CN110414855A - A kind of railcar safety evaluation method based on classification - Google Patents
A kind of railcar safety evaluation method based on classification Download PDFInfo
- Publication number
- CN110414855A CN110414855A CN201910707566.0A CN201910707566A CN110414855A CN 110414855 A CN110414855 A CN 110414855A CN 201910707566 A CN201910707566 A CN 201910707566A CN 110414855 A CN110414855 A CN 110414855A
- Authority
- CN
- China
- Prior art keywords
- event
- class
- security level
- vehicular events
- classification
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims description 52
- 238000012360 testing method Methods 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 15
- 241001269238 Data Species 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000000926 separation method Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a kind of railcar safety evaluation method based on classification, the present invention is based on the basic event base of the standard failure Database of vehicle failure and vehicular events libraries, security level is evaluated to event each in event base by expert or professional technician, security level disaggregated model is then established according to the event sample by evaluation and newly-increased vehicle security status is evaluated.The present invention, which is applied, does not need to increase in field of track traffic new detection device and professional, can be realized in existing management system.
Description
Technical field
The present invention relates to technical field of rail traffic, and in particular to a kind of railcar safety evaluatio side based on classification
Method.
Background technique
In field of track traffic, common train safety evaluation method is by special sensing measurement technology and model
Calculation method obtains corresponding vehicle smoothness index value, and the method is ground based on the dynamics of vehicle mechanism of wheel rail relation
Study carefully, reliable accurately evaluation can be provided for train operational safety really, but at present about vehicle movement stability indicator
It measures relatively difficult, is unable to satisfy demand of both quick obtaining and long-term follow vehicle safety.In response to the above problems, existing
Some processing modes are roughly divided into three kinds, first is that periodically carrying out repair and maintenance to train, it is ensured that each component of train is in well
State, but this mode time between overhauls(TBO) is shorter, remains biggish safe clearance to vehicle, generates a large amount of unnecessary dimension
Shield movement, many components that need not be needed for repair and replacement are all repaired or are replaced in advance, and great waste is caused.Second is that being directed to
New car or doubtful problem vehicle carry out comprehensive dynamic experiment, onboard temporarily install the fortune of various kinds of sensors acquisition vehicle
Dynamic attitude data, every safety indexes of vehicle are calculated with this, to evaluate the safety of the vehicle, but such experiment one
The equipment such as sensor are expensive and service life is extremely short, it is also necessary to engage the personnel of profession to assist experiment, need to expend a large amount of people
Power material resources and time cost are also a kind of greatly waste for operator.Third is that being showed by technical professional from vehicle
Every status data rule of thumb probably judge the security status of vehicle, but this mode be limited to experience accumulation and
The profile of technical staff can not make evaluation steadily in the long term and on a large scale for vehicle safety grade.
Summary of the invention
In order to solve above-mentioned technical problem of the existing technology, the present invention provides a kind of railcars based on classification
Safety evaluation method, the present invention can be realized efficient and intelligent train safety evaluatio.
The present invention is achieved through the following technical solutions:
A kind of railcar safety evaluation method based on classification, this method comprises:
Step S1 obtains all logout basis of formation event base A occurred during railcar operation, and is base
Event type label is arranged in the basic event of each in plinth event base A;
Step S2 establishes vehicular events library B based on basic event base A, and is each of vehicular events library B vehicle
Security level label is arranged in event;
Data in the B of vehicular events library are converted sample matrix B by step S31With test matrix B2;
Step S4 is based on sample matrix B1Preliminary classification model is constructed, using preliminary classification model to test matrix B2It carries out
Security level classification;
Step S5, the test matrix B obtained based on step S4 by disaggregated model2The security level and step of each vehicular events
The security level of corresponding setting to the step S4 preliminary classification model constructed and is verified and is updated in rapid S2.
Preferably, each basic event is provided with 5 label datas in basic event base A in the step S1, successively
Including route, vehicle, event data, event influences and event type.
Preferably, each vehicular events is provided with 9 label datas in the B of vehicular events library in the step S2, successively
Including time, route, vehicle, I class event, II class event, III class event, IV class event, V class event and security level:.
Preferably, the step S3 specifically: convert two for all data under the 4-9 label in the B of vehicular events library
A data matrix B1And B2, wherein B1As sample matrix, B2As test matrix;Data matrix expression formula is as follows:
R=(rijk, i=1,2,3,4,5, j=1,2 ..., n, k=1,2,3,4,5)
Wherein, i indicates security level, and j indicates vehicular events serial number, and k indicates event type;rijkIndicate j-th of vehicle thing
Part, kth class vehicular events, the data of the i-th class security level.
Preferably, the step S4 is specifically included:
Sample matrix B is calculated using clustering algorithm in step S411In in every class security level each vehicular events class
Centre coordinate b, expression formula are as follows:
Wherein, niIndicate the i-th class security level vehicular events quantity, bikIndicate kth in the i-th class security level vehicular events
The centre coordinate value of class basis event;
Step S42 calculates test matrix B2In the class center matrix b number that is calculated of each vehicular events data and step S4
According to distance, obtain class distance matrix C, expression formula are as follows:
Wherein, B2ikIndicate test matrix B2In the i-th class basis event quantity, CijThe minimum corresponding j value of value is to test
Matrix B2In the i-th class basis event security level, QjIndicate the weight of jth class security level.
Preferably, the average probability of happening p that the weight Q of all kinds of security levels is occurred by all kinds of eventsiIt determines, it is specific to wrap
It includes:
The occurrence frequency of all kinds of events in basic event base A is calculated first;
Then according to the average probability of happening p of the every class event of security level classified calculatingi;
According to average probability of happening piCalculate the weight Q of each security level:
Q={ Qi|Qi=1/pi};I=1,2,3,4,5.
Preferably, the step S5 is specifically included;By test matrix B2In each vehicular events pass through mould of classifying in step S4
The security level classification results that type obtains and the security level that vehicular events setting is corresponded in step S2 compare, and verify model
The accuracy of classification is simultaneously updated.
Preferably, this method further include:
Step S6 carries out security level classification to newly-increased vehicular events using the revised disaggregated model of step S5;
Step S7 carries out verification amendment to the security level for increasing vehicular events classification in step S6 newly, and corrects verifying
Sample matrix is added in data afterwards, repeats step S4 and step S5 and is updated to model.
The present invention has the advantage that and the utility model has the advantages that
Operation of the present invention is easy, comprehensively utilizes mathematics relationship and the quick, intelligent of vehicle safety is commented in professional experiences realization
It is fixed, and can accomplish to warn in advance according to the offset rule look-ahead vehicle safety variation tendency of data point.
The present invention takes full advantage of the algorithm of Machine self-learning, and the present invention has the ability of autonomous sustainable renewal iteration,
Often there is new class sample, then by being put in storage after expert evaluation, model is gradually perfect with the increase of sample size, makes calculated result more
It is accurate to add.
The present invention is applied without increasing new detection device and professional operator in field of track traffic, existing
Subway personnel's system in can be realized.
Detailed description of the invention
Attached drawing described herein is used to provide to further understand the embodiment of the present invention, constitutes one of the application
Point, do not constitute the restriction to the embodiment of the present invention.In the accompanying drawings:
Fig. 1 is method flow schematic diagram of the invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below with reference to embodiment and attached drawing, to this
Invention is described in further detail, and exemplary embodiment of the invention and its explanation for explaining only the invention, are not made
For limitation of the invention.
Embodiment 1
The present embodiment proposes a kind of railcar safety evaluation method based on classification, as shown in Figure 1, this method packet
Include following steps:.
Step 1: all event of failure occurred during railcar operation are collected and record the basis to form vehicle trouble
Event base A.Security implication grade is carried out to existing vehicle trouble basis event by railcar expert or professional technician
Basic vehicular events are divided into safe, slight, critical, critical, five class of disaster, the criteria for classifying is described in table 1 below by evaluation.This reality
It applies in example, it successively includes route, vehicle, event number that the basic event of each in basic event base A, which is provided with 5 label datas,
It is influenced according to, event and event type.
1 event type table of table
Step 2: vehicle safety state event library B, each vehicular events in event base are established based on basic database A
Be by basic event base basic event, event type and by railcar expert or professional technician to existing vehicle
The security level evaluation of event.In the present embodiment, each vehicular events is provided with 9 label datas in the B of vehicular events library,
It successively include time, route, vehicle, I class time, II class event, III class event, IV class event, V class event and security level.
Step 3: establishing vehicular events Safety Evaluation, converts two data matrix Bs for vehicular events library B1With
B2, wherein B1As sample matrix, B2As test matrix;By the basic event composition data of vehicular events each in sample database
Change, i.e., each vehicular events record is converted into data mode r, and wherein i is vehicle safety grade, and j is vehicular events serial number, and k is
Basic event class.
R=(rijk, i=1,2,3,4,5, j=1,2 ..., n, k=1,2,3,4,5)
Wherein, rijkIndicate the data of j-th of vehicular events, kth class vehicular events, the i-th class security level.
Step 4: sample matrix B is calculated1In in every class security level each vehicular events classification center coordinate b, expression formula
For
Wherein niIndicate the i-th class security level vehicular events quantity, bikIt is kth class basis event in the i-th class vehicular events
Centre coordinate value.
Step 5: after determining various types of vehicles event center coordinate value, then test matrix B is calculated2In various types of vehicles event
The distance of heart coordinate value obtains class distance matrix C, expression formula are as follows:
Wherein, B2ikIndicate test matrix B2In the i-th class basis event quantity, CijThe minimum corresponding j value of value is to test
Matrix B2In the security level of the i-th class basis event (pass through the affiliated safety etc. that newly-increased vehicular events are determined apart from size
Grade);QjIndicate the weight of jth class security level, the average probability p that the weight of each security level is occurred by all kinds of eventsiIt determines,
Specifically:
The occurrence frequency for calculating each event of basic event base first, then according to the every class event of security level classified calculating
Average occurrence frequency pi, according to piThe weight Q of each classification is calculated, expression formula is
Q={ Qi|Qi=1/pi, i=1,2,3,4,5.
Step 6: the test matrix B that step 6 is obtained2In each event security level and step 2 by subway
The security level of expert or professional technician's evaluation compares, and verifies the correctness of evaluation model;If evaluation is wrong,
It is modified, and revised data are increased into sample matrix, step 4 and step 5 is repeated and model is carried out more
Newly;
Step 7: security level classification is carried out to newly-increased vehicle data using updated model is verified, by expert or skill
Art person carries out selective examination review to the vehicular events safety that system divides, and repairs to the vehicular events safety to get the wrong sow by the ear
Change, and modified data are added in sample matrix, repeats step 4 and step 5 is updated model.That is the present embodiment
Model have autonomous sustainable renewal iteration ability, often have new class sample, then by being put in storage after expert evaluation, model is with sample
The increase of this quantity and it is gradually perfect, keep calculated result more accurate.
Embodiment 2
A kind of railcar safety evaluation method based on classification that above-described embodiment is proposed is applied to a specific line
Road railcar operation data is assessed, the basic event base and vehicle of failure of the standard failure Database based on vehicle
Event base evaluates security level to event each in event base by expert or professional technician, then according to by evaluating
Event sample establish security level disaggregated model and newly-increased vehicle security status evaluated.Detailed process is as follows:
1, A is enabled to indicate basic event base (as shown in table 2), B indicates vehicular events library (as shown in table 3).Here A is one
mA×nAList, B is one mB×nBList, since specific event library content is different due to operator, in this example
Middle mA=201, nA=5, mB=501, nB=9.
The basic event base of table 2
Route | Vehicle | Event | Event influences | Event type |
18 | A1 | Wheel is to scratch | Influence operation security and comfort | |
18 | A1 | Wheel is to scratch | Influence operation security and comfort | |
18 | A1 | Shelled tread | Influence operation security and comfort | |
…… | …… | …… | …… |
3 vehicular events library of table
Vehicular events library B is sampled, takes wherein that 400 row data are as sample data, remaining 100 row data are as surveying
Data are tried, B is obtained after sampling1It is the matrix of 400 rows 9 column, B2It is the matrix of 100 rows 9 column.
2, the event in basic event base A and vehicular events library B is pacified according to historical experience by expert or technician
Full property ranking, grade are divided into safe, slight, critical, critical, five class of disaster, obtain complete basic event base list A
(as shown in table 4) and vehicular events library list B (as shown in table 5).I.e.
The basic event base of table 4
Route | Vehicle | Event | Event influences | Event type |
18 | A1 | Wheel is to scratch | Influence operation security and comfort | Slightly |
18 | A1 | Wheel is to scratch | Influence operation security and comfort | It is critical |
18 | A1 | Shelled tread | Influence operation security and comfort | It is critical |
…… | …… | …… | …… | …… |
5 vehicular events library of table
3, two data matrix Bs are converted by vehicular events library list B, that is, 5 4-9 column data of table1And B2。B1For sample moment
Battle array is the 2nd to the 401 row data of table 5, B2It is the 402nd to the 501 row data of table 5 for test matrix, expression formula is respectively
4, sample data set B is calculated separately using class center calculation method1The class centre coordinate b of five class data, expression formula
It is as follows:
5, test matrix B is calculated2In every vehicular events data and step 4 calculate at a distance from gained class centre coordinate, meter
Calculate apart from when different weights, the average probability p that weighted value Q is occurred by all kinds of events need to be assigned for different classificationsiIt determines,
Obtain class distance matrix C, expression formula are as follows:
Q={ Qi|Qi=1/pi, i=1,2,3,4,5
Wherein, B2ikIndicate test matrix B2In the i-th class basis event quantity, CijThe minimum corresponding j value of value is to test
Matrix B2In the i-th class basis event security level, QjIndicate the weight of jth class security level.
6, it by step 5 classification results and expert evaluation Comparative result, verifies the accuracy of category of model and is modified.This
B in example2Category of model result and expert evaluation result it is completely the same.
7, security level classification is carried out to newly-increased vehicular events using the disaggregated model of step 4 and step 5;
8, verification amendment carried out to the security level for increasing vehicular events classification in step 7 newly, and based on correction result to point
Class model is updated.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (8)
1. a kind of railcar safety evaluation method based on classification, which is characterized in that this method comprises:
Step S1 obtains all logout basis of formation event base A occurred during railcar operation, and is basic thing
Event type label is arranged in the basic event of each in the A of part library;
Step S2 establishes vehicular events library B based on basic event base A, and is each of vehicular events library B vehicular events
Security level label is set;
Data in the B of vehicular events library are converted sample matrix B by step S31With test matrix B2;
Step S4 is based on sample matrix B1Preliminary classification model is constructed, using preliminary classification model to test matrix B2Each
Vehicular events carry out security level classification;
Step S5, the test matrix B obtained based on step S4 by disaggregated model2The security level and step S2 of each vehicular events
In the security level of corresponding setting to the step S4 preliminary classification model constructed and verified and updated.
2. a kind of railcar safety evaluation method based on classification according to claim 1, which is characterized in that described
Each basic event is provided with 5 label datas in basic event base A in step S1, successively includes route, vehicle, event number
It is influenced according to, event and event type.
3. a kind of railcar safety evaluation method based on classification according to claim 2, which is characterized in that described
Each vehicular events is provided with 9 label datas in the B of vehicular events library in step S2, successively includes time, route, vehicle, I
Class event, II class event, III class event, IV class event, V class event and security level:.
4. a kind of railcar safety evaluation method based on classification according to claim 3, which is characterized in that described
Step S3 specifically: convert two data matrix Bs for all data under the 4-9 label in the B of vehicular events library1And B2,
In, B1As sample matrix, B2As test matrix;Date expression is as follows:
R=(rijk, i=1,2,3,4,5, j=1,2 ..., n, k=1,2,3,4,5)
Wherein, i indicates security level, and j indicates vehicular events serial number, and k indicates event type;rijkIndicate j-th of vehicular events,
The data of kth class vehicular events, the i-th class security level.
5. a kind of railcar safety evaluation method based on classification according to claim 4, which is characterized in that described
Step S4 is specifically included:
Sample matrix B is calculated using clustering algorithm in step S411In in every class security level the class center of each vehicular events sit
Mark b, expression formula are as follows:
Wherein, niIndicate the i-th class security level vehicular events quantity, bikIndicate kth class base in the i-th class security level vehicular events
The centre coordinate value of plinth event;
Step S42 calculates test matrix B2In each vehicular events data and step S4 class center matrix b data that are calculated
Distance obtains class distance matrix C, expression formula are as follows:
Wherein, B2ikIndicate test matrix B2In the i-th class basis event quantity, CijThe minimum corresponding j value of value is test matrix
B2In the i-th class basis event security level, QjIndicate the weight of jth class security level.
6. a kind of railcar safety evaluation method based on classification according to claim 5, which is characterized in that all kinds of
The average probability of happening p that the weight Q of security level is occurred by all kinds of eventsiIt determines, specifically includes:
The occurrence frequency of all kinds of events in basic event base A is calculated first;
Then according to the average probability of happening p of the every class event of security level classified calculatingi;
According to average probability of happening piCalculate the weight Q of each security level:
Q={ Qi|Qi=1/pi};I=1,2,3,4,5.
7. a kind of railcar safety evaluation method based on classification according to claim 1-6, feature
It is, the step S5 is specifically included;By test matrix B2In the peace that is obtained by disaggregated model in step S4 of each vehicular events
The security level that vehicular events are arranged is corresponded in full grade separation result and step S2 to compare, and verifies the accurate of category of model
Property is simultaneously updated.
8. a kind of railcar safety evaluation method based on classification according to claim 7, which is characterized in that the party
Method further include:
Step S6 carries out security level classification to newly-increased vehicular events using the revised disaggregated model of step S5;
Step S7 carries out verification amendment to the security level for increasing vehicular events classification in step S6 newly, and will verify revised
Sample matrix is added in data, repeats step S4 and step S5 and is updated to model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910707566.0A CN110414855A (en) | 2019-08-01 | 2019-08-01 | A kind of railcar safety evaluation method based on classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910707566.0A CN110414855A (en) | 2019-08-01 | 2019-08-01 | A kind of railcar safety evaluation method based on classification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110414855A true CN110414855A (en) | 2019-11-05 |
Family
ID=68365070
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910707566.0A Pending CN110414855A (en) | 2019-08-01 | 2019-08-01 | A kind of railcar safety evaluation method based on classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110414855A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898895A (en) * | 2020-07-24 | 2020-11-06 | 重庆长安汽车股份有限公司 | Vehicle quality evaluation method and system based on big data fusion |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101119236A (en) * | 2006-07-31 | 2008-02-06 | 中国航天科技集团公司第五研究院第五一○研究所 | Network safety integrated estimation system |
CN101355504A (en) * | 2008-08-14 | 2009-01-28 | 成都市华为赛门铁克科技有限公司 | Method and apparatus for confirming user behavior |
CN102521710A (en) * | 2011-12-22 | 2012-06-27 | 上海建科工程咨询有限公司 | Building construction quality safety online risk assessment system |
CN102799822A (en) * | 2012-07-11 | 2012-11-28 | 中国信息安全测评中心 | Software running security measurement and estimation method based on network environment |
CN102999695A (en) * | 2012-10-31 | 2013-03-27 | 华中科技大学 | Subway construction safety risk identification and evaluation system and working method thereof |
CN103714387A (en) * | 2014-01-09 | 2014-04-09 | 云南电网公司电网规划研究中心 | Power grid risk refined assessment method |
US20140289796A1 (en) * | 2012-12-20 | 2014-09-25 | Bank Of America Corporation | Reconciliation of access rights in a computing system |
CN106126872A (en) * | 2015-11-02 | 2016-11-16 | 广州地铁集团有限公司 | Operation security appraisal procedure based on track traffic modularization management |
US20170149813A1 (en) * | 2015-11-20 | 2017-05-25 | Webroot Inc. | Binocular Fusion Analytics Security |
CN108345983A (en) * | 2018-01-04 | 2018-07-31 | 北京轨道交通路网管理有限公司 | The appraisal procedure of road network operation security situation and risk, device and processor |
-
2019
- 2019-08-01 CN CN201910707566.0A patent/CN110414855A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101119236A (en) * | 2006-07-31 | 2008-02-06 | 中国航天科技集团公司第五研究院第五一○研究所 | Network safety integrated estimation system |
CN101355504A (en) * | 2008-08-14 | 2009-01-28 | 成都市华为赛门铁克科技有限公司 | Method and apparatus for confirming user behavior |
CN102521710A (en) * | 2011-12-22 | 2012-06-27 | 上海建科工程咨询有限公司 | Building construction quality safety online risk assessment system |
CN102799822A (en) * | 2012-07-11 | 2012-11-28 | 中国信息安全测评中心 | Software running security measurement and estimation method based on network environment |
CN102999695A (en) * | 2012-10-31 | 2013-03-27 | 华中科技大学 | Subway construction safety risk identification and evaluation system and working method thereof |
US20140289796A1 (en) * | 2012-12-20 | 2014-09-25 | Bank Of America Corporation | Reconciliation of access rights in a computing system |
CN103714387A (en) * | 2014-01-09 | 2014-04-09 | 云南电网公司电网规划研究中心 | Power grid risk refined assessment method |
CN106126872A (en) * | 2015-11-02 | 2016-11-16 | 广州地铁集团有限公司 | Operation security appraisal procedure based on track traffic modularization management |
US20170149813A1 (en) * | 2015-11-20 | 2017-05-25 | Webroot Inc. | Binocular Fusion Analytics Security |
CN108345983A (en) * | 2018-01-04 | 2018-07-31 | 北京轨道交通路网管理有限公司 | The appraisal procedure of road network operation security situation and risk, device and processor |
Non-Patent Citations (1)
Title |
---|
宋伟: "广州地铁1号线故障诊断***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 (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898895A (en) * | 2020-07-24 | 2020-11-06 | 重庆长安汽车股份有限公司 | Vehicle quality evaluation method and system based on big data fusion |
CN111898895B (en) * | 2020-07-24 | 2023-06-13 | 重庆长安汽车股份有限公司 | Vehicle quality evaluation method and system based on big data fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP4030365A1 (en) | Multi-mode multi-service rail transit analog simulation method and system | |
JP6889059B2 (en) | Information processing equipment, information processing methods and computer programs | |
CN109689470B (en) | Abnormality diagnosis device, abnormality diagnosis method, and computer program | |
WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
Cárdenas-Gallo et al. | An ensemble classifier to predict track geometry degradation | |
Castillo* et al. | A Markovian–Bayesian network for risk analysis of high speed and conventional railway lines integrating human errors | |
US20120203402A1 (en) | Intelligent Railway System for Preventing Accidents at Railway Passing Points and Damage to the Rail Track | |
Szwarc et al. | Problems of railway noise—a case study | |
Seo et al. | Bridge rating protocol using ambient trucks through structural health monitoring system | |
CN113324648B (en) | Portable high-speed railway wheel rail vibration space-time synchronization test method and system | |
Xu et al. | Optimizing the alignment of inspection data from track geometry cars | |
CN111680940A (en) | Regional rail transit network safety level evaluation method and system | |
CN108345983A (en) | The appraisal procedure of road network operation security situation and risk, device and processor | |
CN107609317A (en) | A kind of steel bridge fatigue evaluation load modeling and Fatigue Assessment method | |
CN109767075A (en) | A kind of urban mass transit network train operation reliability estimation method | |
CN109791677A (en) | System and method for carrying out Geographic Reference and scoring to vehicle data in community | |
CN110414855A (en) | A kind of railcar safety evaluation method based on classification | |
Bridgelall | Characterizing ride quality with a composite roughness index | |
CN112434950A (en) | Method for canceling freight car charging adjustment risk assessment of provincial charging station and application | |
CN114707284B (en) | High-speed railway section throughput simulation computing system | |
CN111832834B (en) | Airport pavement service performance prediction method and device and electronic equipment | |
Chen et al. | Development of macroscopic emission estimation model based on microscopic operating modes | |
CN112033335A (en) | Intelligent monitoring and early warning system and method for railway gauging rule | |
Boriboonsomsin et al. | Improvements to on-road emission modeling of freeways with high-occupancy vehicle facilities | |
Babu | Quantifying the Fatigue Damage Accumulation in Bridges |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
RJ01 | Rejection of invention patent application after publication |