data set Minimum Eustachian distance, then degree of the peeling off OF of sample, as shown in formula (3),

(C2), corresponding classification is assigned to non-classified data sample, expands search radius R, until the degree of peeling off of sample OF is greater than threshold value 0.3, and the radius when search radius of every one kind is the last kind judging for completing unfiled point will finally count It is divided into two classes according to sample, does not assign the data of tag along sort as abnormal Outlier Data.

The synchronization detecting method of subway vehicle door system exception operating condition and component degradation above-mentioned, it is characterised in that: step (D), data set is divided by normal data, degraded data and abnormal Outlier Data according to step (C), obtaining widget degradation information, And maintenance guidance is carried out, include the following steps,

(D1), data set is divided by normal data, degraded data and abnormal Outlier Data according to step (C), by normal The density center of data and degraded data point C1、C2Carry out the analysis of the component degradation of door system;

(D2), by comparing the density center of normal data and degraded data point C1、C2, obtain component degradation model FEATURE, by the corresponding C of each characteristic value1、C2Difference sorted from large to small, take preceding 20 variation characteristic amounts, obtain known Component degradation causes corresponding feature to change, and obtaining variation tendency is to increase or reduce;

(D3), when carrying out component degradation test offline, according to obtaining the degradation model FEATURE of different component degradations, It is comprising 20 feature serial numbers and positive and negative model vector, when handling the real time data of door system, by real time data The algorithm process based on Meanshift is carried out with normal data, obtains the unknown vector f eature of real time data generation, from Search corresponding component degradation type in the model library established offline, component degradation characteristic matching degree, according to shown in formula (4),

Wherein, len (FEATURE) is the length of degradation model, the i.e. number of variation characteristic value, len (feature ∩ FEATURE) the identical number of model vector variation characteristic value in the model vector and off-line model library obtained for real time data;

(D4), the degeneration component that current door system is provided according to aspect of model matching degree shows maintenance personal, reduces dimension It repairs the time, realizes maintenance guidance.

The beneficial effects of the present invention are: subway vehicle door system exception operating condition of the invention detection synchronous with component degradation Method completes detection to system exception operating condition (abnormal Outlier Data) while detecting that system unit is degenerated, have with Lower feature,

(1) present invention does not depend on the foundation of physical model, the data acquired using the method for data-driven based on sensor To carry out the detection of system unit degeneration, it is readily appreciated that, facilitate implementation;

(2) present invention can be while detection system component degradation, and (peel off synchronous progress system exception operating condition number extremely According to) detection, there is synchronous real-time, avoid the adverse effect caused by Hierarchical Clustering of abnormal point caused by unusual service condition, Possibility is provided to construct accurately and reliably system unit degradation model;

(3) present invention is modeled by system degradation component on the door, is able to carry out the detection of component degradation, obtain be Component degradation information of uniting provides maintenance reference to maintenance personal, reduces system maintenance by component degradation characteristic matching matching degree Cost realizes maintenance guidance.

Detailed description of the invention

Fig. 1 is the flow chart of the synchronization detecting method of subway vehicle door system exception operating condition and component degradation of the invention;

Fig. 2 is the structure chart of offline carry out component degradation test of the invention;

Fig. 3 is the normal data of the specific embodiment of the invention and the result figure of V-type 8mm off-line modeling;

Fig. 4 is the normal data of the specific embodiment of the invention and the result figure of screw rod bending off-line modeling.

Specific embodiment

Below in conjunction with Figure of description, the present invention will be further described.Following embodiment is only used for clearly Illustrate technical solution of the present invention, and not intended to limit the protection scope of the present invention.

As shown in Figure 1, the synchronization detecting method of subway vehicle door system exception operating condition and component degradation of the invention, including Following steps,

Step (A) carries out pretreatment operation, including temporal signatures extraction process, frequency to the data of railcar door system The standardization of characteristic of field extraction process, data,

Temporal signatures extraction process, includes the following steps,

(A11), the temporal signatures value of door system data, including reflection central tendency information are extracted with statistical analysis technique First order statistic, be expressed as mean value;The second-order statistic for reflecting dispersion tendency information, is expressed as standard deviation;Reflect statistical The high-order statistic of cloth shape is expressed as the degree of bias, kurtosis;

(A21), stage extraction is carried out to the temporal signatures value for extracting door system data, a switch gate process is divided into Raising speed, high speed, reduction of speed, jogging section and back segment in place, point five stages statistical analysis electric currents, revolving speed, position and acceleration Maximum value, minimum value, mean value, variance, the degree of bias, kurtosis.

Frequency domain character extraction process, includes the following steps,

(A12), the frequency domain character for extracting door system electric current extracts the energy of multiple frequency domains using the method for wavelet transformation Feature;

(A22), by WAVELET PACKET DECOMPOSITION, the energy of each frequency band is isolated, as one of the frequency domain character of extraction, is come Reflect the performance degradation situation of door system;

For example, carry out 4 wavelet decompositions to the signal of electric current, in every layer of reservation low frequency signal, to high-frequency signal into Next layer of wavelet decomposition of row, 5 sub-band signal Di are obtained, and (i=1,2 ..., 5), the energy of sub-band signal Di is under Formula calculates:

Ei=∑ | Di|2

The standardization of data carries out data normalization using the similar standardized method of Z-score, makes different variables Variance normalizing realizes nondimensionalization.

Step (B) is based on MeanShift algorithm, to pretreated subway vehicle door system data, carries out respectively normal The calculating of the density center of data and degraded data point, includes the following steps,

(B1), using MeanShift algorithm, seek the density center point of normal data and degraded data, MeanShift to The formal definition of amount, as shown in formula (1),

Wherein, the statistical nature vector x that i-th switch gated data obtainsiIt indicates, x indicates the statistical nature of datum mark Vector, ShIt is the higher-dimension ball region that a radius is h;(xi- x) it is sample point xiOffset relative to datum mark x;MSh(x) It is to fall into region ShIn t sample point relative to point x offset vector mean value.

(B2), introduce gaussian kernel function G (x), monotonously between reflected sample point and datum mark distance and sample point power The relationship of weight, at this point, vector M Sh(x) turn to, as formula (2) shown in,

Wherein, x indicates that the statistical nature vector of datum mark, h are the bandwidth of kernel function, meets | | MSh(x) | | small Mr. Yu holds Perhaps error condition is to can be obtained the stable state cluster centre point most converged to;

(B3), the algorithm described by (B1) and (B2), respectively obtains the density center point of normal data and degraded data C1、C2

Step (C), it is adaptive to choose density center neighborhood of a point radius, the cluster modeling of complete paired data, and detect Abnormal Outlier Data, includes the following steps,

(C1), expand search radius R, to data set from the density center of normal data and degraded data point respectively In point classify, define the minimum range d of data sampleminFor data sample point other sample points into data set Minimum Eustachian distance, then degree of the peeling off OF of sample, as shown in formula (3),

(C2), corresponding classification is assigned to non-classified data sample, expands search radius R, until the degree of peeling off of sample OF is greater than threshold value 0.3, and the radius when search radius of every one kind is the last kind judging for completing unfiled point will finally count It is divided into two classes according to sample, does not assign the data of tag along sort as abnormal Outlier Data;

Data set is divided into normal data, degraded data and abnormal Outlier Data, acquisition unit according to step (C) by step (D) Part degradation information, and maintenance guidance is carried out, include the following steps,

(D1), data set is divided by normal data, degraded data and abnormal Outlier Data according to step (C), by normal The density center of data and degraded data point C1、C2Carry out the analysis of the component degradation of door system;

(D2), by comparing the density center of normal data and degraded data point C1、C2, obtain component degradation model FEATURE, by the corresponding C of each characteristic value1、C2Difference sorted from large to small, take preceding 20 variation characteristic amounts, obtain known Component degradation causes corresponding feature to change, and obtaining variation tendency is to increase or reduce;

(D3), when carrying out component degradation test offline, as shown in Fig. 2, according to the degeneration mould of different component degradations is obtained Type FEATURE, for comprising 20 feature serial numbers and positive and negative model vector, when handling the real time data of door system, Real time data and normal data are subjected to the algorithm process based on Meanshift, obtain the unknown vector of real time data generation Feature searches corresponding component degradation type, component degradation characteristic matching degree, according to public affairs from the model library established offline Shown in formula (4),

Wherein, len (FEATURE) is the length of degradation model, the i.e. number of variation characteristic value, len (feature ∩ FEATURE) the identical number of model vector variation characteristic value in the model vector and off-line model library obtained for real time data;

(D4), the degeneration component that current door system is provided according to aspect of model matching degree shows maintenance personal, reduces dimension It repairs the time, realizes maintenance guidance.

It, at this time will be but if component degradation characteristic matching degree less than 0.5, is determined as novel features degradation model The model vector feature that line obtains is added in the algorithm model knowledge base of system, while maintenance personal carries out door system Maintenance, provides component degradation information to improve knowledge base, the maintenance for the degradation model next time provides foundation.

Below according to the synchronization detecting method of subway vehicle door system exception operating condition and component degradation of the invention, one is introduced A specific embodiment, carries out experimental verification on a certain railcar door system, and one group of acquisition railcar door system is normal Data, the door leaf for adjusting car door later make the V-type size of car door reach 8mm, acquire the data of mono- group of data of V-type 8mm, synchronous inspection It surveys as a result, as shown in Figure 3, wherein preceding 16 data are positive regular data, and the 17th data are unusual service condition, and remainder data is to be The data of system door leaf V-type 8mm, degree of membership indicate that sample belongs to the degree of normal data, and degree of membership is in 1 expression sample and density Heart point is overlapped, it is observed that can accurately obtain the degeneration mould of door system carrying out when establishing of off-line system model Type, and the outlier for the system of detecting is synchronized, avoid interference of the outlier to degradation model accuracy.Pass through analysis system Model FEATURE, wherein door closing procedure total kilometres reduce, door opening process total kilometres increase meets system physical principle, side The accuracy of system model is demonstrated, if Fig. 4 provides the cluster result of one group of normal data and screw rod bending data,

1 component degradation matching degree result of table

Establish 4 component degradation models of system, respectively V-type 8mm, screw rod bending, intermediate supports offline with algorithm It loosens and nut is damaged, when being tested using corresponding 4 groups of test datas, test result is as shown in table 1, corresponding to survey The characteristic matching degree of data is tried 80% or more, and the characteristic matching degree of erroneous matching does not arrange in table 1 all less than 10% Out.Thus, it is possible to obtain the synchronization detecting method energy of subway vehicle door system exception operating condition and component degradation proposed by the present invention Enough accurately to provide component degradation information, the personnel that can maintain easily timely and accurately carry out system maintenance, shorten maintenance time, Maintenance cost is reduced, while system being avoided further to deteriorate the generation for leading to failure.

In conclusion the synchronization detecting method of subway vehicle door system exception operating condition and component degradation of the invention, is being examined While measuring system unit degeneration, the detection to system exception operating condition (abnormal Outlier Data) is completed, is had the characteristics that,

(1) present invention does not depend on the foundation of physical model, the data acquired using the method for data-driven based on sensor To carry out the detection of system unit degeneration, it is readily appreciated that, facilitate implementation;

(2) present invention can be while detection system component degradation, and (peel off synchronous progress system exception operating condition number extremely According to) detection, there is synchronous real-time, avoid the adverse effect caused by Hierarchical Clustering of abnormal point caused by unusual service condition, Possibility is provided to construct accurately and reliably system unit degradation model;

(3) present invention is modeled by system degradation component on the door, is able to carry out the detection of component degradation, obtain be Component degradation information of uniting provides maintenance reference to maintenance personal, reduces system maintenance by component degradation characteristic matching matching degree Cost realizes maintenance guidance.

Basic principles and main features and advantage of the invention have been shown and described above.The technical staff of the industry should Understand, the present invention is not limited to the above embodiments, and the above embodiments and description only describe originals of the invention Reason, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes and improvements It all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by appended claims and its equivalent circle It is fixed.

Claims (7)

1. a kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation, it is characterised in that: including following Step,
Step (A) carries out pretreatment operation, including temporal signatures extraction process, frequency domain spy to the data of railcar door system Levy the standardization of extraction process, data;
Step (B) carries out normal data to pretreated subway vehicle door system data based on MeanShift algorithm respectively With the calculating of the density center point of degraded data;
Step (C), it is adaptive to choose density center neighborhood of a point radius, the cluster modeling of complete paired data, and detect exception Outlier Data;
Data set is divided into normal data, degraded data and abnormal Outlier Data, obtaining widget according to step (C) and moved back by step (D) Change information, and carries out maintenance guidance.
2. the synchronization detecting method of subway vehicle door system exception operating condition and component degradation according to claim 1, special Sign is: step (A), temporal signatures extraction process include the following steps,
(A11), the temporal signatures value that door system data are extracted with statistical analysis technique, one including reflecting central tendency information Rank statistic, is expressed as mean value;The second-order statistic for reflecting dispersion tendency information, is expressed as standard deviation;Reflect statistical distribution shape The high-order statistic of shape is expressed as the degree of bias, kurtosis;
(A21), stage extraction is carried out to the temporal signatures value for extracting door system data, a switch gate process is divided into liter Speed, high speed, reduction of speed, jogging section and back segment in place, point five stages statistical analysis electric currents, revolving speed, position and acceleration are most Big value, minimum value, mean value, variance, the degree of bias, kurtosis.
3. the synchronization detecting method of subway vehicle door system exception operating condition and component degradation according to claim 1, special Sign is: step (A), frequency domain character extraction process include the following steps,
(A12), the frequency domain character for extracting door system electric current extracts the energy feature of multiple frequency domains using the method for wavelet transformation;
(A22), by WAVELET PACKET DECOMPOSITION, the energy of each frequency band is isolated, as one of the frequency domain character of extraction, Lai Fanying The performance degradation situation of door system.
4. the synchronization detecting method of subway vehicle door system exception operating condition and component degradation according to claim 1, special Sign is: step (A), the standardization of data, carries out data normalization using the standardized method of Z-score, makes difference Variable variance normalizing realizes nondimensionalization.
5. the synchronization detecting method of subway vehicle door system exception operating condition and component degradation according to claim 1, special Sign is: step (B), is based on MeanShift algorithm, to pretreated subway vehicle door system data, carries out respectively normal The calculating of the density center of data and degraded data point, includes the following steps,
(B1), using MeanShift algorithm, the density center point of normal data and degraded data is sought, MeanShift vector Formal definition, as shown in formula (1),
Wherein, the statistical nature vector x that i-th switch gated data obtainsiIt indicating, x indicates the statistical nature vector of datum mark, ShIt is the higher-dimension ball region that a radius is h;(xi- x) it is sample point xiOffset relative to datum mark x;MShIt (x) is to fall into Region ShIn t sample point relative to point x offset vector mean value;
(B2), gaussian kernel function G (x) is introduced, monotonously distance and the weight of sample point between reflected sample point and datum mark Relationship, at this point, vector M Sh(x) it turns to, as shown in formula (2),
Wherein, x indicates that the statistical nature vector of datum mark, h are the bandwidth of kernel function, meets | | MSh(x) | small Mr. Yu's allowable error It can be obtained the stable state cluster centre point most converged to when condition;
(B3), the algorithm described by (B1) and (B2), respectively obtains the density center point C of normal data and degraded data1、C2
6. the synchronization detecting method of subway vehicle door system exception operating condition and component degradation according to claim 1, special Sign is: step (C), adaptive to choose density center neighborhood of a point radius, the cluster modeling of complete paired data, and detects different Normal Outlier Data, includes the following steps,
(C1), expand search radius R from the density center of normal data and degraded data point respectively, data are concentrated Point is classified, and the minimum range d of data sample is definedminFor the minimum of data sample point other sample points into data set Euclidean distance, then degree of the peeling off OF of sample, as shown in formula (3),
(C2), corresponding classification is assigned to non-classified data sample, expands search radius R, until degree of the peeling off OF of sample is big In threshold value 0.3, the search radius of every one kind completes the radius when kind judging of unfiled point for the last time, finally by data sample Originally it is divided into two classes, does not assign the data of tag along sort as abnormal Outlier Data.
7. the synchronization detecting method of subway vehicle door system exception operating condition and component degradation according to claim 5, special Sign is: step (D), and data set is divided into normal data, degraded data and abnormal Outlier Data, acquisition unit according to step (C) Part degradation information, and maintenance guidance is carried out, include the following steps,
(D1), data set is divided by normal data, degraded data and abnormal Outlier Data according to step (C), passes through normal data With the density center point C of degraded data1、C2Carry out the analysis of the component degradation of door system;
(D2), by comparing the density center of normal data and degraded data point C1、C2, component degradation model FEATURE is obtained, By the corresponding C of each characteristic value1、C2Difference sorted from large to small, take preceding 20 variation characteristic amounts, obtain known elements degeneration Corresponding feature is caused to change, and obtaining variation tendency is to increase or reduce;
(D3), when carrying out component degradation test offline, according to the degradation model FEATURE of different component degradations is obtained, it is Comprising 20 feature serial numbers and positive and negative model vector, when handling the real time data of door system, by real time data and just Regular data carries out the algorithm process based on Meanshift, the unknown vector f eature of real time data generation is obtained, from offline Search corresponding component degradation type in the model library of foundation, component degradation characteristic matching degree, according to shown in formula (4),
Wherein, len (FEATURE) is the length of degradation model, the i.e. number of variation characteristic value, len (feature ∩ FEATURE) the identical number of model vector variation characteristic value in the model vector and off-line model library obtained for real time data;
(D4), the degeneration component that current door system is provided according to aspect of model matching degree shows maintenance personal, when reducing maintenance Between, realize maintenance guidance.
CN201710378336.5A 2017-05-25 2017-05-25 A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation CN107192565B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710378336.5A CN107192565B (en) 2017-05-25 2017-05-25 A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710378336.5A CN107192565B (en) 2017-05-25 2017-05-25 A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation

Publications (2)

Publication Number Publication Date
CN107192565A CN107192565A (en) 2017-09-22
CN107192565B true CN107192565B (en) 2019-05-28

Family

ID=59875532

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710378336.5A CN107192565B (en) 2017-05-25 2017-05-25 A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation

Country Status (1)

Country Link
CN (1) CN107192565B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108827632A (en) * 2018-03-30 2018-11-16 刘文飞 A kind of determination method of communications equipment room equipment health status
CN109374318A (en) * 2018-09-27 2019-02-22 南京康尼机电股份有限公司 The more door system method for detecting abnormality of rail vehicle and system based on DPC

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102005034A (en) * 2010-12-01 2011-04-06 南京大学 Remote sensing image segmentation method based on region clustering
CN102187539A (en) * 2008-09-08 2011-09-14 Abb研究有限公司 Apparatus and method for adaptive fault detection in mv distribution circuits
CN104697804A (en) * 2015-03-24 2015-06-10 清华大学 Method and system for detecting and separating intermittent faults of train active suspension system
CN105046270A (en) * 2015-06-19 2015-11-11 上海卓悠网络科技有限公司 Application classification model constructing method and system and application classification method and system
CN105241680A (en) * 2015-08-26 2016-01-13 电子科技大学 Health state assessment method for rotary machine based on probability density function

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101510230A (en) * 2009-03-11 2009-08-19 同济大学 Vehicle road load emulation method
KR20140099986A (en) * 2013-02-04 2014-08-14 동서대학교산학협력단 Colorization-based color image coding method by meanshift segmentation algorithm
CN106406295B (en) * 2016-12-02 2019-02-26 南京康尼机电股份有限公司 Rail traffic vehicles door system fault diagnosis and method for early warning based on multi-state

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102187539A (en) * 2008-09-08 2011-09-14 Abb研究有限公司 Apparatus and method for adaptive fault detection in mv distribution circuits
CN102005034A (en) * 2010-12-01 2011-04-06 南京大学 Remote sensing image segmentation method based on region clustering
CN104697804A (en) * 2015-03-24 2015-06-10 清华大学 Method and system for detecting and separating intermittent faults of train active suspension system
CN105046270A (en) * 2015-06-19 2015-11-11 上海卓悠网络科技有限公司 Application classification model constructing method and system and application classification method and system
CN105241680A (en) * 2015-08-26 2016-01-13 电子科技大学 Health state assessment method for rotary machine based on probability density function

Also Published As

Publication number Publication date
CN107192565A (en) 2017-09-22

Similar Documents

Publication Publication Date Title
Liu et al. Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings
US20190087638A1 (en) Analyzing digital holographic microscopy data for hematology applications
Wei et al. A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection
Cerrada et al. A review on data-driven fault severity assessment in rolling bearings
Ghate et al. Cascade neural-network-based fault classifier for three-phase induction motor
CN103955750B (en) Rolling bearing remaining life prediction method based on feature fusion and particle filtering
CN102854191B (en) Real-time visual detection and identification method for high speed rail surface defect
CN103235933B (en) A kind of vehicle abnormality behavioral value method based on HMM
Soualhi et al. Prognosis of bearing failures using hidden Markov models and the adaptive neuro-fuzzy inference system
Yiakopoulos et al. Rolling element bearing fault detection in industrial environments based on a K-means clustering approach
US8630962B2 (en) Error detection method and its system for early detection of errors in a planar or facilities
Cui et al. Quantitative fault analysis of roller bearings based on a novel matching pursuit method with a new step-impulse dictionary
CN102944416B (en) Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades
CN103197218B (en) A kind of high-voltage cable insulation defect partial discharge electrification detection diagnostic method
Qin et al. The optimized deep belief networks with improved logistic Sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines
Timusk et al. Fault detection using transient machine signals
US10281504B2 (en) Method and apparatus for analyzing waveform signals of a power system
Yang et al. Vibration condition monitoring system for wind turbine bearings based on noise suppression with multi-point data fusion
Li et al. The entropy algorithm and its variants in the fault diagnosis of rotating machinery: A review
Feng et al. Design and implementation of a self-validating pressure sensor
Zhou et al. Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model
CN103473540B (en) The modeling of intelligent transportation system track of vehicle increment type and online method for detecting abnormality
CN103076547A (en) Method for identifying GIS (Gas Insulated Switchgear) local discharge fault type mode based on support vector machines
Kwan et al. A novel approach to fault diagnostics and prognostics
CN103728551B (en) A kind of analog-circuit fault diagnosis method based on cascade integrated classifier

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant