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 PDFInfo
- 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
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000015556 catabolic process Effects 0.000 title claims abstract description 93
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012423 maintenance Methods 0.000 claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims abstract description 23
- 230000003044 adaptive effect Effects 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 18
- 230000007850 degeneration Effects 0.000 claims description 14
- 230000002123 temporal effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000002411 adverse Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 18
- 230000001360 synchronised effect Effects 0.000 description 9
- 238000005452 bending Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/08—Railway vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Train Traffic Observation, Control, And Security (AREA)
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
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.
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 Active 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 (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197647B (en) * | 2017-12-28 | 2021-08-31 | 中南大学 | Rapid clustering method for automobile starter endurance test data |
| CN108827632A (en) * | 2018-03-30 | 2018-11-16 | 刘文飞 | A kind of determination method of communications equipment room equipment health status |
| CN108629007B (en) * | 2018-05-04 | 2022-08-09 | 上饶市普适科技有限公司 | Method for eliminating abnormal values of historical enrollment data |
| 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 |
| CN109580260A (en) * | 2018-11-27 | 2019-04-05 | 南京康尼机电股份有限公司 | A kind of inferior health diagnostic method of track vehicle door system |
| CN110398382A (en) * | 2019-06-28 | 2019-11-01 | 南京康尼机电股份有限公司 | A kind of underground automobile door system performance decline detection method based on DPC |
| CN110717379A (en) * | 2019-08-28 | 2020-01-21 | 南京康尼机电股份有限公司 | Health assessment method for subway car door key components based on feature fusion |
| CN111999580B (en) * | 2020-08-14 | 2023-12-01 | 佳都科技集团股份有限公司 | Method and device for detecting subway platform gate, computer equipment and storage medium |
| CN112198472B (en) * | 2020-09-29 | 2023-11-07 | 国网上海市电力公司 | Online remote verification method and system for partial discharge intelligent sensor |
Citations (5)
| 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)
| 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 |
-
2017
- 2017-05-25 CN CN201710378336.5A patent/CN107192565B/en active Active
Patent Citations (5)
| 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 |
|---|---|---|
| CN107192565B (en) | A kind of synchronization detecting method of subway vehicle door system exception operating condition and component degradation | |
| CN111314331B (en) | Unknown network attack detection method based on conditional variation self-encoder | |
| CN113702895B (en) | Online quantitative evaluation method for error state of voltage transformer | |
| CN107153841B (en) | Sub-health prediction method for urban rail transit vehicle door system | |
| CN110376522A (en) | A kind of Method of Motor Fault Diagnosis of the deep learning network of data fusion | |
| CN110991657A (en) | Abnormal sample detection method based on machine learning | |
| CN110619479B (en) | Fault judgment model modeling method and fault judgment method for photovoltaic module | |
| US11867763B2 (en) | Method for monitoring circuit breaker and apparatus and internet of things using the same | |
| CN106959397B (en) | A kind of design method of the small fault diagnostic system for high-speed rail inverter | |
| Li et al. | Intelligent fault diagnosis of aeroengine sensors using improved pattern gradient spectrum entropy | |
| CN109726770A (en) | A kind of analog circuit fault testing and diagnosing method | |
| Guo et al. | An equipment multiple failure causes intelligent identification method based on integrated strategy for subway sliding plug door system under variable working condition | |
| CN109580260A (en) | A kind of inferior health diagnostic method of track vehicle door system | |
| CN115496108A (en) | Fault monitoring method and system based on manifold learning and big data analysis | |
| CN111797944A (en) | Vehicle door abnormity diagnosis method and device | |
| Yan et al. | Bearing performance degradation assessment based on the continuous-scale mathematical morphological particle and feature fusion | |
| Hasegawa et al. | Adaptive training of vibration-based anomaly detector for wind turbine condition monitoring | |
| CN109145764B (en) | Method and device for identifying unaligned sections of multiple groups of detection waveforms of comprehensive detection vehicle | |
| Moore et al. | Dataset balancing can hurt model performance | |
| CN116956197B (en) | Deep learning-based energy facility fault prediction method and device and electronic equipment | |
| Sun et al. | Air leakage detection of pneumatic train door subsystems using open set recognition | |
| CN110956112B (en) | Novel high-reliability slewing bearing service life assessment method | |
| Dalian et al. | Dual-rotor misalignment fault quantitative identification based on DBN and improved DS evidence theory | |
| US20230059561A1 (en) | Identification of arcing hazards in power distribution systems | |
| Qian et al. | Large-scale kpi anomaly detection based on ensemble learning and clustering |
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 |