CN103345207A - Mining analyzing and fault diagnosis system of rail transit monitoring data - Google Patents
Mining analyzing and fault diagnosis system of rail transit monitoring data Download PDFInfo
- Publication number
- CN103345207A CN103345207A CN2013102113565A CN201310211356A CN103345207A CN 103345207 A CN103345207 A CN 103345207A CN 2013102113565 A CN2013102113565 A CN 2013102113565A CN 201310211356 A CN201310211356 A CN 201310211356A CN 103345207 A CN103345207 A CN 103345207A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- signal monitoring
- railway signal
- fault diagnosis
- 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.)
- Granted
Links
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a mining analyzing and fault diagnosis system of rail transit monitoring data, and relates to the technical field of railway signals. The system comprises a signal monitoring system data processing unit, a data analyzing unit, a knowledge base unit and a fault diagnosis unit, wherein the signal monitoring system data processing unit is used for acquiring history railway signal monitoring data and real-time railway signal monitoring data from an on-site centralized signaling monitoring (CSM) device in each electric service workshop or work area. The data analyzing unit is used for analyzing the history railway signal monitoring data acquired by the signal monitoring system data processing unit, and generating fault diagnosis rules. The knowledge base unit is used for storing judging standards, and storing the fault diagnosis rules of the data analyzing unit, wherein the judging standards are formulated according to the work principle of each railway signal device and national and industry standards and specifications in the railway signal field and are used for fault diagnosis. The fault diagnosis unit is used for generating fault diagnosis results according to the fault diagnosis rules and the judging standards as for the real-time railway signal monitoring data acquired by the signal monitoring system data processing unit.
Description
Technical field
The present invention relates to the railway signal technology field, particularly a kind of mining analysis of track traffic monitor data and fault diagnosis system.
Background technology
In order to improve the modernization maintenance level of China railways signal system equipment, since the nineties, successively independent development continuous centralized signal supervision CSM systems during upgrading such as TJWX-I type and TJWX-2000 type.Computer monitoring system has all been adopted at present most of station, realized the real-time monitoring to the signaling at stations equipment state, and by the main running status of monitoring with tracer signal equipment, grasping the current state of equipment and carry out crash analysis for telecommunication and signaling branch provides basic foundation, has brought into play vital role.And, to the urban track traffic signalling arrangement, concentrate monitoring CSM system also to be widely deployed in city rail cluster/rolling stock section etc. and locate, use for city rail O﹠M.
But, diagnosis aspect at a lot of complex apparatus faults and driving accident reason, this system is helpless, still need rely on the artificial experience analysis and judgement at present, only when significant problem occurring, just find fault under a lot of situations, big, malfunction monitoring and the low inferior technical matters of diagnosis efficiency of workload increased the danger of driving a vehicle when not only having caused artificial diagnosis railway signal system fault.
Summary of the invention
Big, the inefficiency of workload, risk high-technology problem when solving in the prior art artificial diagnosis railway signal system fault the invention provides a kind of mining analysis and fault diagnosis system of track traffic monitor data.
A kind of mining analysis of track traffic monitor data and fault diagnosis system comprise: signal monitoring system data processing unit, data analysis unit, knowledge base unit, failure diagnosis unit and man-machine interface unit; Wherein,
Described signal monitoring system data processing unit is used for gathering historical railway signal Monitoring Data and real-time railway signal Monitoring Data from the centralized signal supervision CSM equipment at each electric affair workshop or scene, work area;
Described data analysis unit is used for the historical railway signal Monitoring Data of signal monitoring system data processing unit collection is analyzed, and generates Failure Diagnostic Code, and sends to the knowledge base unit;
Described knowledge base unit is used for the criterion that storage is used according to the fault diagnosis of the country in the principle of work of each railway signals equipment, railway signal field and industry standard, norm-setting, and the Failure Diagnostic Code of storage data analysis unit;
Described failure diagnosis unit is used for the real-time railway signal Monitoring Data at the collection of signal monitoring system data processing unit, generates fault diagnosis result according to Failure Diagnostic Code and criterion;
Described man-machine interface unit is used for fault diagnosis result is showed the user.
Wherein, described data analysis unit comprises:
Data preparation module is used for selecting railway signal to analyze data from the historical railway signal Monitoring Data that signal monitoring system data processing unit is gathered;
Data preprocessing module, the railway signal that is used for selecting is analyzed data and is handled, and generates the data that are suitable for excavating Failure Diagnostic Code;
Data-mining module is used for adopting data mining algorithm that the data that are fit to the excavation Failure Diagnostic Code are analyzed, and extracts data characteristics;
The pattern generation module is used for generating Failure Diagnostic Code according to the data characteristics of extracting.
Wherein, described failure diagnosis unit comprises:
Characteristic extracting module is used for analyzing at the real-time railway signal Monitoring Data of signal monitoring system data processing unit collection, and extracts data characteristics;
The diagnosis determination module is used for according to Failure Diagnostic Code and criterion the data characteristics of characteristic extracting module extraction being mated, and draws fault diagnosis result.
In the preferred version, this system also comprises the data warehouse unit;
Data analysis unit, the historical railway signal Monitoring Data that also is used for gathering sends to the data warehouse unit; Correspondingly, this data warehouse unit is used for the described historical railway signal Monitoring Data of storage.
The railway signal Monitoring Data that will have now on the centralized signal supervision CSM of the railway system equipment by employing in the system that present embodiment provides gathers out, analyze Failure Diagnostic Code according to the historical railway signal Monitoring Data of gathering, in conjunction with existing railway territory standard, diagnose at real-time railway signal Monitoring Data, determine the whether technological means of fault of railway signal system, solved in the prior art, workload is big when manually diagnosing the railway signal system fault, inefficiency, risk high-technology problem, and then obtain automatic diagnosis railway signal system fault, increase work efficiency, reduce artificial workload, find system problem as early as possible, reduce the technique effect of railway operation risk.
Description of drawings
Accompanying drawing is used to provide further understanding of the present invention, and constitutes the part of instructions, is used from explanation the present invention with embodiments of the invention one, is not construed as limiting the invention.In the accompanying drawings:
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
The mining analysis of a kind of track traffic monitor data that Fig. 1 provides for the embodiment of the invention 1 and the structural representation of fault diagnosis system;
The mining analysis of the another kind of track traffic monitor data that Fig. 2 provides for the embodiment of the invention 1 and the structural representation of fault diagnosis system.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.And, below each embodiment be possibility of the present invention, embodiment puts in order and the numbering of embodiment and the sequence independence that it is preferably carried out.
Embodiment 1
Present embodiment provides a kind of mining analysis and fault diagnosis system of track traffic monitor data, as shown in Figure 1, this system comprises: this signal monitoring system data processing unit of signal monitoring system data processing unit 11(can provide at existing C SM system, also can provide at any railway signal monitoring system of later appearance), data analysis unit 12, knowledge base unit 13, failure diagnosis unit 14 and man-machine interface unit 15; Wherein,
Signal monitoring system data processing unit 11, be used for from the centralized signal supervision CSM equipment at each electric affair workshop or scene, work area, gathering historical railway signal Monitoring Data and real-time railway signal Monitoring Data, and these historical railway signal Monitoring Data that collect and real-time railway signal Monitoring Data are reported to data analysis unit 12.
In the present embodiment, the content of historical railway signal Monitoring Data and real-time railway signal Monitoring Data is the same, includes interlocking, obturation, row control, hump, TDCS(dispatch control management system)/CTC(dispatching concentration control system) and the status data of signalling arrangement such as power supply panel.Different is: historical railway signal Monitoring Data is the railway signal Monitoring Data in the past that signalling arrangement is preserved, comprised the status data under the known device state status in these data, for example determined that the signalling arrangement state is fault, and the status data of this signalling arrangement under this malfunction; In real time the railway signal Monitoring Data is that signalling arrangement equipment state at that time is the status data under the condition of unknown, and for example: whether the status data that signalling arrangement has just produced, also unknown this signalling arrangement fault or normal etc.
Data analysis unit 12 is used for the historical railway signal Monitoring Data that signal monitoring system data processing unit 11 is gathered is analyzed, and generates Failure Diagnostic Code, and Failure Diagnostic Code is sent to knowledge base unit 13.
Knowledge base unit 13 is used for the criterion that storage is used according to the fault diagnosis of the country in the principle of work of each railway signals equipment, railway signal field and industry standard, norm-setting, and the Failure Diagnostic Code of storage data analysis unit 12;
Failure diagnosis unit 14, be used for the real-time railway signal Monitoring Data at 11 collections of signal monitoring system data processing unit, generate fault diagnosis result according to the Failure Diagnostic Code in the knowledge base unit and criterion, this fault diagnosis result can be thought a kind of fault diagnosis result of real time data;
Man-machine interface unit 15 is used for fault diagnosis result is showed the user.
The collaborative assembly with O﹠M information system (patent No. is 201310190664.4 application documents) as the track traffic synthetic monitoring and dispatching of this system that present embodiment provides, device level, system-level and application layer be can run on, signal data analysis and fault diagnosis at different levels finished.Can utilize the device level data of collection on the device level, carry out real-time analysis and the fault diagnosis of device signal.System-level going up according to the relation between the equipment, the package signal data carries out fault diagnosis.Application layer obtains device level and system-level data from data warehouse, carry out data mining analysis and fault diagnosis, and carries out the issue of diagnostic result.
Further in the preferred version, the system that present embodiment provides can also comprise: data warehouse unit 16.
Data analysis unit 12, the historical railway signal Monitoring Data that also is used for gathering sends to data warehouse unit 16; Data warehouse unit 16 is used for the described historical railway signal Monitoring Data of storage.
Data analysis unit 12 also is used for real-time railway signal Monitoring Data is sent to data warehouse unit 16; Correspondingly, data warehouse unit 16, the real-time railway signal Monitoring Data that also is used for data analysis unit 12 transmissions are come is transparent to failure diagnosis unit 14, and data warehouse unit 16 also will back up this real-time railway signal Monitoring Data and then storage simultaneously.
Failure diagnosis unit 14 also is used at data warehouse unit 16 stored historical railway signal Monitoring Data, generates fault diagnosis result according to Failure Diagnostic Code and criterion.This fault diagnosis result also can be thought a kind of fault diagnosis result of historical data.
Data warehouse unit 16 effect in the present embodiment is mainly used in that each electric affair workshop or the Monitoring Data of preserving separately break are concentrated on the upper strata and preserves, to be used for fault diagnosis or follow-up otherwise application.
Following mask body is introduced the function of above-mentioned each unit in the system that present embodiment provides.
1, signal monitoring system data processing unit 11, the concrete mode that is used for passing through switch acquisition device, intelligence sensor and loop line from the centralized signal supervision CSM equipment at each electric affair workshop or scene, work area is obtained switching value and analog data from relay, the module of needs monitoring; Those there are equipment or the system of unified interface, as automatic block system, intelligent power supply panel, computer interlock etc., by bus mode, directly gather the railway signal Monitoring Data of stipulating Ministry of Railways's interface specification from unified interface.
2, data analysis unit comprises 12:
Data preparation module 121 is used for selecting suitable railway signal to analyze data from the historical railway signal Monitoring Data that signal monitoring system data processing unit is gathered.
Above-mentioned suitable railway signal analysis data refer to the status data under the known device state status.At that time equipment state in the historical railway signal Monitoring Data can be gone forward side by side the data of line item as the status data under the known device state status through artificial judgment.
Data preprocessing module 122 is used for that the railway signal of selecting is analyzed data and handles, and generates the data that are suitable for excavating Failure Diagnostic Code.
Data preprocessing module 122 is mainly used in that railway signal is analyzed data and carries out pre-service, and pretreated analysis data are the data that are suitable for excavating the fault diagnosis fault.This pre-service mainly comprises: data scrubbing and integrated, remove noise data, non-data available, original railway signal is analyzed data normalization, standardization and a plurality of data sources are combined, be applicable type with data type conversion again, define new data attribute, reduce data dimension and size.
Data scrubbing (Data Cleaning) is by filling in the vacancy value, the smooth noise data, and identification, deletion isolated point, and solve inconsistent problem and realize " cleaning " data.Solve because dirty data can make mining process fall into chaos, cause insecure output.
Data integration (Data Integration) is to consider that the data that often need when excavating Failure Diagnostic Code to come from a plurality of data sources merge storage, also may need the form that data-switching is become to be suitable for excavating sometimes.
Remove noise data, non-data available, original railway signal is analyzed data normalization, standardization and a plurality of data sources are combined and refer to data reduction (Data Reduction).For example with large data collection compression expression, it will be more effective making the data set excavation after reduction, and produce the excavation result of identical (or almost identical).Mainly comprise eigenwert reduction, feature reduction and sample reduction.
Data-mining module 123 is used for adopting data mining algorithm that the data that are fit to the excavation Failure Diagnostic Code are analyzed, and extracts data characteristics.
Data mining algorithm in the present embodiment comprises: to data classify, method such as isolated point, association rule mining, time series analysis, rough set attribute reduction algorithm.
1) sorting technique: fault detect is to pass through the analytic signal data, determine whether equipment work is normal, namely data to be divided into normal and unusual two classes, so fault diagnosis can be regarded as classification problem, carry out fault detect with the sorting technique in the data mining.
2) isolated point analysis: when the equipment operation irregularity, signal data when corresponding signal data and operate as normal is inconsistent, be that the relative normal data of fault data is isolated point, so can adopt the isolated point analytical approach in the data mining to carry out fault detect.
3) association rule mining: the correlation rule technology lays particular emphasis on the not contact between the same area in the specified data, finds out the dependence between a plurality of territories of satisfying given support and confidence threshold value.Correlation rule is found in association analysis, and these rules are showed the condition that " attribute-value " occurs together in given data centralization continually.By association analysis, the potential incidence relation between the incidence relation between the possible discovering device fault mode and the discovering device different operating parameter.
4) time series analysis: the monitoring of equipment data are time dependent time series datas, adopt the data digging method of time series analysis, comprise trend analysis, similarity searching, excavate with sequence pattern and the cyclic pattern of time relevant data, and dynamic time warping and temporal signatures extract.
The data-mining module effect is selected from large quantities of data with the relevant data of a certain fault by data mining algorithm simply exactly, and these data are extracted as data characteristics.Therefore, the data characteristics that data-mining module extracts can characterize fault exactly, a part of data that perhaps are associated with fault or by the data representation after the conversion.Concrete mining process is with reference to routine down.
For example: utilize the rough set attribute reduction algorithm to carry out fault signature and extract
Algorithm is as follows:
Input: decision table S=(U, C ∪ D) and user's important attribute Y, wherein C is conditional attribute collection (being the bug list collection), comprises n conditional attribute, and D is decision attribute (being fault category), and Y is user's reserved property.
Output: attribute reduction collection R.
Basic ideas: from single-row C1, calculating according to it to be fault type to decision attribute D(correctly) the classification number distinguished | POS
C1(D) | (being classification number in the positive territory of the D of C1), calculate the classification number that correctly to distinguish D according to two row again ... up to obtaining the m row, (m＜=n) D and whole conditional attribute collection C are had identical separating capacity (namely the classification number of correctly D being classified according to these m row is identical with the classification number of classifying according to C), these m row are exactly the set after the yojan according to these m row.
Following table one be from the signal monitoring system acquisition to the historical railway signal Monitoring Data of part the fault sample collection:
Table one
Wherein, decision attribute is the fault code name, and conditional attribute a-g is each attribute of fault correspondence, is Property Name in the bracket, is the sensing station label, and the value in the form is the value after each measurement value sensor is handled by a certain scope discretize.
It as the input decision table, after program, is obtained attribute a, d, e is one group of attribute after the yojan, thereby can obtain the decision table after the yojan, as following table two:
Table two
Wherein, conditional attribute can be used as the data characteristics of extraction.
Pattern generation module 124 is used for generating Failure Diagnostic Code according to the data characteristics of extracting.
Diagnosis rule is exactly one group of failure judgment expression formula, generally is If＜condition〉Then＜conclusion form, it is illustrated under the current condition, may be corresponding fault.
For example: the association rule digging carries out Failure Diagnostic Code, and to set up algorithm as follows:
Input: Mishap Database (FDB), minimum support threshold value (min_sup), minimum confidence level threshold value (min_conf)
Output: the diagnosis rule storehouse obtains the rule of correspondence of fault signature and failure modes.
Association rule digging algorithm carries out the foundation in Failure Diagnostic Code storehouse, works as min_sup=20%, during min_conf=80%, and its result such as following table three:
| B2 | A2 | E6 | E1 | A1 | E10 | D1 | E5 | FaultNum |
| 0 | <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | 4 |
| <NULL> | <NULL> | <NULL> | 1 | <NULL> | <NULL> | <NULL> | <NULL> | 3 |
| <NULL> | <NULL> | <NULL> | <NULL> | 0 | <NULL> | <NULL> | <NULL> | 3 |
| <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | 1 | <NULL> | <NULL> | 2 |
| <NULL> | 0 | <NULL> | <NULL> | <NULL> | <NULL> | 0 | <NULL> | 3 |
| <NULL> | <NULL> | 1 | 0 | <NULL> | <NULL> | <NULL> | <NULL> | 2 |
| <NULL> | <NULL> | 1 | <NULL> | <NULL> | <NULL> | <NULL> | 0 | 3 |
| <NULL> | <NULL> | 1 | <NULL> | <NULL> | <NULL> | <NULL> | 1 | 2 |
| <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | 0 | 1 | 3 |
| <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | 1 | 0 | 3 |
| 1 | 0 | 1 | <NULL> | <NULL> | <NULL> | <NULL> | <NULL> | 1 |
| <NULL> | 1 | 0 | 0 | <NULL> | <NULL> | 1 | <NULL> | 4 |
| <NULL> | 1 | 0 | 0 | <NULL> | <NULL> | <NULL> | 1 | 4 |
Table three
As can be seen, under the condition with high confidence and support, the rule that obtains has also covered all failure modess from table three, has so just obtained having the diagnosis rule storehouse (being the set of Failure Diagnostic Code) of directiveness.
Rule in the diagnosis rule storehouse is expressed as follows:
rule：
If ZQJ1-4is has
Then conclude fault is ZQJ1-4 broken string
rule：
If ZQJ1-4is does not have
And if ZQJ1is does not have KF
Then conclude fault is ZQJ4～KF intermittent line
rule：
If ZQJ1-4is does not have
And if ZQJ1is does not have KZ
And combined side end 05-5is has KZ
Then conclude fault is05-5～ZQJ1 intermittent line
……
3, failure diagnosis unit 14 comprises:
Characteristic extracting module 141 is used for analyzing at the real-time railway signal Monitoring Data of signal monitoring system data processing unit collection, and extracts data characteristics.
The process that 141 pairs of real-time railway signal Monitoring Data of characteristic extracting module in the present embodiment are analyzed is identical with the process that above-mentioned data-mining module is analyzed the data that are fit to the excavation Failure Diagnostic Code, and the data characteristics that characteristic extracting module is extracted is also identical with the data characteristics that above-mentioned data-mining module extracts.Difference is that the data characteristics that data-mining module extracts is used for generating Failure Diagnostic Code, and the data characteristics that characteristic extracting module is extracted is used for whether fault of diagnostic signal equipment.
Diagnosis determination module 142 is used for carrying out the data characteristics that characteristic extracting module is extracted is mated according to Failure Diagnostic Code and criterion, draws preliminary fault diagnosis result.
By above-mentioned table three as can be known, diagnosis determination module 142 can be that condition is mated the data characteristics that characteristic extracting module is extracted one by one in conjunction with criterion with the rule in the diagnosis rule storehouse, if the data characteristics of extracting and the condition of a certain fault in diagnosis rule storehouse coupling can tentative diagnosis be fault then.
Explain decision-making module 143, for reasoning that fault is made an explanation, determine failure cause.
This module can make an explanation to fault with reference to canned data content in the existing expert system.
It is 201310190664.4 application documents to the patent No. that signal monitoring system data processing unit 11, data analysis unit 12, knowledge base unit 13, failure diagnosis unit 14, man-machine interface unit 15 and the data warehouse unit 16 that present embodiment provides can be used as one group of plug-in unit, denomination of invention be a kind of track traffic synthetic monitoring and scheduling collaborative with the O﹠M information system in, realize systemic-function level synoptic diagram as shown in Figure 4 in this system.Particularly, each unit that present embodiment provides can be used as the fault diagnosis assembly and is inserted into the collaborative application support layer with the O﹠M informatization platform of track traffic synthetic monitoring and dispatching, also can be divided into form with assembly and be inserted into device level in the monitor layer that above-mentioned patent document mentions, system-level, application layer etc.Because it is strong that the system that provides of present embodiment has a transplantability, characteristics such as various informativeization, therefore both can be connected the realization corresponding function with existing railway electrical CSM system, also can be connected with the new track traffic monitoring systems such as CSM system of the following railway system, realize the continuity of native system, system is possessed follow the migration transfer ability of railway system's device upgrade.
The railway signal Monitoring Data that will have now on the centralized signal supervision CSM of the railway system equipment by employing in the system that present embodiment provides gathers out, analyze Failure Diagnostic Code according to the historical railway signal Monitoring Data of gathering, in conjunction with existing railway territory standard, diagnose at real-time railway signal Monitoring Data, whether the duty of determining railway signal system the technological means of fault, solved in the prior art, workload is big when manually diagnosing the railway signal system fault, inefficiency, risk high-technology problem, and then obtain automatic diagnosis railway signal system fault, increase work efficiency, reduce artificial workload, find system problem as early as possible, reduce the technique effect of railway operation risk.
The above, it only is the specific embodiment of the present invention, but the present invention can have multiple multi-form embodiment, above by reference to the accompanying drawings the present invention is done and illustrate, this does not also mean that the applied embodiment of the present invention can only be confined in these specific embodiments, those skilled in the art should understand, the embodiment that above provides is some examples in the multiple preferred implementation, and the embodiment of any embodiment claim of the present invention all should be within claim of the present invention scope required for protection; Those skilled in the art can make amendment to the technical scheme of putting down in writing in each embodiment above, perhaps part technical characterictic wherein is equal to replacement.Within the spirit and principles in the present invention all, any modification of doing, be equal to and replace or improvement etc., all should be included within the protection domain of claim of the present invention.
Claims (7)
1. the mining analysis of a track traffic monitor data and fault diagnosis system is characterized in that, comprising: signal monitoring system data processing unit, data analysis unit, knowledge base unit, failure diagnosis unit and man-machine interface unit; Wherein,
Described signal monitoring system data processing unit is used for gathering historical railway signal Monitoring Data and real-time railway signal Monitoring Data from the centralized signal supervision CSM equipment at each electric affair workshop or scene, work area;
Described data analysis unit is used for the historical railway signal Monitoring Data of signal monitoring system data processing unit collection is analyzed, and generates Failure Diagnostic Code, and this Failure Diagnostic Code is sent to the knowledge base unit;
Described knowledge base unit is used for the criterion that storage is used according to the fault diagnosis of the country in the principle of work of each railway signals equipment, railway signal field and industry standard, norm-setting, and the Failure Diagnostic Code of storage data analysis unit;
Described failure diagnosis unit is used for the real-time railway signal Monitoring Data at the collection of signal monitoring system data processing unit, generates fault diagnosis result according to Failure Diagnostic Code and criterion;
Described man-machine interface unit is used for fault diagnosis result is showed the user.
2. system according to claim 1 is characterized in that, described data analysis unit comprises:
Data preparation module is used for selecting railway signal to analyze data from the historical railway signal Monitoring Data that signal monitoring system data processing unit is gathered;
Data preprocessing module, the railway signal that is used for selecting is analyzed data and is handled, and generates the data that are suitable for excavating Failure Diagnostic Code;
Data-mining module is used for adopting data mining algorithm that the data that are fit to the excavation Failure Diagnostic Code are analyzed, and extracts data characteristics;
The pattern generation module is used for generating Failure Diagnostic Code according to the data characteristics of extracting.
3. method according to claim 1 and 2 is characterized in that, described failure diagnosis unit comprises:
Characteristic extracting module is used for analyzing at the real-time railway signal Monitoring Data of signal monitoring system data processing unit collection, and extracts data characteristics;
The diagnosis determination module is used for according to Failure Diagnostic Code and criterion the data characteristics of characteristic extracting module extraction being mated, and draws fault diagnosis result.
4. method according to claim 3 is characterized in that, failure diagnosis unit also comprises:
Explain decision-making module, for reasoning that fault is made an explanation, determine failure cause.
5. system according to claim 1 is characterized in that, this system also comprises the data warehouse unit;
Described data analysis unit, the historical railway signal Monitoring Data that also is used for gathering sends to the data warehouse unit;
Described data warehouse unit is used for the described historical railway signal Monitoring Data of storage.
6. system according to claim 5 is characterized in that,
Described data analysis unit also is used for real-time railway signal Monitoring Data is sent to the data warehouse unit;
Described data warehouse unit, the real-time railway signal Monitoring Data that also is used for the data analysis unit transmission is come is transparent to failure diagnosis unit.
7. system according to claim 5 is characterized in that,
Described failure diagnosis unit also is used at data warehouse unit stored historical railway signal Monitoring Data, generates fault diagnosis result according to Failure Diagnostic Code and criterion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310211356.5A CN103345207B (en) | 2013-05-31 | 2013-05-31 | Mining analyzing and fault diagnosis system of rail transit monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310211356.5A CN103345207B (en) | 2013-05-31 | 2013-05-31 | Mining analyzing and fault diagnosis system of rail transit monitoring data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103345207A true CN103345207A (en) | 2013-10-09 |
| CN103345207B CN103345207B (en) | 2015-06-24 |
Family
ID=49280010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310211356.5A Active CN103345207B (en) | 2013-05-31 | 2013-05-31 | Mining analyzing and fault diagnosis system of rail transit monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103345207B (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103760901A (en) * | 2013-12-31 | 2014-04-30 | 北京泰乐德信息技术有限公司 | Rail transit fault identification method based on association rule classifier |
| CN104615121A (en) * | 2014-12-04 | 2015-05-13 | 深圳市永达电子股份有限公司 | Method and system for train fault diagnosis |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN105376314A (en) * | 2015-11-18 | 2016-03-02 | 深圳市博安达信息技术股份有限公司 | Method and device for extracting environmental monitoring and analyzing data into LIMS |
| CN105954607A (en) * | 2015-11-12 | 2016-09-21 | 北京交通大学 | Method and system for detecting faults of high-speed railway signal system |
| CN106293630A (en) * | 2016-08-19 | 2017-01-04 | 四川网达科技有限公司 | Railway signal fault analyzes logic rule generating means and method |
| CN106406295A (en) * | 2016-12-02 | 2017-02-15 | 南京康尼机电股份有限公司 | Rail transit vehicle door system fault diagnosis and early warning method based on multiple conditions |
| CN106447172A (en) * | 2016-08-31 | 2017-02-22 | 国网安徽省电力公司亳州供电公司 | PMS account-based data check method and system |
| CN103699698B (en) * | 2014-01-16 | 2017-03-29 | 北京泰乐德信息技术有限公司 | A kind of being based on improves Bayesian rail transit fault identification method and system |
| CN104091070B (en) * | 2014-07-07 | 2017-05-17 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
| CN107229271A (en) * | 2017-06-14 | 2017-10-03 | 王东红 | A kind of intelligent transportation development platform method for diagnosing faults and device |
| CN107959583A (en) * | 2017-10-26 | 2018-04-24 | 卡斯柯信号有限公司 | A kind of management system of Centralizing inspection warning message |
| CN108196985A (en) * | 2017-12-29 | 2018-06-22 | 中国电子科技集团公司信息科学研究院 | A kind of storage system failure prediction method and device based on intelligent predicting |
| CN108909773A (en) * | 2017-10-30 | 2018-11-30 | 卡斯柯信号有限公司 | A kind of signalling arrangement comprehensive analysis of fault system |
| CN109085829A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of sound state target identification method |
| WO2019011039A1 (en) * | 2017-07-10 | 2019-01-17 | 比亚迪股份有限公司 | Turnout information processing method and apparatus |
| CN109240265A (en) * | 2018-09-18 | 2019-01-18 | 中国路桥工程有限责任公司 | A kind of railway signal system and intelligent failure diagnosis method |
| CN109254570A (en) * | 2018-09-27 | 2019-01-22 | 卡斯柯信号有限公司 | A kind of Intelligent closed-loop control system applied to high-speed rail signal equipment repair |
| CN110309214A (en) * | 2018-04-10 | 2019-10-08 | 腾讯科技（深圳）有限公司 | A kind of instruction executing method and its equipment, storage medium, server |
| WO2020078137A1 (en) * | 2018-10-19 | 2020-04-23 | 北京全路通信信号研究设计院集团有限公司 | Platform for smart analysis of railway signal system faults |
| CN111198924A (en) * | 2018-11-19 | 2020-05-26 | 长鑫存储技术有限公司 | Method for establishing product failure knowledge base, failure analysis method, device and medium |
| CN111368919A (en) * | 2020-02-25 | 2020-07-03 | 重庆大学 | Feature data construction method, data set construction method, data classification method, EMC fault diagnosis method and system |
| CN111858270A (en) * | 2020-05-29 | 2020-10-30 | 卡斯柯信号有限公司 | Interlocking system fault positioning method based on data mining algorithm |
| CN112487058A (en) * | 2020-11-30 | 2021-03-12 | 北京航空航天大学 | Numerical control machine tool fault monitoring and diagnosing system based on data mining |
| CN112526401A (en) * | 2020-11-17 | 2021-03-19 | 国网天津市电力公司 | Comprehensive on-line monitoring and fault early warning system for high-voltage cable |
| CN113468245A (en) * | 2021-07-19 | 2021-10-01 | 金陵科技学院 | Dynamic minimum support degree calculation method for rail transit application |
| CN113859306A (en) * | 2020-06-30 | 2021-12-31 | 株洲中车时代电气股份有限公司 | Locomotive data expert diagnostic analysis method, device and system |
| CN113963456A (en) * | 2020-07-20 | 2022-01-21 | 核工业理化工程研究院 | Method and system for analyzing operation data of multiple high-speed rotating devices |
| CN114228785A (en) * | 2021-12-22 | 2022-03-25 | 卡斯柯信号有限公司 | Intelligent browsing device based on railway signal system monitoring data |
| CN114228785B (en) * | 2021-12-22 | 2024-05-31 | 卡斯柯信号有限公司 | Intelligent browsing device based on railway signal system monitoring data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917237A (en) * | 2010-07-27 | 2010-12-15 | 北京全路通信信号研究设计院 | Railway signal monitoring method and system |
| CN102879680A (en) * | 2012-09-26 | 2013-01-16 | 中南大学 | Rail transit vehicle equipment universal detection and fault diagnosis method and system |
-
2013
- 2013-05-31 CN CN201310211356.5A patent/CN103345207B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917237A (en) * | 2010-07-27 | 2010-12-15 | 北京全路通信信号研究设计院 | Railway signal monitoring method and system |
| CN102879680A (en) * | 2012-09-26 | 2013-01-16 | 中南大学 | Rail transit vehicle equipment universal detection and fault diagnosis method and system |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103760901A (en) * | 2013-12-31 | 2014-04-30 | 北京泰乐德信息技术有限公司 | Rail transit fault identification method based on association rule classifier |
| CN103699698B (en) * | 2014-01-16 | 2017-03-29 | 北京泰乐德信息技术有限公司 | A kind of being based on improves Bayesian rail transit fault identification method and system |
| CN104091070B (en) * | 2014-07-07 | 2017-05-17 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
| CN104615121A (en) * | 2014-12-04 | 2015-05-13 | 深圳市永达电子股份有限公司 | Method and system for train fault diagnosis |
| CN104615121B (en) * | 2014-12-04 | 2017-08-04 | 深圳市永达电子信息股份有限公司 | A kind of train fault diagnostic method and system |
| CN105045256B (en) * | 2015-07-08 | 2018-11-20 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on date comprision |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN105954607A (en) * | 2015-11-12 | 2016-09-21 | 北京交通大学 | Method and system for detecting faults of high-speed railway signal system |
| CN105376314A (en) * | 2015-11-18 | 2016-03-02 | 深圳市博安达信息技术股份有限公司 | Method and device for extracting environmental monitoring and analyzing data into LIMS |
| CN105376314B (en) * | 2015-11-18 | 2019-04-16 | 深圳博沃智慧科技有限公司 | A kind of method and device that environmental monitoring and analysis data are extracted to LIMS |
| CN106293630B (en) * | 2016-08-19 | 2018-07-27 | 四川网达科技有限公司 | Railway signal fault analyzes logic rules generating means and method |
| CN106293630A (en) * | 2016-08-19 | 2017-01-04 | 四川网达科技有限公司 | Railway signal fault analyzes logic rule generating means and method |
| CN106447172A (en) * | 2016-08-31 | 2017-02-22 | 国网安徽省电力公司亳州供电公司 | PMS account-based data check method and system |
| CN106406295A (en) * | 2016-12-02 | 2017-02-15 | 南京康尼机电股份有限公司 | Rail transit vehicle door system fault diagnosis and early warning method based on multiple conditions |
| CN107229271A (en) * | 2017-06-14 | 2017-10-03 | 王东红 | A kind of intelligent transportation development platform method for diagnosing faults and device |
| WO2019011039A1 (en) * | 2017-07-10 | 2019-01-17 | 比亚迪股份有限公司 | Turnout information processing method and apparatus |
| CN107959583A (en) * | 2017-10-26 | 2018-04-24 | 卡斯柯信号有限公司 | A kind of management system of Centralizing inspection warning message |
| CN108909773A (en) * | 2017-10-30 | 2018-11-30 | 卡斯柯信号有限公司 | A kind of signalling arrangement comprehensive analysis of fault system |
| CN108196985A (en) * | 2017-12-29 | 2018-06-22 | 中国电子科技集团公司信息科学研究院 | A kind of storage system failure prediction method and device based on intelligent predicting |
| CN110309214B (en) * | 2018-04-10 | 2023-06-23 | 腾讯科技（深圳）有限公司 | Instruction execution method and equipment, storage medium and server thereof |
| CN110309214A (en) * | 2018-04-10 | 2019-10-08 | 腾讯科技（深圳）有限公司 | A kind of instruction executing method and its equipment, storage medium, server |
| CN109085829A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of sound state target identification method |
| CN109240265A (en) * | 2018-09-18 | 2019-01-18 | 中国路桥工程有限责任公司 | A kind of railway signal system and intelligent failure diagnosis method |
| CN109254570A (en) * | 2018-09-27 | 2019-01-22 | 卡斯柯信号有限公司 | A kind of Intelligent closed-loop control system applied to high-speed rail signal equipment repair |
| CN111077871A (en) * | 2018-10-19 | 2020-04-28 | 北京全路通信信号研究设计院集团有限公司 | Railway signal system fault intelligent analysis platform |
| CN111077871B (en) * | 2018-10-19 | 2021-06-22 | 北京全路通信信号研究设计院集团有限公司 | Railway signal system fault intelligent analysis platform |
| WO2020078137A1 (en) * | 2018-10-19 | 2020-04-23 | 北京全路通信信号研究设计院集团有限公司 | Platform for smart analysis of railway signal system faults |
| CN111198924B (en) * | 2018-11-19 | 2022-11-25 | 长鑫存储技术有限公司 | Product failure knowledge base establishing method, failure analysis method, device and medium |
| CN111198924A (en) * | 2018-11-19 | 2020-05-26 | 长鑫存储技术有限公司 | Method for establishing product failure knowledge base, failure analysis method, device and medium |
| CN111368919A (en) * | 2020-02-25 | 2020-07-03 | 重庆大学 | Feature data construction method, data set construction method, data classification method, EMC fault diagnosis method and system |
| CN111368919B (en) * | 2020-02-25 | 2023-08-22 | 重庆大学 | Feature data construction method, data set construction method, data classification method, EMC fault diagnosis method and system |
| CN111858270A (en) * | 2020-05-29 | 2020-10-30 | 卡斯柯信号有限公司 | Interlocking system fault positioning method based on data mining algorithm |
| CN113859306A (en) * | 2020-06-30 | 2021-12-31 | 株洲中车时代电气股份有限公司 | Locomotive data expert diagnostic analysis method, device and system |
| CN113963456A (en) * | 2020-07-20 | 2022-01-21 | 核工业理化工程研究院 | Method and system for analyzing operation data of multiple high-speed rotating devices |
| CN112526401A (en) * | 2020-11-17 | 2021-03-19 | 国网天津市电力公司 | Comprehensive on-line monitoring and fault early warning system for high-voltage cable |
| CN112487058A (en) * | 2020-11-30 | 2021-03-12 | 北京航空航天大学 | Numerical control machine tool fault monitoring and diagnosing system based on data mining |
| CN113468245B (en) * | 2021-07-19 | 2023-05-05 | 金陵科技学院 | Dynamic minimum support calculation method for rail transit application |
| CN113468245A (en) * | 2021-07-19 | 2021-10-01 | 金陵科技学院 | Dynamic minimum support degree calculation method for rail transit application |
| CN114228785A (en) * | 2021-12-22 | 2022-03-25 | 卡斯柯信号有限公司 | Intelligent browsing device based on railway signal system monitoring data |
| WO2023116246A1 (en) * | 2021-12-22 | 2023-06-29 | 卡斯柯信号有限公司 | Intelligent browsing device based on railway signal system monitoring data |
| CN114228785B (en) * | 2021-12-22 | 2024-05-31 | 卡斯柯信号有限公司 | Intelligent browsing device based on railway signal system monitoring data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103345207B (en) | 2015-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103345207B (en) | Mining analyzing and fault diagnosis system of rail transit monitoring data | |
| CN103714383B (en) | Rail transit fault diagnosis method and system based on rough set | |
| CN105045256B (en) | Rail traffic real-time fault diagnosis method and system based on date comprision | |
| CN103699698B (en) | A kind of being based on improves Bayesian rail transit fault identification method and system | |
| CN112926666A (en) | Rail transit fault diagnosis method | |
| CN103760901B (en) | A kind of rail transit fault identification method based on Classification of Association Rules device | |
| CN102879680B (en) | The general detection of rail transit vehicle equipment and method for diagnosing faults and system | |
| CN104077552B (en) | A kind of track traffic signal based on cloud computing integrates O＆M method and system | |
| CN101853291B (en) | Data flow based car fault diagnosis method | |
| CN108398934B (en) | equipment fault monitoring system for rail transit | |
| CN110958136A (en) | Deep learning-based log analysis early warning method | |
| CN104091070A (en) | Rail transit fault diagnosis method and system based on time series analysis | |
| CN110855503A (en) | Fault cause determining method and system based on network protocol hierarchy dependency relationship | |
| CN107451004A (en) | A kind of switch breakdown diagnostic method based on qualitiative trends analysis | |
| CN107340766A (en) | Power scheduling alarm signal text based on similarity sorts out and method for diagnosing faults | |
| CN104616092A (en) | Distributed log analysis based distributed mode handling method | |
| CN103324128B (en) | Primary equipment fault warning comprehensive compression method in power dispatching automation system | |
| CN111612018A (en) | Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion | |
| CN104182465A (en) | Network-based big data processing method | |
| CN104751285A (en) | Accuracy judgment and warning system for front-end collected data in automation of electric network management | |
| CN111806516A (en) | Health management device and method for intelligent train monitoring and operation and maintenance | |
| CN110286300A (en) | A kind of multi branch electric power lines road Fault Locating Method, device, equipment and system | |
| CN108376253A (en) | A kind of signal trouble monitoring method based on machine vision | |
| CN101807314B (en) | Method for processing embedded vehicle working condition hybrid heterogeneous data information in real time | |
| AU2017327430B2 (en) | Monitoring infrastructure facilities by means of geo-clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |