CN105954607A - Method and system for detecting faults of high-speed railway signal system - Google Patents
Method and system for detecting faults of high-speed railway signal system Download PDFInfo
- Publication number
- CN105954607A CN105954607A CN201610252220.2A CN201610252220A CN105954607A CN 105954607 A CN105954607 A CN 105954607A CN 201610252220 A CN201610252220 A CN 201610252220A CN 105954607 A CN105954607 A CN 105954607A
- Authority
- CN
- China
- Prior art keywords
- node
- test
- tested
- fault
- tested node
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention discloses a method and system for detecting the faults of a high-speed railway signal system. The method for detecting the faults of a high-speed railway signal system comprises steps of: determining testing nodes and tested nodes; instructing each testing node to send testing tasks to the tested nodes and to record testing responses fed back from the tested nodes; counting the testing responses received by the testing nodes and forming a fault characteristic matrix; and analyzing the fault characteristic matrix by using an artificial immune algorithm in order to position a current fault node in the high-speed railway signal system.
Description
Technical field
The invention belongs to high-speed railway signaling system security control and monitoring technical field, particularly relate to a kind of high
Ferrum signaling system fault detection method and system.
Background technology
Bullet train knocks into the back and the accident of advancing rashly happens occasionally, high ferro signaling system fail to diagnose rapidly and accurately and
Location fault is one of reason.At present, signaling system is various signalling arrangement and subsystem and auxiliary equipment thereof
Integrated, it lays particular emphasis on the interfacing between distinct device or subsystem, and the letter of unlike signal manufacturer
Number equipment interconnecting when constituting system, lacks the mutually test between each subsystem and checking.Signal
The problem that system failure detection exists is as follows:
(1) fault detect and location concentrate on certain equipment or device aspect, track circuit, transponder,
Signaling at stations equipment and computer interlock subsystem etc. are main fault detect object.Various set with signal
Standby supporting maintenance management terminal mainly considers this equipment state and fault detect, function singleness.But, letter
Number system is one and interconnects, and has the system of altitude information interaction characteristic, a certain device or the event of equipment
Barrier very likely produces impact to other equipment being connected, and at present to the fault detect of device and device level without
Method takes into full account the contact between signaling system and impact, once fault location or process from the angle that system is overall
Not in time, it is easy to make failure propagation, the most serious consequence is caused.
(2) degree of intelligence of fault detect is the highest.Although the storage of existing signaling system has substantial amounts of history to detect
Data and fault data, but all in all, lack the excavation to data and recycling, especially to fault
The analysis of data.Major part fault detect and location rely on artificial judgment, inefficiency, it is impossible to comprehensive utilization
Various information, realize intelligent trouble detection with diagnosis policy flexibly.
Therefore, from fault detect and the location of system level research high ferro signaling system, and intelligent algorithm is used
Solve decision system fault, make system make the response of reply fault in time, to ensureing train operating safety tool
There is important meaning.
Summary of the invention
The embodiment of the present invention provides a kind of high ferro signaling system fault detection method and system, in order to from system layer
Face realizes fault detect and the location of high ferro signaling system, it is ensured that traffic safety.
On the one hand, the embodiment of the present application provides a kind of high ferro signaling system fault detection method, including:
Determine multiple test node and multiple tested node;Order each described test node respectively to described
Multiple tested nodes send test assignment, and record the test response of the plurality of tested node feeding back;Statistics
The test that the plurality of test node receives responds and forms fault signature matrix;Pass through Artificial Immune Algorithm
Described fault signature matrix is analyzed, to position the malfunctioning node in current high ferro signaling system.
Alternatively, each described test node of mentioned order sends test to the plurality of tested node respectively
Task includes:
Each described test node is ordered to send test patterns, described test to the plurality of tested node respectively
Code represents the test assignment determined according to fault experts database and signaling system function.
Alternatively, the above-mentioned test response recording the plurality of tested node feeding back includes:
If described test node receives the test result of tested node feeding back and the prestored information of this test node
Unanimously, then it is normal for recording this tested node;
If described test node receives the test result of tested node feeding back and the prestored information of this test node
Inconsistent, then recording this tested node is fault.
Further, above-mentioned test assignment comprises timestamp, and described test node and described tested node
Timestamp keep consistent;Then,
The described test response recording the plurality of tested node feeding back includes:
If described test node receives the consistent with prestored information of tested node feeding back at the appointed time
Test result, then it is normal for recording this tested node;
If described test node do not receive at the appointed time tested node feeding back test result or
Receive the test result inconsistent with prestored information in stipulated time, then recording this tested node is fault.
Further, the described test response recording the plurality of tested node feeding back also includes:
If without communication connection between described test node and tested node, then recording this test node tested with this
Without test relation between node.
Alternatively, it is analyzed including to described fault signature matrix above by Artificial Immune Algorithm:
The test result that each tested node is corresponding, each of which is extracted from described fault signature matrix
The test result that described tested node is corresponding is considered as one group of test result;
One group the most compatible with the current failure disease of described high ferro signaling system is determined by Artificial Immune Algorithm
Test result, tested node corresponding to this group test result is described malfunctioning node.
On the other hand, the embodiment of the present application additionally provides a kind of high ferro signaling system fault detection system, including:
Node screening unit, is used for determining multiple test node and multiple tested node;
Test cell, is used for ordering each described test node to send to the plurality of tested node respectively and surveys
Trial is engaged in, and records the test response of the plurality of tested node feeding back;
Statistic unit, the test received for adding up the plurality of test node responds and forms fault signature
Matrix;
Analytic unit, for being analyzed described fault signature matrix by Artificial Immune Algorithm, with location
Malfunctioning node in current high ferro signaling system.
Alternatively, above-mentioned test cell includes testing module;This test module is used for ordering each described survey
Examination node sends test patterns to the plurality of tested node respectively, and described test patterns represents according to fault experts database
The test assignment determined with signaling system function.
Alternatively, above-mentioned test cell includes judge module and logging modle;
Described judge module is for judging that test node receives test result and this test of tested node feeding back
The prestored information of node is the most consistent;
If consistent, this tested node of the most described logging modle record is normal;If inconsistent, the most described record
This tested node of module record is fault.
Further, described test assignment comprises timestamp, and described test node and described tested node
Timestamp keep consistent;
Described judge module is for judging that test node receives tested node feeding back the most at the appointed time
The test result consistent with prestored information;
If described test node receives tested node feeding back and described prestored information one at the appointed time
The test result caused, this tested node of the most described logging modle record is normal;Otherwise, described logging modle
Recording this tested node is fault.
Further, if without communication connection, the most described logging modle between described test node and tested node
Record between this test node and this tested node without test relation.
Alternatively, above-mentioned analytic unit includes:
Extraction module, for extracting the test knot that each tested node is corresponding from described fault signature matrix
Really, the test result that tested node described in each of which is corresponding is considered as one group of test result;
Determine module, for being determined and the current failure disease of described high ferro signaling system by Artificial Immune Algorithm
Waiting one group of the most compatible test result, tested node corresponding to this group test result is described malfunctioning node.
The high ferro signaling system fault detection method of embodiment of the present invention offer and system, diagnose from system level
The fault of high ferro signaling system, by setting up signaling system Fault Model, uses Artificial Immune Algorithm to ask
Solve model and draw malfunctioning node, and then take the measure of necessity to tackle fault, form a set of efficient intelligence
Fault detection method.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the high ferro signaling system fault detection method provided in the embodiment of the present invention;
Fig. 2 is the high ferro signaling system test schematic diagram in the embodiment of the present invention;
Fig. 3 is that the signaling system Fault Model in the embodiment of the present invention sets up block diagram;
Fig. 4 is that Artificial Immune Algorithm solves signaling system fault model flow chart;
Fig. 5 is the structural representation of the high ferro signaling system fault detection system in the embodiment of the present invention;
Fig. 6 is the schematic diagram of the test cell in Fig. 5;
Fig. 7 is the schematic diagram of the analytic unit in Fig. 5.
Detailed description of the invention
Below in conjunction with the accompanying drawings, elaborate to being preferable to carry out example.It is emphasized that the description below is only
It is only exemplary rather than in order to limit the scope of the present invention and application thereof.
High ferro signaling system level fault detect and location are broadly divided into two stages: test phase and detection-phase
(also referred to as diagnostic phases).Test phase sets up system detection model according to the feature of signaling system, and formulates
Corresponding test order, to obtain the test result between system interior joint;Detection-phase then according to test result,
Find suitable detection algorithm, solve and draw malfunctioning node.It should be noted that after drawing test result,
The necessity of detection process is: in test process, has malfunctioning node and participates in the phenomenon of test, so
Insecure test result can be caused, so to be rejected the test knot of mistake further by detection algorithm
Really, and all results are analysed scientifically, draw the final malfunction of system interior joint.
For the problems referred to above, embodiments provide a kind of high ferro signaling system fault detection method and be
System.
Shown in accompanying drawing 1, the high ferro signaling system fault detection method provided in the embodiment of the present invention, bag
Include:
S101, determines multiple test node and multiple tested node.
This step can be selected based on experience value by tester, it is also possible to by system automatically according to historical data
Carry out match selection.
S102, orders each test node to send test assignment to the plurality of tested node respectively, and remembers
Record the test response of the plurality of tested node feeding back.
In this step, each test node is ordered to send the shape of test assignment respectively to multiple tested nodes
Formula can be but not limited to, and orders each described test node to send to the plurality of tested node respectively
Test patterns, described test patterns represents the test assignment determined according to fault experts database and signaling system function.
In this step, the rule of the test response recording multiple tested node feeding back includes but not limited to:
The test result of tested node feeding back is compared with the prestored information in test node, if test joint
The test result that point receives tested node feeding back is consistent with the prestored information of this test node, then record this quilt
It is normal for surveying node;If described test node receives test result and this test node of tested node feeding back
Prestored information inconsistent, then recording this tested node is fault.
Further, if above-mentioned test assignment comprises timestamp, and described test node and described tested
The timestamp of node keeps consistent;So, tested node feeding back is received at the appointed time at test node
Consistent with prestored information test result time, it is normal for recording this tested node;At described test node
Do not receive at the appointed time the test result of tested node feeding back or receive at the appointed time with
During the inconsistent test result of prestored information, recording this tested node is fault.
S103, adds up the test that the plurality of test node receives and responds and form fault signature matrix.
S104, is analyzed described fault signature matrix by Artificial Immune Algorithm, to position current high ferro
Malfunctioning node in signaling system.
In this step, it is analyzed including to described fault signature matrix by Artificial Immune Algorithm:
The test result that each tested node is corresponding, each of which is extracted from described fault signature matrix
The test result that described tested node is corresponding is considered as one group of test result;Determined by Artificial Immune Algorithm and institute
Stating one group of test result that the current failure disease of high ferro signaling system is the most compatible, this group test result is corresponding
Tested node is described malfunctioning node.
Below in conjunction with actual high ferro signaling system, above-mentioned fault detection method is illustrated.
The first step, sets up the Fault Model of high ferro signaling system Same Scene same time。
High ferro signaling system is a complicated big system, by Train operation control system (CTCS,
Chinese Train Control System), interlock system (CBI, Computer based
Interlocking), three subsystems of dispatching concentration (CTC, Centralized Traffic Control)
System and aid system are constituted.Each subsystem and functions of the equipments differ greatly, and the direction of data stream is the most different, both
There is one-way transmission, also have transmitted in both directions.Equipment component has two-way communications capabilities, can be to be mutually measured with information altogether
Offer passage, such as CTC, RBC (Radio Block Center), TCC (Train Control are provided
Center)、TSRS(Temporary Speed Restriction Server)、CBI、ATP(Automatic
Train Protection) etc., this kind equipment can be as bidirectional nodes, and can not only be used for tester also can conduct
Testee;Equipment component, such as track circuit and transponder, do not possess the ability of computational analysis, can only
As unidirectional node, i.e. as testee.The embodiment of the present invention is right in original system level fault detect theory
On the basis of node definition, extract the node of signaling system as test node and tested joint according to historical data
Point.After determining signaling system test node, use for reference fault information of expert database and information interaction characteristic, clearly
Internodal mutual test assignment.Wherein, fault information of expert database be mainly system record expertise amass
Tired, when which feature train operating data present, fault trend or fault can be determined with.Will
Signaling system mobile unit replaces with vehicle-mounted ATP, and the structure of basis signal system, sets up signaling system and surveys
Attempt as shown in Figure 2.In Fig. 2, each circle represents a test node, and four-headed arrow represents connection
Two nodes between can mutually test;Node pointed by unidirectional arrow, only as testee.
CTCS-3 level train control system is according to operation demand, and having drives a vehicle permits, registers and start, grade turns
14 operation scenes such as change.Select one of them to run scene, limit between each subsystem of signaling system
Information is alternately under Same Scene.So, the interaction data between each subsystem and equipment is all served same
Individual systemic-function, data are complete and contact closely, established the base of mutually test between signaling system node
Plinth.
Whole signaling system uses NTP (Network Time Protocol) agreement to keep between subsystem
Clock synchronizes.Containing timestamp in the interactive information of each node of system test figure, so, using timestamp as
Determine an important indicator of test result.The timestamp of each node derives from same clock, thereby guarantees that
Fault Model is set up on same time reference.Consider the factor such as physical transfer, calculation delay, in advance
Determine an acceptable time interval, if the timestamp of tested node is in acceptable time interval,
Then think that test result is credible, otherwise it is assumed that tested node failure.Whole signaling system Fault Model
Set up block diagram as shown in Figure 3.The process that signaling system performs to be mutually measured is: 1. in existing signaling system in advance
Implant software test module;2. test node sends a series of test patterns to tested node, wherein, test patterns
The implication represented is the test assignment determined according to fault experts database and signaling system function;The most tested node returns
Feed back out response;4. whether test node compares the output response of return and is consistent with expected results, from test joint
The angle of point judges tested node whether fault.In addition to track circuit and transponder, miscellaneous equipment is implanted soft
Part test module.As a example by driving permissions scenarios, test process is described.RBC is according to the temporary speed limitation of circuit
Information, the positional information of train, track circuit occupied information and route information etc., generate driving license
MA(Movement Authority).Finally, the MA that vehicle-mounted ATP sends with reference to RBC, to driving license
Carry out supervision, generate braking mode curve simultaneously and control the operation of train.In this process, RBC calculates
The Back ground Information that generating MA needs has temporary speed limitation information, train position information, route information, track electricity
Road occupied information etc..Wherein, RBC and TCC can obtain temporary speed limitation information simultaneously, and the former can be by soft
Part test module latter sends test assignment, and TCC returns test result, and RBC compares the limit of test result
Speed position, time, speed limit are the most consistent with the speed-limiting messages of self.If consistent, output node is normal
Object information;If inconsistent, the object information of output TCC fault.In like manner, train position information, route
Information, track circuit occupied information also can be judged by similar method.
Collect Same Scene, the test result of same time, draw fault signature matrix according to PMC rule.
Now, the fault signature matrix drawn is referred to as test invalidation model, as it is possible that malfunctioning node take part in survey
Examination process so that test result is insincere.So, also need to by algorithm science after having had test result
Ground is analyzed and is determined final malfunctioning node.
Second step, solves fault model based on Artificial Immune Algorithm。
The purpose of system-level malfunction detection is exactly to find the unique fault mode compatible with disease.The present invention implements
Example uses Artificial Immune Algorithm to solve fault model.Fault signature matrix is as input, with the intelligence of this algorithm
Property and the most appropriate fault mode of adaptability Automatic-searching.
Artificial immune system is as follows with the similitude of high ferro signaling system fault detect: signaling system fault detect
Purpose be for comprehensive much information identification normal node and malfunctioning node, and then malfunctioning node is reported
Police or reparation;Immune function is to identify the own cells in body and non-own cell, and produces spy
Determine antibody and eliminate antigen, it is achieved immunity.In high ferro signaling system, each fault set is by a phase therewith
The fault disease held uniquely determines, this disease compatible with fault set shows as antibody in immune system and knows
The specificity structure of the antigen molecule of other antigen institute foundation.In system, the state set of all nodes is referred to as system
Fault mode, the test result collection of all nodes is collectively referred to as the disease of system.
It is as shown in table 1 that high ferro signaling system a certain moment node is mutually measured result, i.e. obtains the test of signaling system
Invalid model.
Certain moment signaling system of table 1 is mutually measured result
In table 1, first trip represents test node, and first represents tested node, and test result is according to shown in table 2
PMC rule identify, additionally, both without test relations be denoted as-1.Table 1 entirety regards certain equipment fault as
Time corresponding fault disease, certain faulty equipment is a fault set, is equivalent to an antigen;Every string phase
The result of test is a fault mode mutually, is equivalent to an antibody.
Table 2PMC rule
After obtaining signaling system test result, i.e. fault signature matrix, Artificial Immune Algorithm is utilized to solve square
Battle array, positions definite malfunctioning node.As shown in Figure 4, step is as follows for idiographic flow:
1st step: initialize population antibody POP.Utilizing function to randomly generate, that a radix is x is potential anti-
Body.Number N of Population Size, i.e. antibody represents.In the population POP of such as stochastic generation, Qi Zhongyi
Individual antibody is (00000010), x=8, and the node being corresponding in turn to is: CTC, CBI, ATP, RBC, TCC,
TSRS, track circuit, transponder.Wherein, 0 represents that node is normal, and 1 represents node failure.
2nd step: calculate affinity.
In calculating initial population, each fault mode is about the affinity degree of input fault disease, it may be assumed that calculate initial
The affinity of fault signature matrix shown in population POP and table 1.Definition antibody abiWith abkBetween affinity
For
In formula, | | * | | represents Euclidean distance, and N represents antibody number.Above formula shows, antibody and antibody are spatially
Distance is the least, and its affinity is the biggest, stimulates or inhibitory action is the strongest between antibody.
3rd step: clone.
Select the antibody that α affinity is the highest, constitute a new set.
Antibody in antibody population POP is pressed affinity size descending, obtains: Abs={ab1,
ab2,…,abN, and aff (abi)>aff(abi+1), i=1,2 ..., it is big that N-1. chooses affinity from Abs
α the antibody in meansigma methods T constitutes a new set, definition
Cloning this α best individuality, expand antibody population, the scale of clone becomes with the size of affinity
Direct ratio.
4th step: variation.
The mutation operator of structure Multiple Antibodies: transposition operator, shift operator, inversion operator.
Transposition operator: randomly select two characters in antibody character string and exchange its position and form new antibody.
Shift operator: randomly select a substring in antibody character string, circulation left (right) moves this substring and is formed
New antibody.
Inversion operator: randomly select a substring in antibody character string, head and the tail overturn this substring and form new resisting
Body.
Select one or more mutation operators, from clone body, randomly select antibody character string carry out gene change
Different, form new antibody population CLONE*, the probability of gene mutation is inversely proportional to the size of affinity.
5th step: reselect best antibody (fault mode).
Recalculate new population CLONE*The affinity of middle antibody, according to the 3rd step method choice affinity
The population POP that high antibody composition is new*。
6th step: replace worst antibody.
POP is replaced with the new antibodies randomly generated*Middle affinity comes some antibody of rear 10%.
7th step: evaluation algorithm terminates.
When finding an antibody ab ∈ POP*Time consistent with antigen (physical fault set), algorithm terminates.
Output antibody ab=(00010000), the node being corresponding in turn to is: CTC, CBI, ATP, RBC,
TCC, TSRS, track circuit, transponder.Therefore deduce that RBC fault.
Trying to achieve correct fault mode according to as above step is RBC fault.In actual test process,
Obtain similar test result shown in table 1, fault vectors can be tried to achieve according to as above algorithm.Determine fault
After node, signaling system can make following response according to the extent of injury of fault level and fault: stops row
Car runs, changes train operation, signaling system reconstruct and maintenance of equipment etc..
The embodiment of the present invention additionally provides a kind of in order to realize above-mentioned high ferro signaling system fault detection method
System.As it is shown in figure 5, the high ferro signaling system fault detection system 50 that the embodiment of the present invention provides includes:
Node screening unit 51, is used for determining multiple test node and multiple tested node;
Test cell 52, is used for ordering each described test node to send to the plurality of tested node respectively
Test assignment, and record the test response of the plurality of tested node feeding back;
Statistic unit 53, the test received for adding up the plurality of test node responds and forms fault spy
Levy matrix;
Analytic unit 54, for being analyzed described fault signature matrix by Artificial Immune Algorithm, with fixed
Malfunctioning node in the current high ferro signaling system in position.
Alternatively, as shown in Figure 6, above-mentioned test cell 52 includes testing module;This test module is used for ordering
Making each described test node send test patterns to the plurality of tested node respectively, described test patterns represents
The test assignment determined according to fault experts database and signaling system function.
Alternatively, as shown in Figure 6, above-mentioned test cell 52 includes judge module and logging modle;
Described judge module is for judging that test node receives test result and this test of tested node feeding back
The prestored information of node is the most consistent;
If consistent, this tested node of the most described logging modle record is normal;If inconsistent, the most described record
This tested node of module record is fault.
Further, described test assignment comprises timestamp, and described test node and described tested node
Timestamp keep consistent;
Described judge module is for judging that test node receives tested node feeding back the most at the appointed time
The test result consistent with prestored information;
If described test node receives tested node feeding back and described prestored information one at the appointed time
The test result caused, this tested node of the most described logging modle record is normal;Otherwise, described logging modle
Recording this tested node is fault.
Further, if without communication connection, the most described logging modle between described test node and tested node
Record between this test node and this tested node without test relation.
Alternatively, as it is shown in fig. 7, above-mentioned analytic unit 54 includes:
Extraction module, for extracting the test knot that each tested node is corresponding from described fault signature matrix
Really, the test result that tested node described in each of which is corresponding is considered as one group of test result;
Determine module, for being determined and the current failure disease of described high ferro signaling system by Artificial Immune Algorithm
Waiting one group of the most compatible test result, tested node corresponding to this group test result is described malfunctioning node.
The high ferro signaling system fault detection method of embodiment of the present invention offer and system, diagnose from system level
The fault of high ferro signaling system, by setting up signaling system Fault Model, uses Artificial Immune Algorithm to ask
Solve model and draw malfunctioning node, and then take the measure of necessity to tackle fault, form a set of efficient intelligence
Fault detection method.
The above, the only present invention preferably detailed description of the invention, but protection scope of the present invention not office
Being limited to this, any those familiar with the art, can be easily in the technical scope that the invention discloses
The change expected or replacement, all should contain within protection scope of the present invention.Therefore, the protection of the present invention
Scope should be as the criterion with scope of the claims.
Claims (12)
1. a high ferro signaling system fault detection method, it is characterised in that including:
Determine multiple test node and multiple tested node;
Each described test node is ordered to send test assignment, and record to the plurality of tested node respectively
The test response of the plurality of tested node feeding back;
Add up the test that the plurality of test node receives respond and form fault signature matrix;
By Artificial Immune Algorithm, described fault signature matrix is analyzed, to position current high ferro signal system
Malfunctioning node in system.
Method the most according to claim 1, it is characterised in that each described test joint of described order
Point sends test assignment to the plurality of tested node respectively and includes:
Each described test node is ordered to send test patterns, described test to the plurality of tested node respectively
Code represents the test assignment determined according to fault experts database and signaling system function.
Method the most according to claim 1, it is characterised in that described record the plurality of tested node
The test response of feedback includes:
If described test node receives the test result of tested node feeding back and the prestored information of this test node
Unanimously, then it is normal for recording this tested node;
If described test node receives the test result of tested node feeding back and the prestored information of this test node
Inconsistent, then recording this tested node is fault.
Method the most according to claim 3, it is characterised in that comprise timestamp in described test assignment,
And described test node keeps consistent with the timestamp of described tested node;
The described test response recording the plurality of tested node feeding back includes:
If described test node receives the consistent with prestored information of tested node feeding back at the appointed time
Test result, then it is normal for recording this tested node;
If described test node do not receive at the appointed time tested node feeding back test result or
Receive the test result inconsistent with prestored information in stipulated time, then recording this tested node is fault.
5. according to the method described in claim 3 or 4, it is characterised in that described record the plurality of tested
The test response of node feeding back also includes:
If without communication connection between described test node and tested node, then recording this test node tested with this
Without test relation between node.
Method the most according to claim 1, it is characterised in that described by Artificial Immune Algorithm to institute
State fault signature matrix to be analyzed including:
The test result that each tested node is corresponding, each of which is extracted from described fault signature matrix
The test result that described tested node is corresponding is considered as one group of test result;
One group the most compatible with the current failure disease of described high ferro signaling system is determined by Artificial Immune Algorithm
Test result, tested node corresponding to this group test result is described malfunctioning node.
7. a high ferro signaling system fault detection system, it is characterised in that including:
Node screening unit, is used for determining multiple test node and multiple tested node;
Test cell, is used for ordering each described test node to send to the plurality of tested node respectively and surveys
Trial is engaged in, and records the test response of the plurality of tested node feeding back;
Statistic unit, the test received for adding up the plurality of test node responds and forms fault signature
Matrix;
Analytic unit, for being analyzed described fault signature matrix by Artificial Immune Algorithm, with location
Malfunctioning node in current high ferro signaling system.
System the most according to claim 7, it is characterised in that described test cell includes testing module;
Described test module is used for ordering each described test node to send to the plurality of tested node respectively
Test patterns, described test patterns represents the test assignment determined according to fault experts database and signaling system function.
System the most according to claim 7, it is characterised in that described test cell includes judge module
And logging modle;
Described judge module is for judging that test node receives test result and this test of tested node feeding back
The prestored information of node is the most consistent;
If consistent, this tested node of the most described logging modle record is normal;If inconsistent, the most described record
This tested node of module record is fault.
System the most according to claim 9, it is characterised in that comprise the time in described test assignment
Stamp, and described test node is consistent with the holding of the timestamp of described tested node;
Described judge module is for judging that test node receives tested node feeding back the most at the appointed time
The test result consistent with prestored information;
If described test node receives tested node feeding back and described prestored information one at the appointed time
The test result caused, this tested node of the most described logging modle record is normal;Otherwise, described logging modle
Recording this tested node is fault.
11. according to the system described in claim 9 or 10, it is characterised in that
If without communication connection, the most described this test of logging modle record between described test node and tested node
Without test relation between node and this tested node.
12. systems according to claim 7, it is characterised in that described analytic unit includes:
Extraction module, for extracting the test knot that each tested node is corresponding from described fault signature matrix
Really, the test result that tested node described in each of which is corresponding is considered as one group of test result;
Determine module, for being determined and the current failure disease of described high ferro signaling system by Artificial Immune Algorithm
Waiting one group of the most compatible test result, tested node corresponding to this group test result is described malfunctioning node.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510772764 | 2015-11-12 | ||
CN2015107727647 | 2015-11-12 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105954607A true CN105954607A (en) | 2016-09-21 |
Family
ID=56914750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610252220.2A Pending CN105954607A (en) | 2015-11-12 | 2016-04-21 | Method and system for detecting faults of high-speed railway signal system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105954607A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107861026A (en) * | 2017-11-02 | 2018-03-30 | 湖北工业大学 | A kind of electrical power distribution network fault location method based on hybrid artificial immune system |
CN109656228A (en) * | 2018-12-04 | 2019-04-19 | 江苏大学 | A kind of subway signal system onboard equipment fault automatic diagnosis method |
CN110689643A (en) * | 2019-09-24 | 2020-01-14 | 长安大学 | Intelligent networking automobile vehicle running state analysis method based on immune algorithm |
CN113218433A (en) * | 2021-03-31 | 2021-08-06 | 桂林电子科技大学 | Sensor fault detection and data restoration method based on time-varying graph signal processing |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5315520A (en) * | 1991-09-06 | 1994-05-24 | Westinghouse Air Brake Company | Friction brake interface health check system for multiple-axle railway vehicles |
TW201001907A (en) * | 2008-06-20 | 2010-01-01 | Univ Shu Te | Design method of multi-dimensional digital filter |
CN101968853A (en) * | 2010-10-15 | 2011-02-09 | 吉林大学 | Improved immune algorithm based expression recognition method for optimizing support vector machine parameters |
CN103345207A (en) * | 2013-05-31 | 2013-10-09 | 北京泰乐德信息技术有限公司 | Mining analyzing and fault diagnosis system of rail transit monitoring data |
CN103955556A (en) * | 2014-03-27 | 2014-07-30 | 北京交通大学 | Fault logical modeling method for high speed railway train operation control vehicle-mounted system |
CN104714538A (en) * | 2015-01-21 | 2015-06-17 | 中国铁路总公司 | Intelligent trouble diagnostic device and diagnostic method for railway signal system |
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 |
-
2016
- 2016-04-21 CN CN201610252220.2A patent/CN105954607A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5315520A (en) * | 1991-09-06 | 1994-05-24 | Westinghouse Air Brake Company | Friction brake interface health check system for multiple-axle railway vehicles |
TW201001907A (en) * | 2008-06-20 | 2010-01-01 | Univ Shu Te | Design method of multi-dimensional digital filter |
CN101968853A (en) * | 2010-10-15 | 2011-02-09 | 吉林大学 | Improved immune algorithm based expression recognition method for optimizing support vector machine parameters |
CN103345207A (en) * | 2013-05-31 | 2013-10-09 | 北京泰乐德信息技术有限公司 | Mining analyzing and fault diagnosis system of rail transit monitoring data |
CN103955556A (en) * | 2014-03-27 | 2014-07-30 | 北京交通大学 | Fault logical modeling method for high speed railway train operation control vehicle-mounted system |
CN104714538A (en) * | 2015-01-21 | 2015-06-17 | 中国铁路总公司 | Intelligent trouble diagnostic device and diagnostic method for railway signal system |
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 |
Non-Patent Citations (3)
Title |
---|
YUAN JIN SHA ET.AL: "Artificial Immune Algorithm for Fault Diagnosis of Power Transformer", 《2008 IEEE INTERNATIONAL SYMPOSIUM ON KNOWLEDGE ACQUISITION AND MODELING WORKSHOP》 * |
赵青鹤: "高铁信号系统的系统级故障诊断方法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
闫少华: "基于人工免疫方法的系统级故障诊断研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107861026A (en) * | 2017-11-02 | 2018-03-30 | 湖北工业大学 | A kind of electrical power distribution network fault location method based on hybrid artificial immune system |
CN107861026B (en) * | 2017-11-02 | 2019-11-08 | 湖北工业大学 | A kind of electrical power distribution network fault location method based on hybrid artificial immune system |
CN109656228A (en) * | 2018-12-04 | 2019-04-19 | 江苏大学 | A kind of subway signal system onboard equipment fault automatic diagnosis method |
CN110689643A (en) * | 2019-09-24 | 2020-01-14 | 长安大学 | Intelligent networking automobile vehicle running state analysis method based on immune algorithm |
CN110689643B (en) * | 2019-09-24 | 2022-07-26 | 长安大学 | Intelligent networking automobile vehicle driving state analysis method based on immune algorithm |
CN113218433A (en) * | 2021-03-31 | 2021-08-06 | 桂林电子科技大学 | Sensor fault detection and data restoration method based on time-varying graph signal processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106202886B (en) | Track circuit red band Fault Locating Method based on fuzzy coarse central and decision tree | |
CN103955556B (en) | High Speed Train Operation Control onboard system fault logic modeling method | |
CN105954607A (en) | Method and system for detecting faults of high-speed railway signal system | |
CN103001328B (en) | Fault diagnosis and assessment method of intelligent substation | |
Saar et al. | Automatic asphalt pavement crack detection and classification using neural networks | |
CN103617469B (en) | Power system device failure prediction method and system | |
CN105183952B (en) | A kind of power transmission network method for diagnosing faults based on separation time Fuzzy Petri Net | |
CN106802862A (en) | Train operation control system security critical software automatically testing platform | |
CN107054410A (en) | The intelligent diagnosis system and diagnostic method of point machine | |
CN107796602A (en) | A kind of circuit breaker failure diagnostic method of sound and vibration signal fused processing | |
CN107340766B (en) | Power scheduling alarm signal text based on similarity sorts out and method for diagnosing faults | |
CN103714348A (en) | Rail transit fault diagnosis method and system based on decision-making tree | |
CN110850232B (en) | Power grid fault diagnosis system and method based on relay protection auxiliary decision system | |
CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
CN109633370B (en) | Power grid fault diagnosis method based on fault information coding and fusion method | |
CN106646030A (en) | Power grid fault diagnosis method and device based on multiple data sources and expert rule base | |
CN106446245A (en) | Intelligent substation secondary device integrated drawing document system and managing and implementing method thereof | |
CN108537259A (en) | Train control on board equipment failure modes and recognition methods based on Rough Sets Neural Networks model | |
CN104460651B (en) | A kind of ZC based on autonomous learning double is delay machine fault early warning method and device | |
CN109740772A (en) | Railroad train Measuring error analysis method based on big data | |
CN112231201B (en) | Batch automatic regression testing method and system for autonomous machine function of CTC (computer control system) | |
Zheng et al. | Research on fault detection for ZPW-2000A jointless track circuit based on deep belief network optimized by improved particle swarm optimization algorithm | |
CN102802182A (en) | Fault diagnosis device and method for wireless sensor network | |
CN106324429A (en) | RS-IA data mining-based power distribution network fault locating method | |
CN114167217B (en) | Multiple fault diagnosis method for railway distribution network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20160921 |
|
RJ01 | Rejection of invention patent application after publication |