CN107330823A - The fault case management method of train control on board equipment - Google Patents
The fault case management method of train control on board equipment Download PDFInfo
- Publication number
- CN107330823A CN107330823A CN201710413430.XA CN201710413430A CN107330823A CN 107330823 A CN107330823 A CN 107330823A CN 201710413430 A CN201710413430 A CN 201710413430A CN 107330823 A CN107330823 A CN 107330823A
- Authority
- CN
- China
- Prior art keywords
- fault case
- data
- fault
- failure
- train control
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000003993 interaction Effects 0.000 claims abstract description 7
- 230000003068 static effect Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 2
- 238000000151 deposition Methods 0.000 claims 1
- 238000012163 sequencing technique Methods 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 5
- 241000894007 species Species 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011065 in-situ storage Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
- G06Q50/2057—Career enhancement or continuing education service
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of fault case management method of train control on board equipment.This method mainly includes:Using the fault case of the train control on board equipment of collection, the grader of fault case is trained, using the grader of the fault case, classification processing is carried out to non-classified fault case, the fault case after handling classification carries out scene reproduction.Fault case is classified by the present invention by way of text classification according to the difference of manufacturer and failure happening part, student is in training module, obtain the relevant informations such as failure overview, accident analysis, treatment measures, the failure comment of each quasi-representative fault case, simultaneously, for a certain specific fault case, state change when failure is occurred has carried out scene reproduction, and student is by human-computer interaction interface, DMI anomalies before and after vivid acquisition failure occurs.
Description
Technical field
The present invention relates to train control on board equipment administrative skill field, more particularly to a kind of fault case of train control on board equipment
Management method.
Background technology
High-speed railway runs into various failure during operation, inevitably, for these fault cases,
The training education of rail man must be taken, to improve analysis and the disposal ability during reply failure, it is ensured that train can safety, height
Effect, orderly operation.Thus, the training of fault case is taken precautions against for improving worker and problem-solving ability have it is irreplaceable
Important function.
Because the failure situation that train occurs in the process of running is various, the position phase not to the utmost that each road bureau's failure occurs
Together, the training of fault case seems particularly complicated.At present, the training of train control on board equipment fault case is mainly known by specialty
Know study, the recording text of fault case, the explanation for there are experience personnel and the understanding of oneself of books to obtain fault case
Relevant information, so as to reach the purpose of fault case training.
At present, the training of existing train control on board equipment fault case be by professional explanation and book knowledge come
Obtain the specifying information of fault case.This method needs to expend huge manpower and materials for training numerous students.Meanwhile, by
In the complexity of train control on board equipment in itself, the training cycle of fault case is longer, it is difficult to by fault case comprehensively, go deep into shallow
What is gone out imparts to student, gets a desired effect;Only pass through the explanation of picture and word, it is impossible to scene weight when failure is occurred
Student is now given, causes result of training not good.
The content of the invention
The embodiment provides a kind of fault case management method of train control on board equipment, failure is sent out with realizing
State change when raw carries out scene reproduction.
To achieve these goals, this invention takes following technical scheme.
A kind of fault case management method of train control on board equipment, including:
Using the fault case of the train control on board equipment of collection, the grader of fault case is trained;
Using the grader of the fault case, classification processing is carried out to non-classified fault case;
Fault case after handling classification carries out scene reproduction.
Further, the described fault case using the train control on board equipment collected, trains the classification of fault case
Device, including:
The fault case of a number of train control on board equipment is collected, the record of the fault case includes failure
When failure overview, failure cause, treatment measures and failure comment content, according to the manufacturer of train control on board equipment, failure
Happening part carries out classification processing to all fault cases;
The typical fault case in the fault case of each species is extracted, the text of the typical fault case is made
For the training set of text classification, text participle, feature extraction are carried out to training set, characteristic vector weights are calculated, training is out of order
The grader of case.
Further, it is described that text participle, feature extraction are carried out to training set, characteristic vector weights are calculated, train
The grader of fault case, including:
Fault case text is divided into place vocabulary, quantity vocabulary, row complaint and converges, disable vocabulary, move after text participle
Make five kinds of vocabulary of vocabulary;According to the classification of typical fault case, the feature extracted from participle includes acquiescence message, cab signal
Abnormal, wireless connection is overtime, stop in emergency, license of driving a vehicle is abnormal, text prompt is abnormal;
The weight calculation method for employing TF-IDF calculates the weights of characteristic vector i in the weights of characteristic vector, TF-IDF
Formula is:
Wherein MiThe number of times that some word occurs in this text is represented, Q represents the total word number occurred in text, identical word
Then Q will not be superimposed for secondary appearance, the total degree of Q statistics, in the absence of repetition, and D represents corpus article sum, SiRepresent D's
Word i article record is included in sample.
Further, the manufacturer according to train control on board equipment, failure happening part are to all fault cases
Classification processing is carried out, including:
The fault case of train control on board equipment is divided into by 5 species according to the difference of train control on board equipment manufacturer:
CTCS3-300T, CTCS3-300S, CTCS3-300H, CTCS3-200H and CTCS3-200C, according to failure happening part not
It is divided into 7 species with by the fault case of train control on board equipment:ATP、TCR、TIU、GSM-R、SDU、DMI、BTM.
Further, the grader of the described utilization fault case, is carried out at classification to non-classified fault case
Reason, including:
Failure text participle is carried out to non-classified fault case, using the feature in training set to non-classified failure case
Example calculates characteristic vector weights, the grader trained according to the characteristic vector weights of non-classified fault case by training set
Non-classified fault case is classified, in the classification that non-classified fault case is belonged to corresponding fault case.
Further, the fault case after the processing to classification carries out scene reproduction, including:
By the train control on board equipment service data comprising fault case and during correct fault-free in scene playback system
Train control on board equipment service data synchronizes display in same reference axis, real when two number formularies are according to occurring running inconsistent
Scene reproduction now is carried out to fault case, concrete processing procedure includes:
Step 1, according to the corresponding data in given specific data template completion train control on board equipment normal course of operation
Corresponding data during with failure operation, the corresponding data includes static engineering data and operation state data, the static work
Number of passes is supported to be automatically imported according to the data for being reference format;
Step 2, the corresponding data that will fill in are loaded into scene reproduction system, and scene reproduction system reads described
Static engineering data in corresponding data, the static engineering data are arranged according to the incremental mode of kilometer post, are being sat
Drawn out in parameter in patterned mode;
Step 3, scene reproduction system read the operation state data in train control on board equipment normal course of operation, and this is transported
Mobile state data are added in patterned static engineering data, and train operation curve and critical event are drawn in reference axis;
Step 4, scene reproduction system read corresponding data during train control on board equipment failure operation, and the corresponding data is deposited
Enter in caching;
Click on scene reproduction system the button that brings into operation, by corresponding data during train control on board equipment failure operation according to
Time order and function order is progressively shown with patterned way, in the process of running, is currently run according to certain rule judgment
Whether data are consistent with normal service data, if it is determined that data are consistent, then continue to run with;If it is determined that data differ
Cause, then scene reproduction system halt, and inconsistent content, scene reproduction system halt are pointed out with text and patterned way
Afterwards, it can continue to operation.
Further, the fault case after the processing to classification carries out scene reproduction, including:
By the human-computer interaction interface of emulation, the image in front and rear a period of time that scene is broken down carries out simulation fortune
OK, during dry run, operation is suspended, continues to run with, retracts or reruns by clicking on realization, it is specific treated
Journey includes:
The record data obtained in live running is automatically read in scene reproduction system, and by the record data
The data format changed into needed for scene reproduction system;
Record data described in scene reproduction system analysis, and using the fault case grader by the record data
Classified automatically according to fault case classification;While classification, according to the time window scope set in advance, by number of faults
Intercepted and deposited according to file, and the fault data file is named automatically according to fault case classification;
The fault data file to be played back is selected by the interface of scene reproduction system, the fault data file is performed into fortune
Go, suspend, continue to run with, retract and rerun function.
The embodiment of the present invention is to national 18 road bureaus it can be seen from the technical scheme that embodiments of the invention described above are provided
The fault case occurred is collected, by fault case according to manufacturer and failure generating unit by way of text classification
The difference of position is classified, student in training module, obtain the failure overview of each quasi-representative fault case, accident analysis,
The relevant informations such as treatment measures, failure comment, meanwhile, for a certain specific fault case, state change when failure is occurred
Scene reproduction is carried out, student is by human-computer interaction interface, DMI anomalies before and after vivid acquisition failure occurs.
The additional aspect of the present invention and advantage will be set forth in part in the description, and these will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, being used required in being described below to embodiment
Accompanying drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this
For the those of ordinary skill of field, without having to pay creative labor, other can also be obtained according to these accompanying drawings
Accompanying drawing.
Fig. 1 is a kind of handling process of the fault case management method of train control on board equipment provided in an embodiment of the present invention
Figure;
Fig. 2 is the schematic diagram that a kind of fault case to train control on board equipment provided in an embodiment of the present invention is classified.
Embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning
Same or similar element or element with same or like function are represented to same or similar label eventually.Below by ginseng
The embodiment for examining accompanying drawing description is exemplary, is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is individual ", " described " and "the" may also comprise plural form.It is to be further understood that what is used in the specification of the present invention arranges
Diction " comprising " refer to there is the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or during " coupled " to another element, and it can be directly connected or coupled to other elements, or can also exist
Intermediary element.In addition, " connection " used herein or " coupling " can include wireless connection or coupling.Wording used herein
"and/or" includes one or more associated any cells for listing item and all combined.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology) with the general understanding identical meaning with the those of ordinary skill in art of the present invention.Should also
Understand, those terms defined in such as general dictionary, which should be understood that, to be had and the meaning in the context of prior art
The consistent meaning of justice, and unless defined as here, will not be explained with idealization or excessively formal implication.
For ease of the understanding to the embodiment of the present invention, done below in conjunction with accompanying drawing by taking several specific embodiments as an example further
Explanation, and each embodiment does not constitute the restriction to the embodiment of the present invention.
The embodiments of the invention provide the system of a typical fault case training, the system is primarily adapted for use in training railway
Understanding of the worker to typical fault case, and improve analysis and disposal ability of the student to failure.Using the system to railway duty
The training of work, can greatly shorten training cycle, reduction training cost, fault case is giveed training by way of interactive, will
Fault case is straightaway to be presented to student, quick enhancement training quality.
A kind of handling process such as Fig. 1 institutes of the fault case management method of train control on board equipment provided in an embodiment of the present invention
Show, including following process step:
Step S110, using collection substantial amounts of train control on board equipment fault case, train the classification of fault case
Device.
Before the typing of fault case of train control on board equipment is carried out, work is investigated to national 18 road bureaus,
The fault case of substantial amounts of train control on board equipment is have collected in research work, in the record of fault case, the fault case
Record include failure occur when failure overview, failure cause, treatment measures and failure comment etc. content, according to row control car
Carry the manufacturer of equipment, failure happening part and classification processing is carried out to all fault cases.
Because the position that each road bureau's train control on board equipment breaks down is not quite similar, meanwhile, use different manufacturers
Train control on board equipment, the phenomenon of the failure showed when same area breaks down is also incomplete same, in this case, root
According to the difference of train control on board equipment manufacturer, fault case is divided into 5 species:Respectively CTCS3-300T, CTCS3-
300S、CTCS3-300H、CTCS3-200H、CTCS3-200C.According to the different by train control on board equipment of failure happening part
Fault case is divided into 7 species:ATP、TCR、TIU、GSM-R、SDU、DMI、BTM.By such mode, row control vehicle-mounted is set
Standby typical failure carries out comprehensive classification.
Fig. 2 is the schematic diagram that a kind of fault case to train control on board equipment provided in an embodiment of the present invention is classified,
To carry out classification training, processing procedure includes:The typical fault case in the fault case of each species is extracted, will be described
The text of typical fault case carries out text participle, feature extraction to training set, calculates special as the training set of text classification
Vectorial weights are levied, the grader of fault case is finally trained.
Fault case text is divided into place vocabulary, quantity vocabulary, row complaint and converges, disable vocabulary, move after text participle
Make five kinds of vocabulary of vocabulary.According to the classification of typical fault case, the feature extracted from participle includes acquiescence message, cab signal
Abnormal, wireless connection is overtime, stop in emergency, license of driving a vehicle is abnormal, text prompt is abnormal.
The feature extracted is used for the calculating of characteristic vector weights, employs TF-IDF weight calculation method.TF-IDF
(term frequency-inverse document frequency) is a kind of for the conventional of information retrieval and data mining
Weighting technique, is a kind of statistical method, i.e., the ratio occurred according to some word/phrase in itself article, and the phrase exist
The ratio occurred in overall corpus, to calculate the weights of the word/phrase, weights are higher, it was demonstrated that the word, which is got over, can represent this text
The classification of chapter, opposite weights are lower, the word is smaller to the contribution degree of article, assess a words for one in this way
The significance level of article or a corpus.
Characteristic vector i weights formula is in TF-IDF:
Wherein MiThe number of times that some word occurs in this text is represented, Q represents the total word number occurred in text, identical word
Then Q will not be superimposed for secondary appearance, the total degree of Q statistics, in the absence of repetition.D represents corpus article sum, SiRepresent D's
Word i article record is included in sample.
Step 120, the grader using fault case, classification processing is carried out to non-classified fault case.
The a large amount of non-classified fault cases obtained from road bureau, failure text participle is carried out to non-classified fault case,
Characteristic vector weights are calculated to non-classified fault case using the feature in training set.
The grader trained according to the characteristic vector weights of non-classified fault case by training set is to non-classified
Fault case is classified,
The present invention uses Naive Bayes Classifier, and its basic thought is, for given text to be sorted, to calculate
Go out to belong to when each sample to be sorted occurs the probability of each classification, maximum probability generic is sample to be sorted
Classification.Its basic classification step is:Obtain the characteristic attribute of each item to be sorted and the category set of known classification;To every
Individual known class categories calculate the probability of characteristic attribute, then calculate the conditional probability of all divisions of each characteristic attribute;
The classification of final condition maximum probability is the generic of text to be sorted.
Finally automatically non-classified fault case is belonged in the classification of corresponding fault case.
Step 130, to classification handle after fault case carry out scene reproduction.
The present invention needs to set the playback software of the fault case of various species, is passed through using the playback software of fault case
DMI (Driver Machine Interface, human-computer interaction interface) real-time exhibition, scene is carried out to current fault case
Reproduce, scene when failure is occurred is giveed training in interactive, visual in image mode to student, student is had fault in-situ
The understanding become apparent from.During failure scenario reproduces, student can simulate driver driving.
The scene reproduction of fault case is broadly divided into two kinds of different ways of realization, and user can select wherein as needed
One or two kinds of carries out scene reproduction.
Mode one:By the service data when service data comprising fault case and correct fault-free in same range coordinate
Display is synchronized in axle, when two number formularies are according to occurring running inconsistent, system can provide alarm.The realization of which
It is broadly divided into following steps:
(1) first step, the specific data template given according to system (mainly includes static engineering data, train operation to move
State data), user fills in corresponding data when corresponding data and failure operation in daily normal course of operation.Wherein, it is static
Project data is the data of reference format, and system can be supported to be automatically imported;Train operation dynamic data needs user voluntarily to fill out
Enter.
(2) second step, the data that will fill in are loaded into system, and system reads static engineering data, by these data
Arranged, finally drawn out in patterned mode according to the incremental mode of kilometer post.
(3) the 3rd steps, system reads normal course of operation data, by these data on the basis of static data, draws row
Car operation curve and critical event.
(4) the 4th steps, data when system read failure is run are kept in the system cache after these data are read in.
(5) the 5th steps, user, which can click on, starts, suspends and reruns button.When clicking on start button, system
Failure operation data are progressively shown according to time order and function order with patterned way.Meanwhile, in the process of running, system
Ceaselessly judge current data and normal service data according to certain rule.If it is determined that data are consistent, then continue to run with;
If it is determined that data are inconsistent, then system halt, and point out inconsistent content with text and patterned way.System halt
Afterwards, user can continue to operation.
Mode two:Another way of realization is the human-computer interaction interface (emulating DMI) by emulation, by scene appearance
Image in front and rear a period of time of failure carries out dry run.During dry run, it can be realized at any time by clicking on
Suspend, continue to run with, retract or rerun operation.The main thought of which is:
(1) first step, system automatically reads the record data obtained in live running in system, and these are counted
According to the data format needed for conversion cost system.
(2) second step, system parses record data automatically, and is recorded these using above-mentioned shown fault case grader
Data are classified automatically according to fault case classification;While classification, according to the time window scope set in advance, by phase
Close data to be intercepted and deposited, and the data cutout file is named automatically according to fault case classification.
(3) the 3rd steps, user can select the fault data file to be played back by system interface, and these data are literary
Part performs operation, suspends, continues to run with, retracts and rerun function.
Step 140, sorted fault case is shown with excellent pictures and texts, makes failure modes form.
Fault case after classification processing is shown by the form that both pictures and texts are excellent on the right side of training interface, Xue Yuanke
Easily to obtain the related contents such as failure overview, accident analysis, treatment measures, failure comment, by the data of character property also not
It is enough to show incisively and vividly by failure, can be by training the recurrence of failure of page lower right for specific fault case
The playback of failure is carried out, there is the understanding become apparent to fault in-situ.
Failure modes form is made for fault case, in failure modes form, 18, whole nation Railway Bureau is contained
The concrete condition that fault case occurs, the fault case of each road bureau obtained during investigation is recorded, sent out according to failure in detail
Raw position, is the class of ATP, TCR, TIU, GSM-R, SDU, DMI, BTM seven, this 7 class of each road bureau by fault case taxonomic revision
The situation that failure occurs, is shown in failure modes form using block diagram, student is clearly understood each road bureau and occurs event
The overview of barrier, and for the situation of place road bureau, intense session is carried out to common, incident fault case, while also right
The failure occurred in road bureau carries out chapters and sections correspondence, and the typical fault case corresponded in training module will by the form of analogy
Result of training reaches most preferably.
In summary, the embodiment of the present invention is collected to the fault case that national 18 road bureaus occurred, and passes through text
Fault case is classified by the mode of classification according to the difference of manufacturer and failure happening part, and student is in training mould
Block, obtains the relevant informations such as failure overview, accident analysis, treatment measures, the failure comment of each quasi-representative fault case, together
When, for a certain specific fault case, state change when failure is occurred has carried out scene reproduction, and student passes through man-machine interaction
Interface, DMI anomalies before and after vivid acquisition failure occurs.
Failure Reports module provides the specific fault case information of each national road bureau for student, facilitates student to understand each
Quantity and the common happening part of failure occur for road bureau's failure, so as to targetedly be giveed training to fault case.Finally, pass through
Failure is tested oneself module, and student can be estimated to the results of learning of oneself, to deepen the understanding to fault case.
One of ordinary skill in the art will appreciate that:Accompanying drawing be module in the schematic diagram of one embodiment, accompanying drawing or
Flow is not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention can
Realized by the mode of software plus required general hardware platform.Understood based on such, technical scheme essence
On the part that is contributed in other words to prior art can be embodied in the form of software product, the computer software product
It can be stored in storage medium, such as ROM/RAM, magnetic disc, CD, including some instructions are to cause a computer equipment
(can be personal computer, server, or network equipment etc.) performs some of each of the invention embodiment or embodiment
Method described in part.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.Especially for device or
For system embodiment, because it is substantially similar to embodiment of the method, so describing fairly simple, related part is referring to method
The part explanation of embodiment.Apparatus and system embodiment described above is only schematical, wherein the conduct
The unit that separating component illustrates can be or may not be it is physically separate, the part shown as unit can be or
Person may not be physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can root
Some or all of module therein is factually selected to realize the purpose of this embodiment scheme the need for border.Ordinary skill
Personnel are without creative efforts, you can to understand and implement.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, the change or replacement that can be readily occurred in,
It should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
It is defined.
Claims (7)
1. a kind of fault case management method of train control on board equipment, it is characterised in that including:
Using the fault case of the train control on board equipment of collection, the grader of fault case is trained;
Using the grader of the fault case, classification processing is carried out to non-classified fault case;
Fault case after handling classification carries out scene reproduction.
2. according to the method described in claim 1, it is characterised in that the described failure case using the train control on board equipment collected
Example, trains the grader of fault case, including:
The fault case of a number of train control on board equipment is collected, the record of the fault case is included when failure occurs
Failure overview, failure cause, treatment measures and failure comment content, occur according to the manufacturer of train control on board equipment, failure
Position carries out classification processing to all fault cases;
The typical fault case in the fault case of each species is extracted, the text of the typical fault case is regard as text
The training set of this classification, text participle, feature extraction are carried out to training set, characteristic vector weights are calculated, fault case is trained
Grader.
3. method according to claim 2, it is characterised in that it is described training set is carried out text participle, feature extraction,
Characteristic vector weights are calculated, the grader of fault case is trained, including:
Fault case text is divided into place vocabulary, quantity vocabulary, row complaint and converges, disables vocabulary, action word after text participle
Five kinds of vocabulary of remittance;According to the classification of typical fault case, it is different that the feature extracted from participle includes acquiescence message, cab signal
Often, wireless connection is overtime, stop in emergency, license of driving a vehicle is abnormal, text prompt is abnormal;
The weight calculation method for employing TF-IDF calculates the weights formula of characteristic vector i in the weights of characteristic vector, TF-IDF
For:
<mrow>
<msub>
<mi>W</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<msub>
<mi>TF</mi>
<mi>i</mi>
</msub>
<mo>*</mo>
<msub>
<mi>IDF</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<msub>
<mi>M</mi>
<mi>i</mi>
</msub>
<mi>Q</mi>
</mfrac>
<mo>*</mo>
<mi>lg</mi>
<mfrac>
<mi>D</mi>
<msub>
<mi>S</mi>
<mi>i</mi>
</msub>
</mfrac>
</mrow>
Wherein MiThe number of times that some word occurs in this text is represented, Q represents the total word number occurred in text, second of identical word
Then Q occur will not be superimposed, the total degree of Q statistics, in the absence of repetition, and D represents corpus article sum, SiRepresent the sample in D
In include word i article record.
4. method according to claim 3, it is characterised in that the manufacturer according to train control on board equipment therefore
Hinder happening part and all fault cases are carried out with classification processing, including:
The fault case of train control on board equipment is divided into by 5 species according to the difference of train control on board equipment manufacturer:CTCS3-
300T, CTCS3-300S, CTCS3-300H, CTCS3-200H and CTCS3-200C, different according to failure happening part will row
The fault case of control vehicle-mounted equipment is divided into 7 species:ATP、TCR、TIU、GSM-R、SDU、DMI、BTM.
5. the method according to claim 1 or 2 or 3 or 4, it is characterised in that point of the described utilization fault case
Class device, classification processing is carried out to non-classified fault case, including:
Failure text participle is carried out to non-classified fault case, using the feature in training set to non-classified fault case meter
Characteristic vector weights are calculated, the grader trained according to the characteristic vector weights of non-classified fault case by training set is not to
The fault case of classification is classified, in the classification that non-classified fault case is belonged to corresponding fault case.
6. method according to claim 5, it is characterised in that the fault case after the processing to classification carries out scene
Reproduce, including:
By the row control when train control on board equipment service data comprising fault case and correct fault-free in scene playback system
Mobile unit service data synchronizes display in same reference axis, when two number formularies are according to occurring running inconsistent, realization pair
Fault case carries out scene reproduction, and concrete processing procedure includes:
Step 1, according to the corresponding data in given specific data template completion train control on board equipment normal course of operation and therefore
Corresponding data during barrier operation, the corresponding data includes static engineering data and operation state data, the static engineering number
According to the data for reference format, support to be automatically imported;
Step 2, the corresponding data that will fill in are loaded into scene reproduction system, and scene reproduction system reads described corresponding
Static engineering data in data, the static engineering data are arranged according to the incremental mode of kilometer post, in reference axis
In drawn out in patterned mode;
Step 3, scene reproduction system read the operation state data in train control on board equipment normal course of operation, and the operation is moved
State data are added in patterned static engineering data, and train operation curve and critical event are drawn in reference axis;
Step 4, scene reproduction system read corresponding data during train control on board equipment failure operation, the corresponding data are stored in slow
In depositing;
The button that brings into operation of scene reproduction system is clicked on, by corresponding data during train control on board equipment failure operation according to the time
Sequencing is progressively shown with patterned way, in the process of running, according to certain rule judgment current operating data
It is whether consistent with normal service data, if it is determined that data are consistent, then continue to run with;If it is determined that data are inconsistent, then
Scene reproduction system halt, and inconsistent content is pointed out with text and patterned way, can after scene reproduction system halt
Continue to run with.
7. method according to claim 5, it is characterised in that the fault case after the processing to classification carries out scene
Reproduce, including:
By the human-computer interaction interface of emulation, the image in front and rear a period of time that scene is broken down carries out dry run,
During dry run, operation, concrete processing procedure are suspended, continue to run with, retract or rerun by clicking on realization
Including:
The record data obtained in live running is automatically read in scene reproduction system, and the record data is converted
Data format into needed for scene reproduction system;
Record data described in scene reproduction system analysis, and using the fault case grader by the record data according to
Fault case classification is classified automatically;While classification, according to the time window scope set in advance, by fault data text
Part is intercepted and deposited, and names the fault data file automatically according to fault case classification;
The fault data file to be played back is selected by the interface of scene reproduction system, by the fault data file perform operation,
Suspend, continue to run with, retract and rerun function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710413430.XA CN107330823A (en) | 2017-06-05 | 2017-06-05 | The fault case management method of train control on board equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710413430.XA CN107330823A (en) | 2017-06-05 | 2017-06-05 | The fault case management method of train control on board equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107330823A true CN107330823A (en) | 2017-11-07 |
Family
ID=60194873
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710413430.XA Pending CN107330823A (en) | 2017-06-05 | 2017-06-05 | The fault case management method of train control on board equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107330823A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108334049A (en) * | 2017-12-26 | 2018-07-27 | 中车唐山机车车辆有限公司 | The management method and device of vehicle trouble data |
CN110502306A (en) * | 2019-08-26 | 2019-11-26 | 湖南中车时代通信信号有限公司 | A kind of safe man-machine interactive system and method for vehicle-mounted automatic train protection system |
CN112634696A (en) * | 2020-12-21 | 2021-04-09 | 贝壳技术有限公司 | Fault positioning practice method and device, electronic equipment and storage medium |
CN113947893A (en) * | 2021-09-03 | 2022-01-18 | 网络通信与安全紫金山实验室 | Method and system for restoring driving scene of automatic driving vehicle |
CN114475731A (en) * | 2021-12-29 | 2022-05-13 | 卡斯柯信号有限公司 | Signal equipment fault knowledge base system and implementation method thereof |
CN116414390A (en) * | 2023-03-29 | 2023-07-11 | 南京审计大学 | Dynamic operation case development system for big data audit |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070288409A1 (en) * | 2005-05-31 | 2007-12-13 | Honeywell International, Inc. | Nonlinear neural network fault detection system and method |
-
2017
- 2017-06-05 CN CN201710413430.XA patent/CN107330823A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070288409A1 (en) * | 2005-05-31 | 2007-12-13 | Honeywell International, Inc. | Nonlinear neural network fault detection system and method |
Non-Patent Citations (2)
Title |
---|
杨官霞: "抽水蓄能电站事故演习及培训***设计", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
王峰: "基于文本挖掘的高铁车载设备故障诊断方法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108334049A (en) * | 2017-12-26 | 2018-07-27 | 中车唐山机车车辆有限公司 | The management method and device of vehicle trouble data |
CN108334049B (en) * | 2017-12-26 | 2020-09-22 | 中车唐山机车车辆有限公司 | Vehicle fault data management method and device |
CN110502306A (en) * | 2019-08-26 | 2019-11-26 | 湖南中车时代通信信号有限公司 | A kind of safe man-machine interactive system and method for vehicle-mounted automatic train protection system |
CN110502306B (en) * | 2019-08-26 | 2023-02-03 | 湖南中车时代通信信号有限公司 | Safety man-machine interaction system and method for automatic protection system of vehicle-mounted train |
CN112634696A (en) * | 2020-12-21 | 2021-04-09 | 贝壳技术有限公司 | Fault positioning practice method and device, electronic equipment and storage medium |
CN112634696B (en) * | 2020-12-21 | 2023-01-31 | 贝壳技术有限公司 | Fault positioning exercise method and device, electronic equipment and storage medium |
CN113947893A (en) * | 2021-09-03 | 2022-01-18 | 网络通信与安全紫金山实验室 | Method and system for restoring driving scene of automatic driving vehicle |
CN114475731A (en) * | 2021-12-29 | 2022-05-13 | 卡斯柯信号有限公司 | Signal equipment fault knowledge base system and implementation method thereof |
CN116414390A (en) * | 2023-03-29 | 2023-07-11 | 南京审计大学 | Dynamic operation case development system for big data audit |
CN116414390B (en) * | 2023-03-29 | 2024-04-05 | 南京审计大学 | Dynamic operation case development system for big data audit |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107330823A (en) | The fault case management method of train control on board equipment | |
Spurgin | Human reliability assessment theory and practice | |
Arai et al. | Testing methodological developments in the conduct of narrative synthesis: a demonstration review of research on the implementation of smoke alarm interventions | |
Wang et al. | Using the attribute hierarchy method to make diagnostic inferences about examinees’ cognitive skills in critical reading | |
Dawson et al. | SNAPP: Realising the affordances of real-time SNA within networked learning environments | |
Lundberg et al. | Strategies for dealing with resistance to recommendations from accident investigations | |
Freire et al. | Techniques for developing more accessible web applications: a survey towards a process classification | |
CN102831119B (en) | Short text clustering Apparatus and method for | |
CN103077650A (en) | Simulation training system device used for testing safety cognition mentality and behavior | |
Abbas et al. | Qualitative life-grids: A proposed method for comparative European educational research | |
Irwin-Rogers et al. | Youth Violence Commission | |
Naweed | Simulator integration in the rail industry: the Robocop problem | |
CN105632264A (en) | Method and device of managing courseware resources | |
Curtotti et al. | Enhancing the visualization of law | |
Burt et al. | Connotative meanings of student performance labels used in standard setting | |
May et al. | A closer look at tracking human and computer interactions in web‐based communications | |
Bianchi et al. | Investigating student choices in performing higher-level comprehension tasks using TED | |
Luo et al. | Discrimination-Aware Classifiers for Student Performance Prediction. | |
Pons et al. | A Learning Quality Metadata approach: Automatic quality assessment of virtual training from metadata | |
Newbury | Are Design Elements in Blended Learning Courses Factors of Student Completion Rate?. | |
Mellar | Towards a modelling curriculum | |
Kuncoro | Critical Discourse Analysis of Rejecting the Andesite Mining in Wadas Village News on Tempo. co | |
Scheffel et al. | Exploring LogiAssist–the mobile learning and assistance platform for truck drivers | |
Foss et al. | Adaptive hypermedia content authoring using MOT3. 0 | |
Chen et al. | Understand and analyzing learning objects: A foundation for long-term substantiality and use for e-learning |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171107 |
|
WD01 | Invention patent application deemed withdrawn after publication |