CN109299155A - A kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method based on big data - Google Patents
A kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method based on big data Download PDFInfo
- Publication number
- CN109299155A CN109299155A CN201810952849.7A CN201810952849A CN109299155A CN 109299155 A CN109299155 A CN 109299155A CN 201810952849 A CN201810952849 A CN 201810952849A CN 109299155 A CN109299155 A CN 109299155A
- Authority
- CN
- China
- Prior art keywords
- data
- analysis
- fault diagnosis
- big
- big data
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its method based on big data, the following steps are included: obtaining the equipment operating data that urban track traffic centralized monitoring system obtains in real time by data-interface and data import modul, and it is sent to data memory module;The real time data of data memory module receiving device is stored into the Distributed Storage warehouse of Hadoop platform;Data preprocessing module transfers corresponding data from data memory module, the processing of vacancy value, noise processed, data conversion is carried out, and be sent to data analysis module, in order to the further analysis of data;Data analysis module carries out status data analysis using big data platform and data analysis technique, obtains diagnostic result, result is transferred to user and is made alerts or provides accordingly corresponding suggestion;User can check real-time and historical data, the image recording of relevant device by user's access modules, transfer relevant fault diagnosis and data analysis result.
Description
Technical field
The present invention relates to the fault diagnosis fields of Urban Rail Transit Signal equipment, and in particular to a kind of based on big data
Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method.
Background technique
Safety, is the basis of City Rail Transit System operation, and signal system is that City Rail Transit System is transported safely
The core guarantee of battalion.Signalling arrangement is not only to influence the key of the normal operation of Rail Transit System, its failure even can be right
The person and property safety damage, therefore the real-time monitoring of signalling arrangement and fault diagnosis transport the safety of Rail Transit System
Barrack furniture is significant.Centralized signal supervision is the major way for safeguarding track traffic signal equipment.It is able to achieve signalling arrangement
Transferring for operation history data check, and to important equipment or there may be the failures of significant impact to alarm.With track
Traffic system complexity is continuously increased, and the monitoring management demand of signal system and equipment is also continuously improved.
The maintenance system of current track traffic is divided into breakdown maintenance, planned maintenance, condition maintenarnce.Breakdown maintenance refers to
The maintenance work targetedly carried out after equipment failure, the disadvantage is that hysteresis quality is stronger.The basic principle of planned maintenance
It is that maintenance work is carried out to equipment on time according to the plan formulated in advance.Condition maintenarnce then need to investigate equipment actual conditions and
Working condition carries out examination and maintenance to equipment in need.It is set although existing Maintenance and Repair strategy largely ensure that
Arrange standby safe and reliable, but this mode at regular time and quantity will also result in waste and lag to a certain extent, be difficult to make to set
Standby use is arranged to maximize.
In recent years, big data industry high speed development, and in economic market, medical field, intelligent transportation, internet
Etc. industries played important function, its advantage lies in being able to realize miscellaneous mass data is stored and processed, and
Speed is fast, high-efficient.The operation of Urban Rail Transit Signal equipment is all generating data all the time, and data volume is big, type is more
Sample carries out in-depth analysis excavation to rail traffic data, can make these data using big data platform and data analysing method
It is fully used, plays the advantage of big data, timely fault diagnosis and comprehensively supervision are carried out to track traffic signal equipment,
Guarantee driving safety improves operational efficiency.
Summary of the invention
In order to achieve the above object, the technical scheme is that a kind of Urban Rail Transit Signal based on big data
Equipment fault diagnosis method improves plant maintenance pipe, it can be achieved that real-time monitoring and fault diagnosis to track traffic signal equipment
Reason is horizontal, ensures operation security.The following steps are included:
Step 1 is obtained in real time by data-interface and data import modul acquisition urban track traffic centralized monitoring system
Equipment operating data: switching value, power supply panel voltage, railway voltage, switch indication voltage, switch indication electric current, power supply are over the ground
Leakage current, frequency-shift signaling etc., and it is sent to data memory module.
The Distributed Storage of Hadoop platform is arrived in the real time data of step 2, data memory module receiving device, storage
In warehouse.
Step 3, data preprocessing module transfer corresponding data from data memory module, carry out the processing of vacancy value, make an uproar
Sonication, data conversion, and it is sent to data analysis module, in order to the further analysis of data.
Step 4, data analysis module carry out status data analysis using big data platform and data analysis technique, are examined
It is disconnected as a result, result is transferred to user and is made alerting or providing accordingly corresponding suggestion.
Step 5, user can check real-time and historical data, the image recording of relevant device by user's access modules,
Transfer relevant fault diagnosis and data analysis result.
Further, the step 3 specifically includes the following steps:
Step 3-1: the processing of vacancy value: when multiple attribute value vacancies of a tuple, ignore the tuple;When tuple only
When there are a small number of attribute values to lack, vacancy value is filled up;The mode filled up include manually fill up, global constant, affiliated attribute
Under average value, or under the attribute data application derive tool, possible fill out is obtained by the analysis to other numerical value
It supplements with money;
Step 3-2: the processing of noise data: using the method for branch mailbox, data are averagely divided into several casees, to each case
Numerical value in son is converted, and the average value of all numerical value, intermediate value or boundary value in case are converted to;
Step 3-3: data conversion: initial data is reclassified, is encoded;It is clustered, smoothing processing, is referred to suitable
For different mining algorithms;Reduction process is carried out to data, using wavelet transformation and principal component analysis, to obtain to protect
The relatively small data set of legacy data integrality is held, in order to the analysis of further data.
Further, the step 4 is by the distributed computing MapReduce model and data analysis algorithm of big data platform
It combines, wherein the workflow of MapReduce includes:
Step 4-1: each node being sent in cluster after the data of concentration are divided is respectively processed;
Step 4-2: the node in cluster reports the update of the periodicity of fruiting of operation to JobTracker;
Step 4-3: assuming that within a preset time, JobTracker does not receive the heartbeat message from TaskTracker,
It is so just defaulted as the TaskTracker failure of the DataNode, JobTracker can send out the data for distributing to this node
Give other node.
Further, the data analysis module in the step 4 uses Apriori algorithm, is based on breadth-first, successively repeatedly
For the association algorithm of thought, by continuous iteration, k+1 item collection is finally released from k Candidate Sets.Its step includes:
Step 4-4. sets LkIt is k frequent item sets, CkIt is k Candidate Sets;Use LkTo generate Lk+1For;
Step 4-5. seeks frequent 1 item collection L1, use set I as Candidate Set C1, scan data set D acquires C1Support,
It finds out and is wherein greater than the element of minimum support min_support as frequent 1 item collection L1;
Step 4-6. gradually scan data set D, to obtain candidate CkSupport, and find out wherein be greater than minimum
The element of support min_support is as frequent k item collection Lk;
Step 4-7. is according to frequent k (k >=1) item collection LkTo generate k+1 Candidate Set Ck+1;
Step 4-8. iteration executes step S3 and step S4, until that cannot find out k+1 Candidate Sets.
The present invention also provides a kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment based on big data is used for city
The fault diagnosis and data of track traffic signal equipment are analyzed, comprising:
Data import modul, the equipment real-time running data for obtaining centralized monitoring system imported into big data platform
It is further processed;
Data memory module, for storing a large amount of device real-time monitoring data;
Data preprocessing module implements receiving device data, is pre-processed and converted to data, in order to next step
Data analysis, and will after processing data transmission to data analysis module;
Data analysis module is based on big data distributed platform, is analyzed using data processing algorithm device data
Processing and Condition Prediction of Equipment;
User's access modules provide the window of real-time monitoring equipment data situation for user, by data analysis and event
Barrier diagnostic result is sent to user, and makes and alarm or provide accordingly corresponding suggestion.
Further, data import modul (including opens equipment real time data that rail traffic centralized monitoring system obtains
Guan Liang, power supply panel voltage, railway voltage, switch indication voltage, switch indication electric current, power supply leakage current, frequency-shift signaling etc. over the ground),
Data are imported into the Distributed Data Warehouse of Hadoop big data platform using data import tool Sqoop from traditional database
In.
Further, obtained device data is stored in Hadoop cluster by data memory module.The present invention uses
HBase stores data.The table of HBase is divided into many song HRegion, is later saved in ready-portioned table
In HRegion server zone.Once the size of table is more than setting value, table is divided into different regions, and each area by HBase automatically
Can all there be a subset of the row in domain, be distinguished by major key.It physically sees, a table is divided into multiple HRegion, each
Word table is stored in place appropriate.Each Region has a unique RegionID, and all HRegion identifiers are most
All it is afterwards: table name word+beginning major key+unique ID.
Further, data preprocessing module carries out the processing of vacancy value, noise processed, data turn to the data being collected into
It changes, and taxonomic revision is carried out to valid data.
The processing method of vacancy value has: 1. ignore, and when multiple attribute value vacancies of a tuple, ignore the tuple;2.
It fills up, when tuple, which only has a small number of attribute values, to be lacked, vacancy value is filled up.The mode filled up includes manually filling up, being global
Average value under constant, affiliated attribute, or under the attribute data application derive tool, by the analysis to other numerical value come
Obtain possible Filling power.
The processing method of noise data has: 1. branch mailbox, data is averagely divided into several casees, to the numerical value in each chest
It is converted, is converted to the average value of all numerical value, intermediate value or boundary value in case;2. cluster, while eliminating noise, hair
Existing isolated point;3. regression analysis.
The method of data conversion has: 1. pairs of initial data reclassify, encode, defined variable and modification variable;2. data
Algebraic operation, change variable between non-linear relation, make it easier to model solution;3. data summarize with it is extensive;4. adding
Power processing, keeps sample more representative or emphasizes the importance of certain data.
Further, data analysis module analyzes the distributed computing MapReduce model of big data platform and data
Algorithm combines, and is modeled using data analysis algorithm to data, the fault diagnosis and data analysis of equipment is realized, using big
Data platform carries out distributed computing, gives full play to the advantage of mass data, realizes data processing rapidly and efficiently.
Further, data analysis module uses Apriori algorithm, is based on breadth-first, the association of layer-by-layer iteration thought
Algorithm finally releases k+1 item collection by continuous iteration from k Candidate Sets.
Further, user's access modules are based on hardware and software platform system, check interface for what user provided equipment initial data,
Analysis according to the data analysis module is as a result, send user platform for failure diagnosis information, and make corresponding alarm
Or provide corresponding suggestion.
The invention has the benefit that being carried out to rail traffic data deep using big data platform and data analysing method
Enter analysis mining, these data can be made to be fully used, play the advantage of big data, track traffic signal equipment is carried out
Timely fault diagnosis and comprehensively supervision, guarantee driving safety improve operational efficiency.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment the present invention is based on big data
Fig. 2 is the flow chart of Sqoop data import modul of the present invention
Fig. 3 is the flow chart of data preprocessing module of the present invention
Fig. 4 is distributing mode computer system MapReduce configuration diagram of the present invention
The flow chart of Fig. 5 Apriori algorithm of the present invention
Specific embodiment
In order to better understand the technical content of the present invention, special to lift specific embodiment and institute's accompanying drawings is cooperated to be described as follows.
As shown in Figure 1, the present invention provides a kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment based on big data,
Fault diagnosis and data for Urban Rail Transit Signal equipment are analyzed, including data import modul, data memory module, number
Data preprocess module, data analysis module, user's access modules.
The equipment real-time running data that track traffic signal centralized monitoring system obtains mainly includes switching value, analog quantity
And frequency-shift signaling, it is imported into data memory module by data import modul.And by data according to data type, device type
It gives different preprocessing modules respectively after certain classification, targetedly carries out the processing of vacancy value, noise processed, data
Conversion, and taxonomic revision is carried out to valid data, it prepares for the analysis of subsequent data.Will treated data transmission to data
Analysis module is based on big data distributed platform, is analyzed and processed using data processing algorithm to device data and equipment shape
State prediction.Finally, user's access modules provide the window of real-time monitoring equipment data situation for user, by data analysis and
Fault diagnosis result is sent to user, and makes and alarm or provide accordingly corresponding suggestion.
As shown in figure 3, data preprocessing module transfers corresponding data from data memory module, carry out at vacancy value
Reason, noise processed, data conversion, and it is sent to data analysis module, in order to the further analysis of data.
S1. the processing of vacancy value: when multiple attribute value vacancies of a tuple, ignore the tuple;When tuple is only few
When number attribute value lacks, vacancy value is filled up.The mode filled up include manually fill up, global constant, under affiliated attribute
Average value, or tool is derived to the data application under the attribute, possible Filling power is obtained by the analysis to other numerical value.
S2. the processing of noise data: using the method for branch mailbox, data are averagely divided into several casees, in each chest
Numerical value converted, be converted to the average value of all numerical value, intermediate value or boundary value in case.
S3. data conversion: initial data is reclassified, is encoded;It is clustered, smoothing processing, refers to and be suitable for
Different mining algorithms;Reduction process is carried out to data, using wavelet transformation and principal component analysis, to obtain to keep former
There is the relatively small data set of data integrity, in order to the analysis of further data.
As shown in figure 4, distributed computing software architecture MapReduce is sent to cluster after the data of concentration are divided first
In each node be respectively processed;Then the node in cluster the update of the periodicity of fruiting of operation report to
JobTracker.Assuming that within a preset time, JobTracker does not receive the heartbeat message from TaskTracker, then
It is just defaulted as the TaskTracker failure of the DataNode, JobTracker can be sent to the data for distributing to this node
Other node.
As shown in figure 5, data analysis module uses Apriori algorithm, it is based on breadth-first, the association of layer-by-layer iteration thought
Algorithm finally releases k+1 item collection by continuous iteration from k Candidate Sets.
Mainly there are two processing steps for the algorithm: connection and beta pruning.If LkIt is k frequent item sets, CkIt is k Candidate Sets.With
LkTo generate Lk+1For, the realization step of Apriori algorithm are as follows:
1: seeking frequent 1 item collection L1, use set I as Candidate Set C1, scan data set D acquires C1Support, find out it
In greater than minimum support min_support element as frequent 1 item collection L1;
Gradually scan data set D, to obtain candidate CkSupport, and find out wherein be greater than minimum support
The element of min_support is as frequent k item collection Lk;
According to frequent k (k >=1) item collection LkTo generate k+1 Candidate Set Ck+1;
Iteration executes step (2) and step (3), until that cannot find out k+1 Candidate Sets.
In conclusion Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment provided by the invention based on big data and its
Method carries out processing analysis, Modeling Calculation by the mass data generated to track traffic signal equipment, can be effectively to setting
Standby operating status and fault condition is analyzed comprehensively, provides real-time quick fault diagnosis, to ensure rail traffic driving
Safety provides technical support.
Although embodiments of the present invention are illustrated in specification, these embodiments are intended only as prompting,
It should not limit protection scope of the present invention.It is equal that various omission, substitution, and alteration are carried out without departing from the spirit and scope of the present invention
It should be included within the scope of the present invention.
Claims (11)
1. a kind of Urban Rail Transit Signal equipment fault diagnosis method based on big data, which is characterized in that including following step
It is rapid:
Step 1 is set by what data-interface and data import modul acquisition urban track traffic centralized monitoring system obtained in real time
Standby operation data: switching value, power supply panel voltage, railway voltage, switch indication voltage, switch indication electric current, power supply over the ground leakage current,
Frequency-shift signaling etc., and it is sent to data memory module;
The Distributed Storage warehouse of Hadoop platform is arrived in the real time data of step 2, data memory module receiving device, storage
In;
Step 3, data preprocessing module transfer corresponding data from data memory module, carry out the processing of vacancy value, at noise
Reason, data conversion, and it is sent to data analysis module, in order to the further analysis of data;
Step 4, data analysis module carry out status data analysis using big data platform and data analysis technique, obtain diagnosis knot
Fruit, result is transferred to user and made alert or provide corresponding suggestion accordingly;
Step 5, real-time and historical data, the image recording that relevant device is checked by user's access modules transfer relevant event
Barrier diagnosis and data analysis result.
2. the track traffic signal equipment method for diagnosing faults according to claim 1 based on big data, which is characterized in that
The step 3 specifically includes the following steps:
Step 3-1: the processing of vacancy value: when multiple attribute value vacancies of a tuple, ignore the tuple;When tuple is only few
When number attribute value lacks, vacancy value is filled up;The mode filled up include manually fill up, global constant, under affiliated attribute
Average value, or tool is derived to the data application under the attribute, possible Filling power is obtained by the analysis to other numerical value;
Step 3-2: the processing of noise data: using the method for branch mailbox, data are averagely divided into several casees, in each chest
Numerical value converted, be converted to the average value of all numerical value, intermediate value or boundary value in case;
Step 3-3: data conversion: initial data is reclassified, is encoded;It is clustered, smoothing processing, refers to and be suitable for
Different mining algorithms;Reduction process is carried out to data, using wavelet transformation and principal component analysis, to obtain to keep former
There is the relatively small data set of data integrity, in order to the analysis of further data.
3. the track traffic signal equipment method for diagnosing faults according to claim 1 based on big data, which is characterized in that
The step 4 combines the distributed computing MapReduce model of big data platform with data analysis algorithm, wherein
The workflow of MapReduce includes:
Step 4-1: each node being sent in cluster after the data of concentration are divided is respectively processed;
Step 4-2: the node in cluster reports the update of the periodicity of fruiting of operation to JobTracker;
Step 4-3: assuming that within a preset time, JobTracker does not receive the heartbeat message from TaskTracker, then
It is just defaulted as the TaskTracker failure of the DataNode, JobTracker can be sent to the data for distributing to this node
Other node.
4. the track traffic signal equipment method for diagnosing faults according to claim 1 based on big data, which is characterized in that
Data analysis module in the step 4 uses Apriori algorithm, and specific steps include:
Step 4-4. sets LkIt is k frequent item sets, CkIt is k Candidate Sets;Use LkTo generate Lk+1For;
Step 4-5. seeks frequent 1 item collection L1, use set I as Candidate Set C1, scan data set D acquires C1Support, find out
Wherein the element greater than minimum support min_support is as frequent 1 item collection L1;
Step 4-6. gradually scan data set D, to obtain candidate CkSupport, and find out and be wherein greater than minimum support
The element of min_support is spent as frequent k item collection Lk;
Step 4-7. is according to frequent k (k >=1) item collection LkTo generate k+1 Candidate Set Ck+1;
Step 4-8. iteration executes step S3 and step S4, until that cannot find out k+1 Candidate Sets.
5. a kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment based on big data characterized by comprising data are led
Enter module, data memory module, data preprocessing module, data analysis module and user's access modules.
6. the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment according to claim 5 based on big data, feature
It is, the equipment real time data that the data import modul obtains rail traffic centralized monitoring system utilizes data import tool
Sqoop is by data from the Distributed Data Warehouse that traditional database imported into Hadoop big data platform.
7. the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment according to claim 5 based on big data, feature
It is, obtained device data is stored in Hadoop cluster by the data memory module.
8. the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment according to claim 5 based on big data, feature
It is, the data preprocessing module carries out the processing of vacancy value, noise processed, data conversion to the data that are collected into, and to having
It imitates data and carries out taxonomic revision.
9. the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment according to claim 5 based on big data, feature
It is, the data analysis module mutually ties the distributed computing MapReduce model of big data platform with data analysis algorithm
It closes, data is modeled using data analysis algorithm, carry out distributed computing using big data platform.
10. the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment according to claim 5 based on big data, feature
It is, the data analysis module uses Apriori algorithm, is based on breadth-first, and the association algorithm of layer-by-layer iteration thought passes through
Continuous iteration finally releases k+1 item collection from k Candidate Sets, the specific steps are as follows:
Connection and beta pruning;If LkIt is k frequent item sets, CkIt is k Candidate Sets;Use LkTo generate Lk+1For, Apriori algorithm
Realize step are as follows:
(1) frequent 1 item collection L is sought1, use set I as Candidate Set C1, scan data set D acquires C1Support, find out wherein big
In minimum support min_support element as frequent 1 item collection L1;
(2) gradually scan data set D, to obtain candidate CkSupport, and find out wherein be greater than minimum support min_
The element of support is as frequent k item collection Lk;
(3) according to frequent k (k >=1) item collection LkTo generate k+1 Candidate Set Ck+1;
(4) iteration executes step (2) and step (3), until that cannot find out k+1 Candidate Sets.
11. the Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment according to claim 1 based on big data, feature
It is, user's access modules are based on hardware and software platform system, the interface of checking of equipment initial data are provided for user, according to described in
The analysis of data analysis module is as a result, send user platform for failure diagnosis information, and make and alarm or provide accordingly phase
The suggestion answered.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810952849.7A CN109299155A (en) | 2018-08-21 | 2018-08-21 | A kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810952849.7A CN109299155A (en) | 2018-08-21 | 2018-08-21 | A kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109299155A true CN109299155A (en) | 2019-02-01 |
Family
ID=65165259
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810952849.7A Pending CN109299155A (en) | 2018-08-21 | 2018-08-21 | A kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299155A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102682187A (en) * | 2011-03-14 | 2012-09-19 | 卡斯柯信号有限公司 | Intelligent failure diagnosis method for track traffic equipment |
CN103338261A (en) * | 2013-07-04 | 2013-10-02 | 北京泰乐德信息技术有限公司 | Storage and processing method and system of rail transit monitoring data |
CN106997400A (en) * | 2017-05-25 | 2017-08-01 | 南京多伦科技股份有限公司 | A kind of monitoring of transit equipment O&M and data analysis system based on cloud service |
-
2018
- 2018-08-21 CN CN201810952849.7A patent/CN109299155A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102682187A (en) * | 2011-03-14 | 2012-09-19 | 卡斯柯信号有限公司 | Intelligent failure diagnosis method for track traffic equipment |
CN103338261A (en) * | 2013-07-04 | 2013-10-02 | 北京泰乐德信息技术有限公司 | Storage and processing method and system of rail transit monitoring data |
CN106997400A (en) * | 2017-05-25 | 2017-08-01 | 南京多伦科技股份有限公司 | A kind of monitoring of transit equipment O&M and data analysis system based on cloud service |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103714383B (en) | Rail transit fault diagnosis method and system based on rough set | |
CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
CN102130783B (en) | Intelligent alarm monitoring method of neural network | |
CN108008332A (en) | A kind of new energy Remote testing device method for diagnosing faults based on data mining | |
CN104077552B (en) | A kind of track traffic signal based on cloud computing integrates O&M method and system | |
CN103793853B (en) | Condition of Overhead Transmission Lines Based appraisal procedure based on two-way Bayesian network | |
CN109948169A (en) | A kind of railway freight-car prognostic and health management system | |
CN105354614B (en) | A kind of electric network information O&M active forewarning method based on big data | |
CN104299659B (en) | Nuclear power station running state monitoring method, apparatus and system | |
CN106354118A (en) | Fault diagnosis system and method for train based on fault tree | |
CN103745229A (en) | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) | |
CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
CN107529667A (en) | Mixed reality nuclear power station emulates and analysis system | |
CN107908175A (en) | A kind of electric system site intelligent operational system | |
CN105225007A (en) | A kind of sector runnability method for comprehensive detection based on GABP neural network and system | |
CN104615121B (en) | A kind of train fault diagnostic method and system | |
CN108446396A (en) | A kind of electric power data processing method based on modified CIM model | |
CN112576312B (en) | Data collection and processing method for electric-hydraulic control support of intelligent fully-mechanized coal mining face | |
CN108830335A (en) | Photovoltaic plant fault early warning method and system | |
CN107067129A (en) | Way and structures risk case possibility acquisition methods and system based on grid | |
CN105572492A (en) | City rail train auxiliary inverter fault diagnosis device | |
CN108647860A (en) | Power equipment state monitoring based on OpenStack and assessment cloud platform | |
CN114138870A (en) | Power supply arm train load characteristic obtaining method based on dynamic current collection | |
CN109299155A (en) | A kind of Urban Rail Transit Signal Fault Diagnosis of Mechanical Equipment and its diagnostic method based on big data | |
CN108667670A (en) | A kind of computer networking technology on-line maintenance system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190201 |