CN106406296A - Train fault diagnosis system and method based on vehicle and cloud - Google Patents
Train fault diagnosis system and method based on vehicle and cloud Download PDFInfo
- Publication number
- CN106406296A CN106406296A CN201611154208.4A CN201611154208A CN106406296A CN 106406296 A CN106406296 A CN 106406296A CN 201611154208 A CN201611154208 A CN 201611154208A CN 106406296 A CN106406296 A CN 106406296A
- Authority
- CN
- China
- Prior art keywords
- fault diagnosis
- data
- fault
- module
- clouds
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24048—Remote test, monitoring, diagnostic
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention provides a train fault diagnosis system and method based on a vehicle and cloud, and relates to the technical field of high-speed rail large data fault diagnosis. The system comprises a vehicle fault diagnosis subsystem and a cloud fault diagnosis subsystem. The vehicle fault diagnosis subsystem is combined with the cloud fault diagnosis subsystem. Cloud service is used to monitor the running process of a train. Cloud data are continuously updated, and a fault diagnosis and prediction model is continuously optimized and updated, and can visualize a diagnosis process. According to the invention, the details of the fault diagnosis and prediction model are more and more perfect; the precision is improved continuously; the performance is beyond the control of a traditional single real-time fault diagnosis module; the requirements of high reliability and high precision of the train fault diagnosis subsystem in the running process are satisfied; and the safety of the train in the running process is improved.
Description
Technical field
The present invention relates to high ferro big data fault diagnosis technology field, more particularly, to a kind of based on vehicle-mounted and high in the clouds train
Fault diagnosis system and method.
Background technology
At present, the High-speed Railway Network of China quickly grows, and this plays economic effect as early as possible and has positive role for it.Due to
Train running speed is fast, in order to preferably grasp the running status of train, diagnoses train fault in time, needs highly reliable train
Fault diagnosis control system, train status monitoring and fault diagnosis system are the important composition portions of railway operation safety security system
Point.
Existing train fault diagnosis is mainly controlled using onboard system, adopts the conventional method based on diagnostic rule,
Detect the deviation of anticipatory behavior on the basis of state variable can be obtained, with the help of fault and phenomenon of the failure relevant knowledge, examine
Disconnected abort situation.The related element of all subsystems of onboard diagnostic system monitoring and function.Due to bullet train data have bright
Aobvious big data feature, the value of the bullet train failure diagnosis information containing in the big data of bullet train operation and maintenance is huge
Greatly, and data has the features such as species is many, real-time, data volume is big, processing speed is fast so that existing fault diagnosis system is difficult
To adapt to above feature.The modeling of data-driven and fault diagnosis obtain a lot of progress and application in recent years in industrial quarters, are
Bullet train fault, diagnosis provide new approach and means.
At present, the research of some method for diagnosing faults based on data model existing, such as Patent No.
A kind of 201610143119.3 high ferro train control on board equipment method for diagnosing faults, the method is by mobile unit fault data
It is analyzed and feature extraction, decision information table is set up in extraction, and sets up Bayes's fault diagnosis network carrying out fault diagnosis.Should
Method still has a lot of deficiencies:1. it is based only upon onboard system and carries out fault diagnosis, diagnosis efficiency is low;2. model algorithm is single, and
And computation model can not be improved according to train operation situation and be optimized, train-installed fault diagnosis system diagnostic reliability
Low.
In sum, traditional train fault diagnosis is based only upon onboard system, due to train data rapid growth, and vehicle-mounted
System computing capacity and hardware resource are limited, and high ferro train is difficult to complete to substantial amounts, Rapid Accumulation in the process of moving
Large-scale data is analyzed modeling.Simultaneously in view of the special space environment of bullet train, big rule also cannot be disposed ON TRAINS
Mould computing cluster to set up high-precision train Diagnose System Model in real time to carry out mass rapid computing, and calculates mould
Type can not be improved according to train operation situation and be optimized, and lead to train-installed fault diagnosis subsystem fault diagnosis rate low,
The highly reliable monitoring requirement of high accuracy under bullet train complex situations can not be met.Therefore, be badly in need of research new based on cloud
Bullet train big data fault diagnosis system.
Content of the invention
For the defect of prior art, the present invention provides a kind of train fault diagnostic system based on vehicle-mounted and high in the clouds and side
Method, is monitored to train in the process of moving using cloud service, and high in the clouds data is constantly updated simultaneously, and model detail is more and more completeer
Kind, precision improves constantly, and performance beyond tradition single real-time fault diagnosis module controls, and meets train-installed fault diagnosis
The highly reliable in the process of moving high-precision requirement of system, improves train security in the process of moving.
On the one hand, the present invention provide a kind of based on vehicle-mounted and high in the clouds train fault diagnostic system, this system includes vehicle-mounted
Fault diagnosis subsystem and high in the clouds fault diagnosis subsystem.
Described vehicle-mounted fault diagnosis subsystem includes vehicle carried data collecting module, real-time fault diagnosis module and cloud diagnosis mould
Block;Described high in the clouds fault diagnosis subsystem includes high in the clouds data acquisition module, data memory module, data processing module, fault
Diagnosis and prediction module data visualization model.
Described vehicle carried data collecting module is used for the service data of train is acquired.
Described real-time fault diagnosis module is used for carrying out real-time fault diagnosis and prediction to train in train travelling process.
Described cloud diagnostic module is used for calling the fault diagnosis service that high in the clouds fault diagnosis subsystem is provided that train is entered
Row assist type fault diagnosis, i.e. on the one hand the diagnostic result to vehicle-mounted real-time fault diagnosis module and high in the clouds fault diagnosis subsystem
Fault diagnosis result contrasted, and comparing result is shown;On the other hand when comparing result shows described vehicle-mounted event
When failing to report or misrepresenting deliberately of significant trouble in barrier diagnostic subsystem, and by setting data transmission priority, preferential transmission diagnosis refers to
Make data, carry out quick auxiliary diagnosis using cloud diagnostic module.
Described high in the clouds data acquisition module, is on the one hand used for gathering the row transmitting in train travelling process by train network
The real time data that car runs, is on the other hand used for gathering the historical data that train operation terminates rear train operation.
The data that described data memory module is used for being gathered high in the clouds data acquisition module carries out data cleansing, data turns
Change data compression, and data is stored in corresponding data storage system by different types of data;Described data cleansing includes data
Fill a vacancy, data replaces data format specification;Described data conversion includes data fractionation, data sorting, data deduplication sum
According to checking;Described data compression is used for compress, to save memory space.
Described data processing module includes Computational frame submodule, inquiry submodule, data statistics submodule and algorithms library
Submodule;
Described Computational frame submodule includes real-time streaming Computational frame and non real-time batch processing Computational frame, described real-time
Streaming Computational frame is used for the calculating of real-time stream, and described non real-time batch processing Computational frame is used for calculating non real-time history number
According to;
Described inquiry submodule is used for inquiring about train operation in real time and historical data;
Described data statistics submodule is used for carrying out statistical disposition to the historical data of train operation;
Described algorithms library submodule is used for managing the algorithm of data processing.
Described fault diagnosis and fault prediction module includes model setting up submodule, model evaluation submodule, model management submodule
Block and fault diagnosis and fault prediction Attendant sub-module;
Described model setting up submodule is used for building fault diagnosis and fault prediction model using train history data;
Described model evaluation submodule is used for the diagnosis and prediction effect of fault diagnosis and fault prediction model is estimated;
All historical failures that described model management submodule is used for constructed by administrative model setting up submodule diagnose and pre-
Survey model;
Described fault diagnosis and fault prediction Attendant sub-module is used for providing and monitor fault diagnosis and fault prediction cloud service.
Described data visualization module is used for showing the result that Various types of data processes operation, including Query Result, statistics knot
Really, result of calculation and fault diagnosis result.
On the other hand, the present invention also provide a kind of based on vehicle-mounted and high in the clouds train fault diagnostic method, the method is passed through
Above-mentioned based on vehicle-mounted and high in the clouds train fault realizing of the diagnosis system, comprise the following steps that:
Historical data in step 1, vehicle carried data collecting module is uploaded to high in the clouds data acquisition module, high in the clouds by network
Data acquisition module is acquired to train data;
Step 2, the initial data uploading in the data acquisition module of high in the clouds is carried out with data cleansing and conversion after, then carry out
Data storage, specifically includes following steps:
Step 2.1, using ETL (Extract-Transform-Load) instrument to uploading in the data acquisition module of high in the clouds
Initial data carry out data fill a vacancy, data replace data format specification data cleansing operation, and data split, number
Data transformation operations according to sequence, the checking of data deduplication data;
Step 2.2, by cleaning, conversion after the corresponding data-storage system of data Cun Chudao, specially:
Step 2.2.1, structural data is saved in database;
Step 2.2.2, unstructured data is saved in file system;
Step 3, using the history data of train, high in the clouds original fault diagnosis and fault prediction model is estimated, and
Build new fault diagnosis and fault prediction model, specifically include following steps:
Step 3.1, model evaluation submodule are newly uploaded to the historical data of high in the clouds data acquisition module to cloud using train
End fault diagnosis subsystem original fault diagnosis and fault prediction model is estimated, if having wrong report or failing to report situation, executes step
Rapid 3.2, otherwise direct execution step 5;
Step 3.2, the historical data being newly uploaded to high in the clouds data acquisition module using train and high in the clouds data-storage system
In original historical data set up new fault diagnosis and fault prediction model, this model specification is optimal models, and by this model
Store model management submodule;
Step 3.3, structure supply vehicle-mounted fault diagnosis subsystem remote access high in the clouds fault diagnosis service interface, execute step
Rapid 4;
Before step 4, train operation, to the fault diagnosis in the real-time fault diagnosis module of vehicle-mounted fault diagnosis subsystem
It is updated with forecast model, specifically include following steps:
Step 4.1, before train operation, high in the clouds fault diagnosis subsystem to vehicle-mounted fault diagnosis subsystem real-time therefore
Fault diagnosis and fault prediction model in barrier diagnostic module is tested, judge this model be whether fault diagnosis and fault prediction effect
Excellent model;If this model is not the optimum model of fault diagnosis and fault prediction effect, execution step 4.2 is examined to vehicle mounted failure
Fault diagnosis and fault prediction model in the real-time fault diagnosis module of disconnected subsystem is updated, if this model be fault diagnosis with
The optimum model of prediction effect, then execution step 5;
Step 4.2, judge whether to need the fault diagnosis and fault prediction model updating in real-time fault diagnosis module overall
This model can be made to reach optimum, if it is not, i.e. only need to be to the correlation of the fault diagnosis and fault prediction model in real-time fault diagnosis module
Parameter is updated just making this model reach optimum, then execution step 4.2.1, if so, then execution step 4.2.2;
Fault diagnosis and forecast in step 4.2.1, the real-time fault diagnosis module of train-installed fault diagnosis subsystem
The model model optimum compared to the diagnosis and prediction effect in the fault diagnosis and fault prediction module of high in the clouds fault diagnosis subsystem,
Only partial parameters need to be changed, then change the relevant parameter of model;
Fault diagnosis and fault prediction in step 4.2.2, the real-time fault diagnosis module of train-installed fault diagnosis subsystem
The model model optimum compared to diagnosis and prediction effect in the fault diagnosis and fault prediction module of high in the clouds fault diagnosis subsystem, needs
The optimum model of effect is integrally downloaded to vehicle-mounted fault diagnosis subsystem, if the hardware of vehicle-mounted fault diagnosis subsystem calculates
Resource can effectively support the computing of the optimum model of the fault diagnosis and fault prediction effect constructed by the fault diagnosis subsystem of high in the clouds,
Then execution step 4.2.2.1;If the hardware computing resource of vehicle-mounted fault diagnosis subsystem cannot support high in the clouds fault diagnosis subsystem
The computing of the constructed up-to-date fault diagnosis and fault prediction model of system, then execution step 4.2.2.2;
Step 4.2.2.1, the optimum fault diagnosis and fault prediction model constructed by the fault diagnosis subsystem of high in the clouds is complete
Model is directly downloaded in train-installed fault diagnosis subsystem;
Step 4.2.2.2, the up-to-date fault diagnosis and fault prediction model to the complexity constructed by the fault diagnosis subsystem of high in the clouds
Fault diagnosis model carries out yojan, builds the fault diagnosis and fault prediction model after yojan, and downloads it to train-installed fault
In diagnostic subsystem;
Step 5, vehicle-mounted fault diagnosis subsystem carry out real-time fault diagnosis to train, specifically include following steps:
Step 5.1, vehicle carried data collecting module are by the real-time Data Transmission being gathered to real-time fault diagnosis module and cloud
Diagnostic module;
Step 5.2, real-time fault diagnosis module carry out real time fail using the data of Real-time Collection to the train in travelling
Diagnosis, fault diagnosis result is transferred to cloud diagnostic module;
Step 5.3, cloud diagnostic module are using real time data by calling the fault that high in the clouds fault diagnosis subsystem is provided
Diagnosis and prediction service interface carries out fault diagnosis to train, and concrete grammar is:
Step 5.3.1, high in the clouds data acquisition module are carried out by the real time data that network uploads in train travelling process
Collection;
Step 5.3.2, using ETL instrument, the real time data of collection in step 5.3.1 is carried out by data cleansing data turns
After changing operation, store corresponding data-storage system;
Step 5.3.3, high in the clouds fault diagnosis subsystem respond remote fault diagnosis service request, and concrete response process is:
Step 5.3.3.1, high in the clouds fault diagnosis subsystem fault diagnosis and fault prediction model clear to carrying out in step 5.3.2
Train operating data after washing and changing is analyzed and fault diagnosis;
Step 5.3.3.2, fault diagnosis result is returned to the cloud diagnostic module of vehicle-mounted fault diagnosis subsystem;
Step 5.4, cloud diagnostic module by by call the diagnostic result that high in the clouds fault diagnosis and fault prediction service formed with
The diagnostic result that real-time fault diagnosis module in vehicle-mounted fault diagnosis subsystem in step 5.2 is formed is compared, and goes forward side by side
Row prompting;If Comparative result finds that the real-time fault diagnosis module in vehicle-mounted fault diagnosis subsystem is failed to report for significant trouble
Or misrepresent deliberately, then execution step 5.4.1;If Comparative result has not found to fail to report or misrepresent deliberately, directly execution step 5.4.4;
Step 5.4.1, vehicle-mounted fault diagnosis subsystem pass through the lifting of cloud diagnostic module and call high in the clouds fault diagnosis and fault prediction
Service carries out fault diagnosis and fault prediction and the priority with high in the clouds communication;
Step 5.4.2, vehicle-mounted fault diagnosis subsystem pass through the raising of cloud diagnostic module and call high in the clouds fault diagnosis and fault prediction
Service carries out fault diagnosis and fault prediction and the shared bandwidth that communicates with high in the clouds, preferential transmission diagnostic instruction data;
Step 5.4.3, cloud diagnostic module call the service that high in the clouds fault diagnosis subsystem is provided quickly to be assisted and examine
Disconnected;
Fault diagnosis result is pointed out by step 5.4.4, cloud diagnostic module in time;
The historical data of this train is uploaded to high in the clouds data acquisition module after terminating by step 6, train operation.
As shown from the above technical solution, the beneficial effects of the present invention is:The present invention provides one kind to be based on vehicle-mounted and high in the clouds
Train fault diagnostic system and method, using cloud service, train is monitored in the process of moving, high in the clouds data is not simultaneously
Disconnected renewal, fault diagnosis and fault prediction model detail is more and more perfect, and precision improves constantly, the single real time fail of performance beyond tradition
Diagnostic module controls, and meets the highly reliable in the process of moving high-precision requirement of train-installed fault diagnosis subsystem, improves
Train security in the process of moving.Concrete effect is:Train-installed fault diagnosis subsystem is examined with high in the clouds fault
Disconnected subsystem combines, the dual high reliability that ensure that train-installed fault diagnosis subsystem;Vehicle-mounted fault diagnosis subsystem will
Data is deposited in the data-storage system of high in the clouds, constructs unified fault data management system, realizes the height to fault data
Effect management;The monitoring of fault diagnosis effect is carried out it is ensured that vehicle-mounted to the train in travelling by the cloud diagnostic module on train
The high reliability of real-time fault diagnosis;The fault diagnosis and fault prediction mould constructed by service data that high in the clouds is updated using continuous accumulation
Type constantly improve, precision improves constantly, the single vehicle-mounted real-time fault diagnosis system of fault diagnosis and fault prediction performance beyond tradition.
Brief description
Fig. 1 be provided in an embodiment of the present invention a kind of based on vehicle-mounted and high in the clouds train fault diagnostic system structured flowchart;
Fig. 2 is a kind of feature knot based on the vehicle-mounted train fault diagnostic system with high in the clouds provided in an embodiment of the present invention
Composition;
Fig. 3 is a kind of overall procedure based on the vehicle-mounted train fault diagnostic method with high in the clouds provided in an embodiment of the present invention
Figure;
Fig. 4 is that a kind of train fault diagnostic method based on vehicle-mounted and high in the clouds provided in an embodiment of the present invention is driven in train
Front flow chart;
Fig. 5 is a kind of train fault diagnostic method based on vehicle-mounted and high in the clouds provided in an embodiment of the present invention in train driving
During flow chart.
Specific embodiment
With reference to the accompanying drawings and examples, the specific embodiment of the present invention is described in further detail.Hereinafter implement
Example is used for the present invention is described, but is not limited to the scope of the present invention.
The present embodiment taking axle temperature fault diagnosis as a example, a kind of based on vehicle-mounted and high in the clouds train fault diagnostic system, such as Fig. 1
Shown, including vehicle-mounted fault diagnosis subsystem and high in the clouds fault diagnosis subsystem.
Vehicle-mounted fault diagnosis subsystem includes vehicle carried data collecting module, real-time fault diagnosis module and cloud diagnostic module.
Vehicle carried data collecting module is used for the service data of train being acquired, including some for gathering different pieces of information
Sensor.
Real-time fault diagnosis module is used for carrying out real-time fault diagnosis and prediction to train in train travelling process.
Cloud diagnostic module is auxiliary for calling the fault diagnosis service that high in the clouds fault diagnosis subsystem is provided that train is carried out
Help formula fault diagnosis, that is, on the one hand to the diagnostic result of vehicle-mounted real-time fault diagnosis module and high in the clouds fault diagnosis subsystem therefore
Barrier diagnostic result is contrasted, and comparing result is shown;On the other hand when comparing result shows that described vehicle mounted failure is examined
When failing to report or misrepresenting deliberately of significant trouble in disconnected subsystem, by setting data transmission priority, preferential transmission diagnostic instruction and
Data, carries out quick auxiliary diagnosis using cloud diagnostic module.
High in the clouds fault diagnosis subsystem includes high in the clouds data acquisition module, data memory module, data processing module, fault
Diagnosis and prediction module data visualization model.
High in the clouds data acquisition module, is on the one hand used for gathering in train travelling process and is transported by the train that train network is transmitted
The real time data of row, is on the other hand used for gathering the historical data that train operation terminates rear train operation.
Data memory module be used for data that high in the clouds data acquisition module is gathered carry out data cleansing, data conversion and
Data compression, and data is stored in corresponding data storage system by different types of data;Data cleansing include data fill a vacancy, data
Replace data format specification;Data conversion includes data fractionation, data sorting, the checking of data deduplication data;Data pressure
Contract for compress, to save memory space.
Data processing module includes Computational frame submodule, inquiry submodule, data statistics submodule and algorithms library submodule
Block;Computational frame submodule includes real-time streaming Computational frame and non real-time batch processing Computational frame, real-time streaming Computational frame
For the calculating of real-time stream, non real-time batch processing Computational frame is used for calculating non real-time historical data;Inquiry submodule is used
In inquiry train operation in real time and historical data;Data statistics submodule is used for carrying out Statistics Division to the historical data of train operation
Reason;Algorithms library submodule is used for managing the algorithm of data processing.
Fault diagnosis and fault prediction module include model setting up submodule, model evaluation submodule, model management submodule and
Fault diagnosis and fault prediction Attendant sub-module;Model setting up submodule be used for using train history data build fault diagnosis with
Forecast model;Model evaluation submodule is used for the diagnosis and prediction effect of fault diagnosis and fault prediction model is estimated;Model
Management submodule is used for all historical failure diagnosis and prediction models constructed by administrative model setting up submodule;Fault diagnosis with
Prediction Attendant sub-module is used for providing and monitor fault diagnosis and fault prediction cloud service.
Data visualization module is used for showing the result that Various types of data processes operation, including Query Result, statistics, meter
Calculate result and fault modeling and predict the outcome.
A kind of functional structure such as Fig. 2 institute based on the vehicle-mounted train fault diagnostic system with high in the clouds that the present embodiment provides
Show.
Using a kind of above-mentioned side that based on vehicle-mounted and high in the clouds train fault diagnostic system, axle temperature is carried out with fault diagnosis
Method, as shown in figure 3, concrete grammar is as follows.
Axle temperature in step 1, the vehicle carried data collecting module of a certain row high ferro train and other historical datas pass through network
It is uploaded to high in the clouds data acquisition module, high in the clouds data acquisition module is acquired to this train data, and these historical datas include
The axle temperature of train operation, train sensing data, train operation status information, train number, working line, driver's numbering, letter
Breath classification coding, train operation daily record etc..
Step 2, the initial data uploading in the data acquisition module of high in the clouds is carried out with data cleansing and conversion after, then carry out
Data storage, specifically includes following steps:
Step 2.1, using ETL instrument Kettle (a kind of ETL instrument increased income) to uploading to high in the clouds data acquisition module
In initial data carry out that data is filled a vacancy, data is replaced the data cleansing of data format specification and processed, and data is carried out
Data fractionation, data sorting, the data conversion treatment of data deduplication data checking;
Step 2.2, by cleaning, conversion after the corresponding data-storage system of data Cun Chudao, specially:
Step 2.2.1, structural data is saved in database, specifically includes:By train axle temperature data, mode of operation number
According to waiting storage Dao memory database Redis (Key-Value database) in, data trnascription write local file is backed up,
Store in non-relational database HBase after data in Redis is compressed using lossless compression algorithm;High speed is arranged
The train number of car, working line, driver's numbering, information category coding etc. store in relevant database Mysql;
Step 2.2.2, unstructured data is saved in file system, specially by the Operation Log literary composition of train operator
It is distributed that the unstructured datas such as part, fault message information store HDFS (Hadoop Distributed File System)
In file management system.
Step 3, using the history data of train, high in the clouds original fault diagnosis and fault prediction model is estimated, and
Build new fault diagnosis and fault prediction model, specifically include following steps:
Step 3.1, model evaluation submodule are newly uploaded to the axle temperature historical data of high in the clouds data acquisition module using train
Fault diagnosis subsystem original fault diagnosis and fault prediction model in high in the clouds is estimated, if assessment result determines and having wrong report or leak
Report situation, then execution step 3.2, otherwise direct execution step 5;Specifically appraisal procedure is:
Step 3.1.1, model evaluation submodule obtain high ferro train axle temperature historical data from database, and normalization is (a kind of
Simplify calculate mode, will have the expression formula of dimension, through conversion, turn to nondimensional expression formula, become scalar) process after structure
Build the test set sample of fault diagnosis and fault prediction model;
Step 3.1.2, the T of calculating test set sample data2(Hotelling T2Statistic) and square prediction error
(Square Predicted Error, SPE) statistic and its corresponding control limit (i.e. the restriction scope of statistical indicator), use
Test set sample data is estimated to original fault diagnosis and fault prediction model and verifies, if having wrong report or failing to report situation, needs
Fault diagnosis subsystem original fault diagnosis and fault prediction model in high in the clouds is updated, execution step 3.2, otherwise not update
Model, direct execution step 5;
Step 3.2, newly it is uploaded to the axle temperature historical data of high in the clouds data acquisition module using train and high in the clouds data is deposited
In storage system, original axle temperature historical data sets up new fault diagnosis and fault prediction model, and this model specification is optimal models,
And this model is stored model management submodule;In the present embodiment, the method setting up new fault diagnosis and fault prediction model is:
It is directed to high ferro train axle temperature using PCA (Principal Component Analysis, principal component analysis) method
Historical data sets up new Fault diagnosis and forecast model, obtains high ferro train axle temperature historical data from database, at normalization
Build training set and the test set sample of model after reason, model is trained and verifies.
Step 3.3, structure supply vehicle-mounted fault diagnosis subsystem remote access high in the clouds fault diagnosis service interface, execute step
Rapid 4.
Before step 4, train operation, to the axle temperature fault in the real-time fault diagnosis module of vehicle-mounted fault diagnosis subsystem
Diagnosis and prediction model is updated, and specifically includes following steps:
Step 4.1, before train operation, high in the clouds fault diagnosis subsystem to vehicle-mounted fault diagnosis subsystem real-time therefore
Axle temperature fault diagnosis and fault prediction model in barrier diagnostic module is tested, and judges whether this model is fault diagnosis and fault prediction effect
The optimum model of fruit;If this model is not the optimum model of fault diagnosis and fault prediction effect, execution step 4.2, to vehicle-mounted event
Axle temperature fault diagnosis and fault prediction model in the real-time fault diagnosis module of barrier diagnostic subsystem is updated, if this model is event
The optimum model of barrier diagnosis and prediction effect, then execution step 5;
Step 4.2, judge whether to need the axle temperature fault diagnosis and fault prediction model updating in real-time fault diagnosis module whole
Body just can make this model reach optimum, if it is not, i.e. only need to be to the axle temperature fault diagnosis and fault prediction mould in real-time fault diagnosis module
The relevant parameter of type is updated just making this model reach optimum, then execution step 4.2.1, if so, then execution step
4.2.2;
Axle temperature fault diagnosis in step 4.2.1, the real-time fault diagnosis module of train-installed fault diagnosis subsystem and
Forecast model is compared to the diagnosis and prediction effect in the axle temperature fault diagnosis and fault prediction module of high in the clouds fault diagnosis subsystem
Excellent model, only need to change partial parameters, then the axle temperature fault diagnosis and fault prediction model in change vehicle-mounted fault diagnosis subsystem
The relevant parameter T of algorithm2Control limit with SPE statistic;
Axle temperature fault diagnosis in step 4.2.2, the real-time fault diagnosis module of train-installed fault diagnosis subsystem with
Forecast model is optimum compared to fault diagnosis and fault prediction effect in the fault diagnosis and fault prediction module of high in the clouds fault diagnosis subsystem
Axle temperature fault diagnosis and fault prediction model, need for model optimum for effect integrally to download to vehicle-mounted fault diagnosis subsystem;If
The hardware computing resource of vehicle-mounted fault diagnosis subsystem can effectively support the axle temperature event constructed by the fault diagnosis subsystem of high in the clouds
The computing of the optimum model of barrier diagnosis and prediction effect, then execution step 4.2.2.1;If the hardware of vehicle-mounted fault diagnosis subsystem
Computing resource cannot support the computing of the up-to-date axle temperature fault diagnosis and fault prediction model constructed by the fault diagnosis subsystem of high in the clouds,
Then execution step 4.2.2.2;
Step 4.2.2.1, by the axle temperature fault diagnosis and fault prediction model of the optimum constructed by the fault diagnosis subsystem of high in the clouds
Complete model with Docker (Docker be an engine increased income in that context it may be convenient to create a light weight for any application
Level, transplantable, self-centered container) form be directly downloaded to the real time fail of train-installed fault diagnosis subsystem
In diagnostic module;
Step 4.2.2.2, the up-to-date axle temperature fault diagnosis and fault prediction to the complexity constructed by the fault diagnosis subsystem of high in the clouds
Symbolic fault diagnosis model carries out yojan, builds the axle temperature fault diagnosis and fault prediction model after yojan, and by the axle after this yojan
Warm fault diagnosis and fault prediction model downloads to the real-time fault diagnosis of train-installed fault diagnosis subsystem in the form of Docker
In module.
Above-mentioned step is the renewal weight of the fault diagnosis and fault prediction model being carried out according to historical data before train is driven
Build process, its flow process is as shown in Figure 4.
Real-time fault diagnosis module in step 5, train-installed fault diagnosis subsystem utilizes train shaft temperature sensor institute
The real-time axle temperature data of collection carries out real-time fault diagnosis to the train in travelling, as shown in figure 5, specifically including following steps:
Step 5.1, vehicle carried data collecting module are by the axle temperature being gathered real-time Data Transmission to real-time fault diagnosis module
With cloud diagnostic module;
Step 5.2, real-time fault diagnosis module are carried out to the train in travelling using the axle temperature data of Real-time Collection in real time
Axle temperature fault diagnosis, fault diagnosis result is transferred to cloud diagnostic module;
Step 5.3, cloud diagnostic module by call the axle temperature fault diagnosis that high in the clouds fault diagnosis subsystem is provided with pre-
API (Application Programming Interface, application programming interface) service surveying service is real-time to train
Axle temperature data carries out fault diagnosis, but this process has the regular hour and postpones, and concrete grammar is:
Step 5.3.1, high in the clouds data acquisition module in train travelling process pass through GSM-R (GSM-R digital mobile communication
System, is based on common wireless communication system GSM platform, the digital wireless communication system developing exclusively for meeting railway applications
System) network upload real-time axle temperature data be acquired;
Step 5.3.2, using ETL instrument in step 5.3.1 collection real-time axle temperature data carry out data cleansing (include
Data is filled a vacancy, data replace data format specification) data conversion (include data fractionation, data sorting, data deduplication and
Data verification) operation after, store corresponding data-storage system;
Step 5.3.3, high in the clouds fault diagnosis subsystem respond remote fault diagnosis service request, and concrete response process is:
Step 5.3.3.1, the axle temperature fault diagnosis and fault prediction model of high in the clouds fault diagnosis subsystem enter in step 5.3.2
Train operation axle temperature data after row cleaning and conversion is analyzed and fault diagnosis;
Step 5.3.3.2, axle temperature fault diagnosis result is returned to the cloud diagnostic module of vehicle-mounted fault diagnosis subsystem;
Step 5.4, cloud diagnostic module will be examined by the axle temperature fault calling high in the clouds fault diagnosis and fault prediction service to be formed
The axle temperature fault diagnosis knot that real-time fault diagnosis module in vehicle-mounted fault diagnosis subsystem in disconnected result and step 5.2 is formed
Fruit is compared, and is pointed out;If Comparative result finds the real-time fault diagnosis module pin in vehicle-mounted fault diagnosis subsystem
Great axle temperature fault is failed to report or misrepresents deliberately, then execution step 5.4.1;If Comparative result has not found to fail to report or misrepresent deliberately,
Directly execution step 5.4.4;
Step 5.4.1, vehicle-mounted fault diagnosis subsystem pass through the lifting of cloud diagnostic module and call high in the clouds fault diagnosis and fault prediction
Service carries out fault diagnosis and fault prediction and the priority with high in the clouds communication;
Step 5.4.2, vehicle-mounted fault diagnosis subsystem pass through the raising of cloud diagnostic module and call high in the clouds fault diagnosis and fault prediction
Service carries out fault diagnosis and fault prediction and the shared bandwidth that communicates with high in the clouds, preferential transmission diagnostic instruction data;
Step 5.4.3, cloud diagnostic module call the service that high in the clouds fault diagnosis subsystem is provided quickly to be assisted and examine
Disconnected;
Fault diagnosis result is pointed out by step 5.4.4, cloud diagnostic module in time.
The historical data of this train is uploaded to high in the clouds data acquisition module after terminating by step 6, train operation.
This failure diagnostic process is got back after terminating new service data, returns again to execution step 1.Train operating data
Constantly update, the data of renewal is used for optimizing or rebuilding fault diagnosis and fault prediction model, it is right that the model optimizing or rebuilding is used for again
Train carries out fault diagnosis, and with the continuous operation of system, the flow process of the method circulates execution always.
Due to the hardware resource limitation of train-installed fault diagnosis subsystem, high ferro train produces in the process of moving
Data volume is big, and the operational capability of real-time fault diagnosis module and model accuracy are limited, add that computation model can not be according to train
Ruuning situation is improved and is optimized, and leads to train-installed fault diagnosis subsystem reliability not high it is impossible to meet bullet train
The highly reliable monitoring requirement of high accuracy under complex situations.What the present invention provided the train fault diagnosis based on vehicle-mounted and high in the clouds
A kind of system and method, there is provided vehicle-mounted high in the clouds framework, the fault in the train-installed fault diagnosis subsystem of effective guarantee
The highly reliable high-precision problem of diagnosis and prediction model, its distinctive cloud service can be supervised in the process of moving to train
Control, high in the clouds data continuous renewal simultaneously, model detail is more and more perfect, and precision improves constantly, and performance beyond tradition is single in real time
Fault diagnosis module controls, and improves train security in the process of moving.
Finally it should be noted that:Above example only in order to technical scheme to be described, is not intended to limit;Although
With reference to the foregoing embodiments the present invention is described in detail, it will be understood by those within the art that:It still may be used
To modify to the technical scheme described in previous embodiment, or wherein some or all of technical characteristic is equal to
Replace;And these modifications or replacement, do not make the essence of appropriate technical solution depart from the model that the claims in the present invention are limited
Enclose.
Claims (2)
1. a kind of train fault diagnostic system based on vehicle-mounted and high in the clouds it is characterised in that:This system includes vehicle-mounted fault diagnosis
Subsystem and high in the clouds fault diagnosis subsystem;
Described vehicle-mounted fault diagnosis subsystem includes vehicle carried data collecting module, real-time fault diagnosis module and cloud diagnostic module;
Described high in the clouds fault diagnosis subsystem includes high in the clouds data acquisition module, data memory module, data processing module, fault diagnosis
With prediction module data visualization model;
Described vehicle carried data collecting module is used for the service data of train is acquired;
Described real-time fault diagnosis module is used for carrying out real-time fault diagnosis and prediction to train in train travelling process;
Described cloud diagnostic module is auxiliary for calling the fault diagnosis service that high in the clouds fault diagnosis subsystem is provided that train is carried out
Help formula fault diagnosis, that is, on the one hand to the diagnostic result of vehicle-mounted real-time fault diagnosis module and high in the clouds fault diagnosis subsystem therefore
Barrier diagnostic result is contrasted, and comparing result is shown;On the other hand when comparing result shows that described vehicle mounted failure is examined
When failing to report or misrepresenting deliberately of significant trouble in disconnected subsystem, by setting data transmission priority, preferential transmission diagnostic instruction and
Data, carries out quick auxiliary diagnosis using cloud diagnostic module;
Described high in the clouds data acquisition module, is on the one hand used for gathering in train travelling process and is transported by the train that train network is transmitted
The real time data of row, is on the other hand used for gathering the historical data that train operation terminates rear train operation;
Described data memory module be used for data that high in the clouds data acquisition module is gathered carry out data cleansing, data conversion and
Data compression, and data is stored in corresponding data storage system by different types of data;Described data cleansing include data fill a vacancy,
Data replaces data format specification;Described data conversion includes data fractionation, data sorting, data deduplication data are tested
Card;Described data compression is used for compress, to save memory space;
Described data processing module includes Computational frame submodule, inquiry submodule, data statistics submodule and algorithms library submodule
Block;
Described Computational frame submodule includes real-time streaming Computational frame and non real-time batch processing Computational frame, described real-time streaming
Computational frame is used for the calculating of real-time stream, and described non real-time batch processing Computational frame is used for calculating non real-time historical data;
Described inquiry submodule is used for inquiring about train operation in real time and historical data;
Described data statistics submodule is used for carrying out statistical disposition to the historical data of train operation;
Described algorithms library submodule is used for managing the algorithm of data processing;
Described fault diagnosis and fault prediction module include model setting up submodule, model evaluation submodule, model management submodule and
Fault diagnosis and fault prediction Attendant sub-module;
Described model setting up submodule is used for building fault diagnosis and fault prediction model using train history data;
Described model evaluation submodule is used for the diagnosis and prediction effect of fault diagnosis and fault prediction model is estimated;
Described model management submodule is used for all historical failure diagnosis and prediction moulds constructed by administrative model setting up submodule
Type;
Described fault diagnosis and fault prediction Attendant sub-module is used for providing and monitor fault diagnosis and fault prediction cloud service;
Described data visualization module is used for showing the result that Various types of data processes operation, including Query Result, statistics, meter
Calculate result and fault diagnosis result.
2. a kind of based on vehicle-mounted and high in the clouds train fault diagnostic method, by the one kind described in claim 1 be based on vehicle-mounted and
The train fault realizing of the diagnosis system in high in the clouds it is characterised in that:The method comprises the following steps that:
Historical data in step 1, vehicle carried data collecting module is uploaded to high in the clouds data acquisition module, high in the clouds data by network
Acquisition module is acquired to train data;
Step 2, the initial data uploading in the data acquisition module of high in the clouds is carried out with data cleansing and conversion after, then carry out data
Storage, specifically includes following steps:
Step 2.1, using ETL (Extract-Transform-Load) instrument former in the data acquisition module of high in the clouds to uploading to
Beginning data carry out data fill a vacancy, data replace data format specification data cleansing operation, and data split, data row
Sequence, the data transformation operations of data deduplication data checking;
Step 2.2, by cleaning, conversion after the corresponding data-storage system of data Cun Chudao, specially:
Step 2.2.1, structural data is saved in database;
Step 2.2.2, unstructured data is saved in file system;
Step 3, using the history data of train, high in the clouds original fault diagnosis and fault prediction model is estimated, and builds
New fault diagnosis and fault prediction model, specifically includes following steps:
Step 3.1, model evaluation submodule are newly uploaded to the historical data of high in the clouds data acquisition module to high in the clouds event using train
Barrier diagnostic subsystem original fault diagnosis and fault prediction model is estimated, if having wrong report or failing to report situation, execution step
3.2, otherwise direct execution step 5;
In step 3.2, the historical data being newly uploaded to high in the clouds data acquisition module using train and high in the clouds data-storage system
Original historical data sets up new fault diagnosis and fault prediction model, this model specification is optimal models, and this model is deposited
Store up model management submodule;
Step 3.3, structure supply vehicle-mounted fault diagnosis subsystem remote access high in the clouds fault diagnosis service interface, execution step 4;
Before step 4, train operation, to the fault diagnosis in the real-time fault diagnosis module of vehicle-mounted fault diagnosis subsystem and in advance
Survey model to be updated, specifically include following steps:
Step 4.1, before train operation, high in the clouds fault diagnosis subsystem is examined to the real time fail of vehicle-mounted fault diagnosis subsystem
Fault diagnosis and fault prediction model in disconnected module is tested, and judges whether this model is that fault diagnosis and fault prediction effect is optimum
Model;If this model is not the optimum model of fault diagnosis and fault prediction effect, execution step 4.2, to vehicle-mounted fault diagnosis
Fault diagnosis and fault prediction model in the real-time fault diagnosis module of system is updated, if this model is fault diagnosis and fault prediction
The optimum model of effect, then execution step 5;
Step 4.2, judge whether to need the fault diagnosis and fault prediction model updating in real-time fault diagnosis module integrally just can make
This model reaches optimum, if it is not, i.e. only need to be to the relevant parameter of the fault diagnosis and fault prediction model in real-time fault diagnosis module
It is updated just making this model reach optimum, then execution step 4.2.1, if so, then execution step 4.2.2;
Fault diagnosis and forecast model in step 4.2.1, the real-time fault diagnosis module of train-installed fault diagnosis subsystem
The model optimum compared to the diagnosis and prediction effect in the fault diagnosis and fault prediction module of high in the clouds fault diagnosis subsystem, only needs
Change partial parameters, then change the relevant parameter of model;
Fault diagnosis and fault prediction model in step 4.2.2, the real-time fault diagnosis module of train-installed fault diagnosis subsystem
The model optimum compared to diagnosis and prediction effect in the fault diagnosis and fault prediction module of high in the clouds fault diagnosis subsystem, need by
The optimum model of effect integrally downloads to vehicle-mounted fault diagnosis subsystem, if the hardware computing resource of vehicle-mounted fault diagnosis subsystem
The computing of the optimum model of the fault diagnosis and fault prediction effect constructed by the fault diagnosis subsystem of high in the clouds can effectively be supported, then hold
Row step 4.2.2.1;If the hardware computing resource of vehicle-mounted fault diagnosis subsystem cannot support high in the clouds fault diagnosis subsystem institute
The computing of the up-to-date fault diagnosis and fault prediction model building, then execution step 4.2.2.2;
Step 4.2.2.1, by the complete model of the optimum fault diagnosis and fault prediction model constructed by the fault diagnosis subsystem of high in the clouds
It is directly downloaded in train-installed fault diagnosis subsystem;
Step 4.2.2.2, the up-to-date fault diagnosis and fault prediction model fault to the complexity constructed by the fault diagnosis subsystem of high in the clouds
Diagnostic model carries out yojan, builds the fault diagnosis and fault prediction model after yojan, and downloads it to train-installed fault diagnosis
In subsystem;
Step 5, vehicle-mounted fault diagnosis subsystem carry out real-time fault diagnosis to train, specifically include following steps:
The real-time Data Transmission being gathered is diagnosed by step 5.1, vehicle carried data collecting module to real-time fault diagnosis module and cloud
Module;
Step 5.2, real-time fault diagnosis module carry out real-time fault diagnosis using the data of Real-time Collection to the train in travelling,
Fault diagnosis result is transferred to cloud diagnostic module;
Step 5.3, cloud diagnostic module are using real time data by calling the fault diagnosis that high in the clouds fault diagnosis subsystem is provided
With prediction service interface, fault diagnosis is carried out to train, concrete grammar is:
Step 5.3.1, high in the clouds data acquisition module are acquired by the real time data that network uploads in train travelling process;
Step 5.3.2, using ETL instrument in step 5.3.1 collection real time data carry out data cleansing data conversion behaviour
After work, store corresponding data-storage system;
Step 5.3.3, high in the clouds fault diagnosis subsystem respond remote fault diagnosis service request, and concrete response process is:
Step 5.3.3.1, the fault diagnosis and fault prediction model of high in the clouds fault diagnosis subsystem to being carried out in step 5.3.2 and
Train operating data after conversion is analyzed and fault diagnosis;
Step 5.3.3.2, fault diagnosis result is returned to the cloud diagnostic module of vehicle-mounted fault diagnosis subsystem;
Step 5.4, cloud diagnostic module are by by calling the diagnostic result that high in the clouds fault diagnosis and fault prediction service formed and step
The diagnostic result that real-time fault diagnosis module in vehicle-mounted fault diagnosis subsystem in 5.2 is formed is compared, and is carried
Show;If Comparative result finds that the real-time fault diagnosis module in vehicle-mounted fault diagnosis subsystem is failed to report for significant trouble or wrong
Report, then execution step 5.4.1;If Comparative result has not found to fail to report or misrepresent deliberately, directly execution step 5.4.4;
Step 5.4.1, vehicle-mounted fault diagnosis subsystem pass through the lifting of cloud diagnostic module and call high in the clouds fault diagnosis and fault prediction service
Carry out fault diagnosis and fault prediction and the priority with high in the clouds communication;
Step 5.4.2, vehicle-mounted fault diagnosis subsystem pass through the raising of cloud diagnostic module and call high in the clouds fault diagnosis and fault prediction service
Carry out fault diagnosis and fault prediction and the shared bandwidth that communicates with high in the clouds, preferential transmission diagnostic instruction data;
Step 5.4.3, cloud diagnostic module call the service that high in the clouds fault diagnosis subsystem is provided to carry out quick auxiliary diagnosis;
Fault diagnosis result is pointed out by step 5.4.4, cloud diagnostic module in time;
The historical data of this train is uploaded to high in the clouds data acquisition module after terminating by step 6, train operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611154208.4A CN106406296B (en) | 2016-12-14 | 2016-12-14 | It is a kind of based on vehicle-mounted and cloud train fault diagnostic system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611154208.4A CN106406296B (en) | 2016-12-14 | 2016-12-14 | It is a kind of based on vehicle-mounted and cloud train fault diagnostic system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106406296A true CN106406296A (en) | 2017-02-15 |
CN106406296B CN106406296B (en) | 2019-04-23 |
Family
ID=58087610
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611154208.4A Active CN106406296B (en) | 2016-12-14 | 2016-12-14 | It is a kind of based on vehicle-mounted and cloud train fault diagnostic system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106406296B (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106953847A (en) * | 2017-02-27 | 2017-07-14 | 江苏徐工信息技术股份有限公司 | A kind of cross-platform real-time processing method of big data based on thrift |
CN106970607A (en) * | 2017-03-31 | 2017-07-21 | 株洲中车时代电气股份有限公司 | The method of testing and system of a kind of converter control system |
CN107016057A (en) * | 2017-02-28 | 2017-08-04 | 北京铁路局 | Row control vehicle-mounted ATP equipment integral intelligent O&M method and system |
CN107025274A (en) * | 2017-03-21 | 2017-08-08 | 华中科技大学 | Equipment health status intelligent perception system and method based on Hadoop |
CN107589695A (en) * | 2017-09-12 | 2018-01-16 | 中国中车股份有限公司 | A kind of train groups prognostic and health management system |
CN107679159A (en) * | 2017-09-28 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Generation method, device, server and the storage medium that fault diagnosis class problem replies |
CN107697107A (en) * | 2017-09-12 | 2018-02-16 | 中国中车股份有限公司 | A kind of train groups prognostic and health management ground intelligent processing system and method |
CN108038214A (en) * | 2017-12-21 | 2018-05-15 | 重庆脉实智能制造有限公司 | The collection of railway Overhaul Yard section device data, storage, the method and system of analysis and application |
CN109141898A (en) * | 2018-09-13 | 2019-01-04 | 湖北谊立舜达动力科技有限公司 | A kind of Diagnosis of Diesel Motor system based on Internet of Things |
CN109696316A (en) * | 2017-10-20 | 2019-04-30 | 株洲中车时代电气股份有限公司 | A kind of train remote supervision system |
CN109765448A (en) * | 2019-02-01 | 2019-05-17 | 唐智科技湖南发展有限公司 | A kind of distributed type fault diagnosis method, apparatus and system |
CN109915218A (en) * | 2019-03-07 | 2019-06-21 | 东方电气自动控制工程有限公司 | A kind of electro-hydraulic converting member fault diagnosis system of DEH system |
CN109917772A (en) * | 2017-12-13 | 2019-06-21 | 北京航空航天大学 | A kind of PHM rapid prototyping system of remote online assessment equipment state |
CN109948169A (en) * | 2017-12-20 | 2019-06-28 | 中国中车股份有限公司 | A kind of railway freight-car prognostic and health management system |
CN110018425A (en) * | 2019-04-10 | 2019-07-16 | 北京理工大学 | A kind of power battery fault diagnosis method and system |
CN110163225A (en) * | 2018-02-11 | 2019-08-23 | 顺丰科技有限公司 | It is a kind of that package detection and recognition methods, apparatus and system are mixed based on cloud platform |
CN110361207A (en) * | 2019-07-25 | 2019-10-22 | 中南大学 | A kind of intelligence train EEF bogie presence forecasting system and its method |
CN110428066A (en) * | 2019-07-25 | 2019-11-08 | 中南大学 | It is a kind of intelligence Electric device presence assessment with operation platform and its method |
CN110874093A (en) * | 2018-09-03 | 2020-03-10 | 上汽通用汽车有限公司 | Method and system for predicting life of brake lining of vehicle and storage medium |
CN111133289A (en) * | 2017-09-28 | 2020-05-08 | 株式会社电装 | Vehicle diagnostic device, vehicle diagnostic system, and vehicle diagnostic program |
CN111352116A (en) * | 2020-03-31 | 2020-06-30 | 湖北阿桑奇汽车电子科技有限公司 | Ultrasonic obstacle positioning simulation device for vehicle |
CN111516727A (en) * | 2020-05-12 | 2020-08-11 | 上海数深智能科技有限公司 | High-speed rail defect abnormity intelligent diagnosis and detection system and method based on double vibration measurement sensors |
CN111830927A (en) * | 2019-04-23 | 2020-10-27 | 中车大连电力牵引研发中心有限公司 | Vehicle fault monitoring method and device and vehicle-mounted diagnosis equipment |
CN112307335A (en) * | 2020-10-29 | 2021-02-02 | 中国第一汽车股份有限公司 | Vehicle service information pushing method, device and equipment and vehicle |
CN113085952A (en) * | 2020-01-08 | 2021-07-09 | 株洲中车时代电气股份有限公司 | Train monitoring system |
CN113204227A (en) * | 2021-04-26 | 2021-08-03 | 江苏徐工工程机械研究院有限公司 | Cloud collaborative fault diagnosis system and method for layered modular engineering machinery |
US11400952B2 (en) | 2020-12-24 | 2022-08-02 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for automated driving |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102529903A (en) * | 2010-12-31 | 2012-07-04 | 上海博泰悦臻电子设备制造有限公司 | Comprehensive vehicle failure detecting system |
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 |
CN104133467A (en) * | 2014-07-30 | 2014-11-05 | 浪潮集团有限公司 | OBDS long-distance fault diagnosis and recovery system based on cloud computation |
CN104185309A (en) * | 2014-08-12 | 2014-12-03 | 深圳市元征科技股份有限公司 | On-board wireless local area network equipment |
US20150242198A1 (en) * | 2014-02-25 | 2015-08-27 | Ford Global Technologies, Llc | Silent in-vehicle software updates |
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 |
CN105487532A (en) * | 2016-02-19 | 2016-04-13 | 上海果路交通科技有限公司 | Vehicle-mounted diagnostic data sharing terminal system |
CN107589695A (en) * | 2017-09-12 | 2018-01-16 | 中国中车股份有限公司 | A kind of train groups prognostic and health management system |
-
2016
- 2016-12-14 CN CN201611154208.4A patent/CN106406296B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102529903A (en) * | 2010-12-31 | 2012-07-04 | 上海博泰悦臻电子设备制造有限公司 | Comprehensive vehicle failure detecting system |
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 |
US20150242198A1 (en) * | 2014-02-25 | 2015-08-27 | Ford Global Technologies, Llc | Silent in-vehicle software updates |
CN104133467A (en) * | 2014-07-30 | 2014-11-05 | 浪潮集团有限公司 | OBDS long-distance fault diagnosis and recovery system based on cloud computation |
CN104185309A (en) * | 2014-08-12 | 2014-12-03 | 深圳市元征科技股份有限公司 | On-board wireless local area network equipment |
US20160057635A1 (en) * | 2014-08-12 | 2016-02-25 | Launch Tech Co., Ltd. | Vehicular wireless local area network device |
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 |
CN105487532A (en) * | 2016-02-19 | 2016-04-13 | 上海果路交通科技有限公司 | Vehicle-mounted diagnostic data sharing terminal system |
CN107589695A (en) * | 2017-09-12 | 2018-01-16 | 中国中车股份有限公司 | A kind of train groups prognostic and health management system |
Non-Patent Citations (1)
Title |
---|
赵虹: ""动车组维修决策***数据仓库的研究与应用"", 《万方硕士论文数据库》 * |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106953847A (en) * | 2017-02-27 | 2017-07-14 | 江苏徐工信息技术股份有限公司 | A kind of cross-platform real-time processing method of big data based on thrift |
CN107016057A (en) * | 2017-02-28 | 2017-08-04 | 北京铁路局 | Row control vehicle-mounted ATP equipment integral intelligent O&M method and system |
CN107025274A (en) * | 2017-03-21 | 2017-08-08 | 华中科技大学 | Equipment health status intelligent perception system and method based on Hadoop |
CN106970607A (en) * | 2017-03-31 | 2017-07-21 | 株洲中车时代电气股份有限公司 | The method of testing and system of a kind of converter control system |
CN107697107B (en) * | 2017-09-12 | 2020-03-10 | 中国中车股份有限公司 | Ground intelligent processing system and method for train set fault prediction and health management |
CN107697107A (en) * | 2017-09-12 | 2018-02-16 | 中国中车股份有限公司 | A kind of train groups prognostic and health management ground intelligent processing system and method |
CN107589695A (en) * | 2017-09-12 | 2018-01-16 | 中国中车股份有限公司 | A kind of train groups prognostic and health management system |
CN107679159A (en) * | 2017-09-28 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Generation method, device, server and the storage medium that fault diagnosis class problem replies |
US11541899B2 (en) | 2017-09-28 | 2023-01-03 | Denso Corporation | Vehicle diagnosis apparatus, vehicle diagnosis system, and vehicle diagnosis program |
CN111133289A (en) * | 2017-09-28 | 2020-05-08 | 株式会社电装 | Vehicle diagnostic device, vehicle diagnostic system, and vehicle diagnostic program |
CN107679159B (en) * | 2017-09-28 | 2021-06-11 | 百度在线网络技术(北京)有限公司 | Method and device for generating fault diagnosis question response, server and storage medium |
CN109696316A (en) * | 2017-10-20 | 2019-04-30 | 株洲中车时代电气股份有限公司 | A kind of train remote supervision system |
CN109917772A (en) * | 2017-12-13 | 2019-06-21 | 北京航空航天大学 | A kind of PHM rapid prototyping system of remote online assessment equipment state |
CN109948169A (en) * | 2017-12-20 | 2019-06-28 | 中国中车股份有限公司 | A kind of railway freight-car prognostic and health management system |
CN108038214A (en) * | 2017-12-21 | 2018-05-15 | 重庆脉实智能制造有限公司 | The collection of railway Overhaul Yard section device data, storage, the method and system of analysis and application |
CN110163225A (en) * | 2018-02-11 | 2019-08-23 | 顺丰科技有限公司 | It is a kind of that package detection and recognition methods, apparatus and system are mixed based on cloud platform |
CN110874093B (en) * | 2018-09-03 | 2023-02-21 | 上汽通用汽车有限公司 | Method and system for predicting life of brake lining of vehicle and storage medium |
CN110874093A (en) * | 2018-09-03 | 2020-03-10 | 上汽通用汽车有限公司 | Method and system for predicting life of brake lining of vehicle and storage medium |
CN109141898A (en) * | 2018-09-13 | 2019-01-04 | 湖北谊立舜达动力科技有限公司 | A kind of Diagnosis of Diesel Motor system based on Internet of Things |
CN109765448A (en) * | 2019-02-01 | 2019-05-17 | 唐智科技湖南发展有限公司 | A kind of distributed type fault diagnosis method, apparatus and system |
CN109765448B (en) * | 2019-02-01 | 2021-07-13 | 唐智科技湖南发展有限公司 | Distributed fault diagnosis method, device and system |
CN109915218A (en) * | 2019-03-07 | 2019-06-21 | 东方电气自动控制工程有限公司 | A kind of electro-hydraulic converting member fault diagnosis system of DEH system |
CN109915218B (en) * | 2019-03-07 | 2021-09-03 | 东方电气自动控制工程有限公司 | DEH system electrohydraulic conversion part fault diagnosis system |
CN110018425A (en) * | 2019-04-10 | 2019-07-16 | 北京理工大学 | A kind of power battery fault diagnosis method and system |
CN111830927A (en) * | 2019-04-23 | 2020-10-27 | 中车大连电力牵引研发中心有限公司 | Vehicle fault monitoring method and device and vehicle-mounted diagnosis equipment |
CN110361207A (en) * | 2019-07-25 | 2019-10-22 | 中南大学 | A kind of intelligence train EEF bogie presence forecasting system and its method |
CN110428066A (en) * | 2019-07-25 | 2019-11-08 | 中南大学 | It is a kind of intelligence Electric device presence assessment with operation platform and its method |
CN110428066B (en) * | 2019-07-25 | 2023-04-07 | 中南大学 | Intelligent train electrical device online state evaluation and operation and maintenance system and method thereof |
CN113085952A (en) * | 2020-01-08 | 2021-07-09 | 株洲中车时代电气股份有限公司 | Train monitoring system |
CN111352116A (en) * | 2020-03-31 | 2020-06-30 | 湖北阿桑奇汽车电子科技有限公司 | Ultrasonic obstacle positioning simulation device for vehicle |
CN111516727A (en) * | 2020-05-12 | 2020-08-11 | 上海数深智能科技有限公司 | High-speed rail defect abnormity intelligent diagnosis and detection system and method based on double vibration measurement sensors |
CN112307335A (en) * | 2020-10-29 | 2021-02-02 | 中国第一汽车股份有限公司 | Vehicle service information pushing method, device and equipment and vehicle |
US11400952B2 (en) | 2020-12-24 | 2022-08-02 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for automated driving |
CN113204227A (en) * | 2021-04-26 | 2021-08-03 | 江苏徐工工程机械研究院有限公司 | Cloud collaborative fault diagnosis system and method for layered modular engineering machinery |
Also Published As
Publication number | Publication date |
---|---|
CN106406296B (en) | 2019-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106406296A (en) | Train fault diagnosis system and method based on vehicle and cloud | |
CN107589695B (en) | Train set fault prediction and health management system | |
CN108320043B (en) | Power distribution network equipment state diagnosis and prediction method based on electric power big data | |
CN113465920B (en) | Cloud, fog and edge end cooperative bearing state monitoring and management method and system | |
CN107991870B (en) | Fault early warning and service life prediction method for escalator equipment | |
CN114282434A (en) | Industrial equipment health management system and method | |
CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
KR20190107080A (en) | Cloud-based vehicle fault diagnosis method, apparatus and system | |
US20130268501A1 (en) | System and method for monitoring distributed asset data | |
CN114021400A (en) | Pantograph monitoring operation and maintenance system based on digital twinning | |
CN111915026A (en) | Fault processing method and device, electronic equipment and storage medium | |
CN105775943A (en) | Data driven elevator part early warning system and method | |
CN117196066A (en) | Intelligent operation and maintenance information analysis model | |
CN110268425A (en) | System for analyzing machine data | |
CN116107282B (en) | Industrial robot predictive maintenance system based on enterprise application integration | |
CN112506097A (en) | Jig frame remote monitoring system and method based on industrial internet | |
CN116579697A (en) | Cold chain full link data information management method, device, equipment and storage medium | |
CN110221173B (en) | Power distribution network intelligent diagnosis method based on big data drive | |
CN114417501A (en) | Airborne deployment-oriented health management predictive modeling method | |
CN117074822A (en) | Charging pile fault diagnosis method, computer equipment and storage medium | |
Mandala | Integrating AWS IoT and Kafka for Real-Time Engine Failure Prediction in Commercial Vehicles Using Machine Learning Techniques | |
CN116432397A (en) | Rail transit fault early warning method based on data model | |
CN113757223B (en) | Hydraulic component reliability analysis method and system, computer device, and storage medium | |
Tao et al. | A state and fault prediction method based on RBF neural networks | |
CN107121616B (en) | Method and device for fault positioning of intelligent instrument |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |