CN102879680A - Rail transit vehicle equipment universal detection and fault diagnosis method and system - Google Patents
Rail transit vehicle equipment universal detection and fault diagnosis method and system Download PDFInfo
- Publication number
- CN102879680A CN102879680A CN2012103634160A CN201210363416A CN102879680A CN 102879680 A CN102879680 A CN 102879680A CN 2012103634160 A CN2012103634160 A CN 2012103634160A CN 201210363416 A CN201210363416 A CN 201210363416A CN 102879680 A CN102879680 A CN 102879680A
- Authority
- CN
- China
- Prior art keywords
- fault
- fault diagnosis
- rule
- expert system
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a rail transit vehicle equipment universal detection and fault diagnosis method and a system thereof. The method comprises the following steps: signals acquired through a data acquisition module are input to a fault diagnosis module to obtain a fault diagnosis conclusion; an expert system rule base is arranged in the fault diagnosis module; and a plurality of rules relevant to faults are stored in the expert system rule base; the expert system rule base adopts fault trees to represent the interrelationship of the various rules; a fault diagnosis process is served as a data matching process based on importance degree; the acquired data and the rules in the expert system rule base are matched from the highest importance degree to the lowest importance degree; if the matching is successful, a matching result is output and a fault conclusion is given out; and no fault occurs if the matching is not successful after the whole rule base is browsed. The rail transit vehicle equipment universal detection and fault diagnosis method and the system have good universality and are quick in fault diagnosis.
Description
Technical field
The present invention relates to a kind of rail traffic vehicles and equip general detection and method for diagnosing faults and system.
Background technology
The fast development of China railways has not only increased railway mileage and transportation by railroad total amount, has also increased the rolling stock that each Railway Bureau administers.Along with the development of each big and medium-sized cities city rail traffic, the subway light rail vehicle is also increasing sharply.The various direct current Shaoshan series in the past that not only comprised of the rolling stock model that these roll up has also comprised harmonious each the model locomotive of the interchange of setting out on a journey recently and each model motor train unit of CRH, also comprises various cities rail railcar.For the security of operation of vehicle, all vehicles all need to overhaul behind the operation certain hour.Existing rolling stock model is numerous, but the existing repair apparatus of the unit of maintenance all is for a certain vehicle mostly, a certain concrete parts.When maintenance, the staff need to ceaselessly change test equipment, changes various test article, has greatly increased maintainer's workload, has increased the recondition expense of maintenance unit, has also affected the effect of maintenance simultaneously, directly threatens driving and passenger's safety.Therefore be badly in need of a kind of various vehicles that are adapted to, detection and method for diagnosing faults and the system that can test all critical components of car load.
Summary of the invention
Technical matters to be solved by this invention provides a kind of rail traffic vehicles and equips general detection and method for diagnosing faults and system, and it is good that this rail traffic vehicles is equipped general detection and method for diagnosing faults and system's versatility, and fault diagnosis speed is fast.
The technical solution of invention is as follows:
A kind of rail traffic vehicles is equipped general detection and method for diagnosing faults, will be input in the fault diagnosis module by the signal of data collecting module collected, obtains the fault diagnosis conclusion;
Be provided with the expert system rule storehouse in the described fault diagnosis module, the expert system rule stock contains and fault
Relevant many rules; The expert system rule storehouse adopts fault tree to characterize the mutual relationship of each rule;
Failure diagnostic process is the Data Matching process based on importance degree;
Importance degree is defined as P
C|T=P
C/ P
T, wherein, P
CBe the probability of happening of minimal cut set C, P
TProbability of happening for the fault tree top event;
The data of collection and the rule in the expert system rule storehouse are mated from big to small according to importance degree; If the match is successful, then the output matching result gives the conclusion that is out of order;
All can't the match is successful if travel through whole rule base, then expression is not broken down.
The process of coupling is: such as a certain rule be:
" regular M: if current value greater than threshold k, over current fault then "
The process of coupling is: gather current value i, i and K are compared, if i〉K, then finish coupling, the output conclusion is " over current fault ".
The method for building up in expert system rule storehouse is:
The expert system rule storehouse is comprised of many fault trees, and each fault tree is corresponding with a kind of fault phase respectively; Construction method for the fault tree of a certain fault is: obtain all minimal cut sets for the fault tree of a certain fault, each minimal cut set of fault tree is converted to the rule in the knowledge base again, thereby form a fault tree for a certain fault;
Pass between the superior and the subordinate's node in the fault tree be " with " or the logical relation of "or".
A kind of rail traffic vehicles is equipped general detection and fault diagnosis system, adopts aforesaid rail traffic vehicles to equip general detection and method for diagnosing faults carries out fault diagnosis;
Rail traffic vehicles equips general detection and fault diagnosis system comprises data acquisition module and fault diagnosis module.
Data acquisition module comprises host computer, exchanges variable voltage source, exchanges adjustable current source and data acquisition unit;
Exchange variable voltage source and all be connected with AC power by contactor or isolating switch with the input side that is connected adjustable current source, Devices to test connects the output terminal that exchanges variable voltage source or the output terminal that exchanges adjustable current source;
Data acquisition unit is used for gathering current sensor signal, voltage sensor signals, speed sensor signal, temperature sensor signal and pressure sensor signal, and the signal that gathers is transferred to host computer.
Beneficial effect:
Rail traffic vehicles of the present invention is equipped general detection and method for diagnosing faults and system, has broken that checkout equipment can only be for a certain fixedly vehicle, the tradition that a certain fixed equipment detects in the past.It not only can be tested the nearly all critical component of locomotive (pantograph, primary cut-out, high voltage potential transformer, primary current mutual inductor, tractive transformer, traction convertor, traction electric machine, auxiliary transformer, AuCT, battery charger), can also carry out joint test to system, carry out fault diagnosis.And being applicable to all rail traffic vehicles, it is a kind of general detection and fault diagnosis system and method.
Comprise critical component state-detection and fault diagnosis two parts on this entire system.The critical component state-detection can be simulated and provide the required main status signal of locomotive operation, and the information of Real-time Collection critical component, sends to main frame by network.Overall failure diagnosis: collect the data that each critical component sends from network, by specific diagnosis algorithm locomotive is carried out fault diagnosis.
It is good that rail traffic vehicles of the present invention is equipped general detection and method for diagnosing faults and system's versatility, and fault diagnosis speed is fast.
Description of drawings
Fig. 1 is the power supply unit entire block diagram;
Fig. 2 is the physical circuit figure of power supply unit and detection part;
Fig. 3 is the structured flowchart of data acquisition unit;
Fig. 4 is for detecting the structured flowchart of software;
Fig. 5 is based on fault tree and regular expert system structure block diagram;
Fig. 6 is the Rule process flow diagram based on fault tree;
Fig. 7 is current imbalance fault tree synoptic diagram;
Fig. 8 is current imbalance fault tree rough schematic view;
Fig. 9 is framework synoptic diagram (figure a is that the framework classification is 0 frame diagram, and figure b is that the framework classification is 1 frame diagram);
Figure 10 is the dictionary table data structure diagram;
Figure 11 is current imbalance diagnostic knowledge frame diagram;
Figure 12 is the Rule Expression intention;
Figure 13 is that rule condition represents intention;
Figure 14 is direct frame representation intention;
Figure 15 is indirect frame representation intention;
Figure 16 is that the corresponding Rule of judgment of framework represents intention;
Figure 17 is the rule-based reasoning process flow diagram;
Figure 18 is each functional module composition diagram of fault diagnosis software system;
Figure 19 is the expert system Troubleshooting Flowchart;
Figure 20 is I compressor fault tree synoptic diagram;
Figure 21 is I compressor fault rule base synoptic diagram;
Figure 22 is I compressor fault rule condition storehouse synoptic diagram.
Embodiment
Below with reference to the drawings and specific embodiments the present invention is described in further details:
Embodiment 1:
Rail traffic vehicles is equipped the hardware platform of general detection and fault diagnosis system mainly by power supply unit, signal input and output unit.
Power supply unit: the power supply unit entire block diagram as shown in Figure 1.
Whole system adopts the three-phase four-wire system Alternating Current Power Supply.According to the electrical locomotive power characteristics, electric power incoming line is respectively high-power ac power and high-power DC power supply provides power supply.
High-power ac power: in practical service environment, the locomotive power supply power acquisition is powered with single-phase 25kV, and allowing scope range of the fluctuation of voltage is the highest 31kV of minimum 19kV.Therefore this high-power ac power is designed to the adjustable transformer with multichannel output, the user can according to the test needs by host computer regulate this AC power output voltage (range of regulation is 0 ~ 35kV), the sensor in the power supply with the voltage Real-time Feedback of output to host computer.This power supply not only can satisfy the testing requirement of main-transformer, can also provide vacuum circuit breaker for the user, the detection of the High-Voltage Electrical Appliances such as high voltage potential transformer.
High-power DC power supply: in the alternating current electric locomotive, current transformer is divided into interchange link and DC link, in detection, not only needs to provide the AC power input, also needs to provide direct supply for detecting DC link.Locomotive control power is supplied with by battery charger, because the difference of vehicle, the charging set model is also different, and the power supply of input also is divided into direct current and exchanges, and therefore needs system that direct supply is provided.The size of user by host computer controllable power voltage, simultaneously the sensor of power supply unit also with signal feedback such as electric current and voltages to host computer, realize closed-loop control.
The physical circuit of power supply unit as shown in Figure 2.Wherein QF1 is main circuit breaker, and PT is voltage sensor, and TA is current sensor.The data that both collect all will access the PXI cabinet by shielding line and carry out data acquisition, and the data that collect will be transferred to host computer by the pci bus between PXI cabinet and the host computer, call for detecting software and fault diagnosis software.In order to realize the controlled of power supply, the user can send a signal to PXI cabinet output control signal by host computer, and control signal is through output conditioning output control supply voltage.The data input-output unit
As shown in Figure 3, data acquisition unit is comprised of input and output conditioning unit, PXI cabinet (containing data collecting card) and train network communication unit.The type of data input and output mainly comprises analog output, digital output (comprising PWM output), TCN output.Be mainly current sensor signal, voltage sensor signals, speed sensor signal, temperature sensor signal and pressure sensor signal.
Each critical component of locomotive is not an independent individuality, but need to communicates with other unit cooperation when normal operation.When detecting, in order to simulate nominal situation as far as possible, need detection system to export corresponding signal to unit under test, simulate the parts relevant with equipment under test.The output signal of simultaneously equipment under test generation needs system acquisition to feed back to system's host computer, by the control algolithm that locomotive is intrinsic signal is processed, and forms close-loop feedback.
Simultaneously in the real testing process to control and the fault diagnosis of unit under test, associated data in the time of need to providing parts to detect, therefore we also need to utilize the relevant data of sensor collection of system when detecting.The direct current signal that the signal of the signal of unit under test output and sensor output all is converted to 0-5v after through the signal condition cell translation can directly be inputted the PXI cabinet and gather with data collecting card.The data of PXI cabinet collection all send to host computer by the PCI bridge with data.Unit under test such as need carry out network service, then can send signal to the TCN unit, and the TCN unit is transferred to host computer by Ethernet with signal.Host computer passes through the control program of simulation train according to the data of input, makes a policy, and by train network unit and PXI cabinet output control command and control signal.Because the signal of PXI cabinet output is the required signal of matching block fully, so the signal of its output also need pass through the output signal conditioning unit, is converted to the signal that mates with unit under test.Whole process is closed-loop control.
Software section
Software mainly partly consists of by detecting software section and fault diagnosis.
Detecting software adopts labview and Vc comprehensively to programme.Mainly comprise data acquisition configuration, data flow configuration, user interface configuration and test data management.
According to the step that test is carried out, need to set up first testing engineering.In engineering, to carry out first every configuration of data collecting card, the projects such as sampling rate of capture card should be set in configuration, and physical channel and signal name is corresponding.Carry out the testing process configuration according to user's needs, add test procedure, test condition, test figure.After finishing configuration, call the test subscriber interface, according to different vehicles, different units under test is set up model and is called corresponding configuration file and can test.If need to preserve test data of experiment, before experiment, also need the test data storage rule is arranged.
Function declaration
The data acquisition configuration is user's data acquisition card hardware corridor attribute configuration, the submodule of the corresponding interface of foundation and test procedure.When the tested product of each detection not simultaneously, the signal name that the user can be flexibly needs passage and the user of data capture card be shone upon, the user also can by call configuration file in the past, revise and finish the acquisition tasks configuration.After finishing, user's configuration will in submodule functional configuration district, show the channel configuration information in the existing configuration file.
The testing process configuration.The user can set experimental procedure according to the test experience outline of the different units under test of different automobile types in this module, by the corresponding data acquisition channel that sets before calling, chooses the passage that needs and adds in the flow testing tabulation.
The user interface configuration.The user disposes corresponding test interface according to the different units under test of different automobile types, and the user can set up the mixed-media network modules mixed-media distributed model according to vehicle, shows each module particular location onboard.Preserve simultaneously reusability and transplantability that the interface is improved at the interface, and can generate independently test interface.By calling the testing process tabulation that configures, detect according to the flow process of user preset in user interface, the vehicle model that the user also can configure by click is tested a certain parts separately.Simultaneously can also call the network assistant at this interface, check the real time data on the network.
Fault diagnosis system
Overall failure diagnosis expert system basic ideas: fault tree analysis was mainly used in the analytic system failure cause in the past, and the fiduciary level of computing system with the optimization system design, therefore, is used widely in systems reliability analysis and design.In recent years, the research that utilizes fault tree models to carry out source of trouble search has caused very big concern.Because fault tree is easy to the analysis event, and RBES match reasoning speed directly perceived is fast, and therefore, this method analyzes and obtain knowledge with fault tree, and with the diagnostic expert system that rule match is carried out reasoning, its structure as shown in Figure 5.
1, based on the Rule of fault tree
The target of fault tree qualitative analysis is to seek the source of trouble that causes top event to occur, i.e. the bottom event of fault tree combination, all fault modes that identification causes top event to occur.The most frequently used method is to seek all minimal cut sets of object fault tree, each minimal cut set of fault tree is converted to the rule in the knowledge base, its basic step such as Fig. 6 again.
As from the foregoing, obtaining Minimizing Cut Sets of Fault Trees is the key point of obtaining expert system rule.The normal fault tree search method from top to bottom that adopts is found the solution Minimizing Cut Sets of Fault Trees, its concrete operation step is: because of the increase of logical “and” door is bottom event number in the minimal cut set, for rule, what inputs are one have with door, and how many conditional numbers of so corresponding rule just has individual.What logic sum gate increased is the Minimizing Cut Sets of Fault Trees number, namely one or what inputs are arranged, the corresponding rule of how many bars is so just arranged, therefore to obtain minimal cut set by fault tree, can take to run into from top to bottom AND gate and just all incoming events below the AND gate are in line, run into OR-gate and just all events below the OR-gate are formed a line.The rest may be inferred, until can not decompose.The below obtains corresponding failure diagnostician rule as an example of traction motor current imbalance fault tree example.The current imbalance fault tree as shown in Figure 7.Its coding reduced form as shown in Figure 8.
At first press search procedure from top to bottom, the whole minimal cut sets that obtain fault tree are: (B003600010001), (B003600010002), (B003600020003), (B003600020004), (B003600020005), (B003600010006), (B003600030007), (B003600030008), (B003600030009), (B003600020010), (B003600020011), can find out, owing in fault tree, between the node all be or logical relation, so each leaf node consists of a minimal cut set, totally 11.Therefore it is as follows to get the uneven Expert Rules of traction motor current:
(1)IF B003600010001 THEN F0036；
(2)IF B003600010002 THEN F0036；
(3)IF B003600010003 THEN F0036；
…………………
(11) IF B003600020011 THEN F0036; Totally 11.By same method, can obtain other fault Expert Rules of electric locomotive electric part.The Expert Rules of native system is to utilize computer program to remove analysis of failure tree automatic acquisition, and is kept in the rule list, for the failure diagnosis reasoning machine utilization.
In order to describe the size of each minimal cut set of fault tree contribution that generation is done to top event, degree of importance for minimum cut sets can be defined as P
C|T:
P
C|T＝P
C/P
T (3-1)
P in the formula (3-1)
CBe the probability of happening of minimal cut set C, P
TProbability of happening for the fault tree top event.Degree of importance for minimum cut sets P
C|TPhysical meaning is the number percent that the minimal cut set probability accounts for fault tree top event probability.Because each bottom event is separate, mutual exclusive event in the minimal cut set, by probability statistics, P as can be known
CProduct for each bottom event probability in the minimal cut set.
Still take traction motor current imbalance fault tree as example, how introduction calculates the importance degree of Minimizing Cut Sets of Fault Trees in detail now.Suppose probable value such as the table 4 of each bottom event.Probable value in this paper be set with two kinds of methods: the one, the domain expert passes through the knowledge base management man-machine dialog interface and artificially sets; The 2nd, by fault history information is added up, calculate the probability that each bottom event occurs.
Table 4 bottom event probability tables
| The bottom event numbering | B00360001000 | B00360001000 | B00360001000 | B00360002000 |
| Probable value | 0.04 | 0.05 | 0.07 | 0.12 |
| The bottom event numbering | B00360002000 | B00360002000 | B00360003000 | B00360003000 |
| Probable value | 0.2 | 0.11 | 0.03 | 0.07 |
| The bottom event numbering | B00360003000 | B00360002001 | B00360002001 | |
| Probable value | 0.12 | 0.105 | 0.085 |
The probability that calculates each intermediate event of fault tree and top event according to probability statistics knowledge is as follows:
P
M00360001=1-(1-P
B003600010001)(1-P
B003600010002)(1-P
B003600010003)=0.1963,
P
M00360003=1-(1-P
B003600020006)(1-P
B003600030007)(1-P
B003600030008)=0.1971,
P
M00360002=1-(1-P
B003600030004)(1-P
B003600020005)(1-P
B003600030009)(1-P
B003600020010)(1-P
B003600020011)(1-P
M00360003)=0.4074,
P
T=1-(1-P
M00360001) (1-P
M00360002)=0.5237, the probability that expression top event current imbalance fault occurs.According to importance degree computing formula P
M|T=P
M/ P
TCalculate the importance degree of each minimal cut set or rule, final calculation result is as shown in table 5.
Table 5 current imbalance Minimizing Cut Sets of Fault Trees importance degree
As can be seen from the table, the importance degree of minimal cut set (B003600020005) is maximum, so the rule of its correspondence should be mated at first, the last coupling of rule (strictly all rules does not have in the situation that the match is successful in front) that the cut set of importance degree minimum (B003600030007) is corresponding.In theory, each minimal cut set might be the reason that causes top event to occur.But in fact importance degree is less, the probability that corresponding fault mode occurs is often also less, even may not occur, therefore carry out the rule match ordering by importance degree, can make that rule match is orderly, regular carries out, and can obviously improve the efficient of source of trouble search, the simple rule coupling of therefore saying than the front has obvious superiority.
2, fault diagnosis expert system knowledge-base design
The method for expressing of expert system knowledge has frame representation, production rule representation etc., and each has something to recommend him, and comprehensive relative merits have separately designed based on the framework of fault tree and the Integrated Knowledge Representation method of rule.Main cause is that the diagnostic knowledge of Fault Diagnosis Expert System of Electric Locomotive relatively is fit to adopt the form based on production rule to represent; On the other hand, because fault of electric locomotive diagnostic knowledge quantity is various, fault type is complicated, but with knowledge classification storage Effective Raise inference engine of expert system inference speed and Reasoning Efficiency.Framework is as a kind of data structure of description object attribute, has stronger structural and inheritance, can describe well the fault of electric locomotive diagnostic tree and also can show the contact explicitly of the inner structure of these diagnostic knowledges relation and knowledge, it has remedied the shortcoming of production rule.We are divided into two kinds to framework, and a kind of is direct framework, and the framework classification is 0, and a kind of is indirect framework, and the framework classification is 1.As shown in Figure 9.
Wherein, frame number is generally corresponding true number, and frame name is called corresponding true title, and father's groove is the frame name of father node; The groove type is the logical communication link relation of present event and subevent, if this event is bottom event, then the groove type is 0.The framework of the uneven diagnostic knowledge of traction motor current as shown in figure 11.
The knowledge-base design of based on database technology
The knowledge base of this method will be comprised of following several database tables, and the below will simply set forth each table.
1. data dictionary table
The effect of data dictionary table is that whole conditions and conclusion are encoded into sign format, and then the condition of the strictly all rules in the knowledge base and conclusion all represent with symbol.Process on the one hand like this and can effectively promote search and inference speed; Replace complicated Word message not only to save storage space with simple symbol on the other hand, and be convenient to the writing of SQL statement in the database.The specific coding rule that this paper adopts is: top event coding=" F "+self 4 position digital coding is F0036 such as the current imbalance event; Intermediate event coding=" M "+top event 4 position digital codings+self 4 position digital coding are M00360002 such as the uneven event code of current failure; Bottom event coding=" B "+intermediate event 8 position digital codings+self 4 position digital coding, damaging event code such as silicon cell is B003600020006.Event code work is all realized automatically by computing machine.The dictionary table data structure as shown in figure 10.
Rule list
Rule list is one of core in the expert system knowledge base.Process very flexible and easy-to-understand based on the knowledge representation of this data structure.What is more important, it is so that one of expert system nucleus module---and the design of the program of inference machine module becomes and more is easily understood, and whole reasoning process is also more rigorous, efficient.The data structure of rule list as shown in figure 12.Rule can represent that with minimal cut set a minimal cut set can have a plurality of bottom events or have and only have a bottom event, and quantitatively not restriction that is to say that the true number of condition of a rule is uncertain.If the true maximum rule of employing condition is processed, and will cause like this waste of storage resources, it is a kind of not bery reasonably method for designing.Therefore, the present invention builds a rule condition table by other and comes the corresponding condition of storage rule true number, the coding of the bottom event in the minimal cut set namely, rule condition list data structure.In addition, can find out wherein there is one for importance degree from rule list, this is the service of inference machine heuristic search control strategy, is the importance degree of each minimal cut set of obtaining of the quantitative test by fault tree.So its priority that degree of importance for minimum cut sets is large is just high, also just can be taken the lead in selecting to mate with the fault fact by inference machine, thus raising fault diagnosis efficient.
Frame table
Frame table also is one of native system knowledge base core component.From the practical function of frame table, it is exactly the storage list of fault of electric locomotive tree.Type according to the node of fault tree is different, frame table can be divided into: indirectly frame table and directly frame table, and respectively such as Figure 14 and shown in Figure 15.In fact, frame table is mainly used to represent root node and the intermediate node of fault tree indirectly, and directly frame table is used for representing the fault tree leaf node.It should be noted that the quantity that indirect frame table also exists the Rule of judgment in the frame table is uncertain factor, from saving the angle of storage space, the employing of the present invention method the same with rule list processed.Namely build in addition indirect framework Rule of judgment table and come the corresponding Rule of judgment of storing framework, list structure as shown in figure 16.
3, Fault Diagnosis Expert System of Electric Locomotive Design of Inference Engine
Inference machine is a nucleus module of fault diagnostic expert system, the brain that is equivalent to the domain expert, it utilizes the fault information data of diagnosed object, and the inference strategy that designs in advance in conjunction with knowledge and the inference machine of knowledge base carries out the reasoning diagnosis, releases system failure reason.In fact, the reasoning based on the fault diagnosis expert system of knowledge is exactly the matching process of a rule.The simplest method is that the rule in the rule list is mated one by one, and concrete steps are:
The user is according to current significant failure symptom, from rule base, select the fault factbase of the locomotive information formation of respective rule and locomotive detection dot information and user's input to mate, at last by with user interactions, diagnostic result is confirmed, thereby is provided diagnostic result and maintenance suggestion.Shown in the Troubleshooting Flowchart 17.
This reasoning matching process has blindness and matching speed is slow.In order to improve matching speed, this paper introduces the degree of importance for minimum cut sets concept, in fact also is regular importance degree.The probability that this minimal cut set of the higher expression of importance degree causes top event to occur is larger, should preferentially mate on rule match.Therefore can carry out rule match according to regular importance degree size order.
Now lift an example and make a concrete analysis of explanation: analyze with the current imbalance fault.
After being connected by measured motor and all the sensors and hardware platform, start-up system.Suppose current sensor return current signal this moment, be judged as current imbalance through upper computer software.Can infer reason 1 according to the expert system rule storehouse thus: normal uneven, or reason 2: fault is uneven.Search for downwards according to the importance degree of minimal cut set again, can be found out that by above calculating the importance degree of " microcomputer fault " this fault is maximum, therefore begin at first coupling.
Each functional module composition diagram of fault diagnosis software system as shown in figure 18.
Software mainly is comprised of the five functional module: fault diagnosis module, knowledge base management module, fault tree administration module, data management module and user management module.The below briefly introduces each functions of modules.
(1) fault diagnosis module is one of nucleus module of this fault diagnosis software, and fault diagnosis module comprises reasoning module and reasoning explanation module, i.e. inference machine in the expert system and explanation engine.In order to realize the versatility of reasoning module, this software realizes that successfully inference machine separates with knowledge base.Whole system adopts forward reasoning and acquainted search strategy, it is the Enlightened Search strategy, in order to realize this target,, when design of rule-bases, introduced the concept of importance degree, rule is carried out the priority setting, can improve the success ratio of rule match, accelerate inference speed, avoid the blindness of inscience search.
(2) the knowledge base management module is a module that complete expert system is indispensable, the knowledge base management module of native system comprises from fault tree obtains rule and computation rule importance degree two large functions, that is to say that the rule in the knowledge base comes automatic acquisition by fault tree, is not directly to revise the renewal that knowledge base realizes knowledge base by knowledge engineer or domain expert.Say to a certain extent, also solve the problems such as knowledge acquisition difficulty of the RBES of knowing clearly.
(3) fault tree administration module by the knowledge base management module of introducing above as can be known, wants a fault diagnosis system and obtains complete rule-based knowledge base, and it is particularly important to design the fault tree administration module.This software is realized demonstration, the edition function of fault tree based on the TreeView control among the C#, is simple and easy to use.
(4) data management module mainly is to preserve the fault diagnosis historical data, for user's inquiry, can export to the Excel format print, and the fault frequency in the simultaneous faults historical record can be used as the reference of regular importance degree.Secondly also have the data document relevant with electric locomotive for user's query learning.
(5) user management module comprises that user right distributes and user basic information renewal two parts.The user right distribution is different according to user's function, distributes different authorities, and the general user can only carry out fault history inquiry, derivation and pertinent literature function of browse; The technician can carry out Analysis on Fault Diagnosis; The knowledge engineer can carry out knowledge base or fault tree is safeguarded; Managerial personnel can carry out the functions such as distribution of user right.User basic information mainly is to be convenient to contact the personnel of each side.
The expert system fault diagnosis flow scheme as shown in figure 19.
Describe the basic reasoning flow process of fault diagnosis as an example of I compressor contactor 16KM fault example, wherein the status signal of contactor 16KM can pass through the LCU automatic acquisition.Enter the stand-by motor fault diagnosis module.
The below introduces native system in detail to the reasoning process of I Compressor Fault Diagnosis, and fault tree also can be seen from the knowledge base management interface fault tree that represents with Tree View view structure as shown in figure 20.
As can be seen from Figure 20, compressor fault comprises the more than fault of air draft and does not beat the wind fault.Rule acquisition module is obtained rule and computation rule importance degree by the regulation obtaining method of front surface analysis gained, and preservation advances the rule base table, shown in Figure 21,22.
The user can be inquired in the phenomenon of the failure hurdle in the auxiliary unit diagnosis, which kind of phenomenon of the failure the I compressor is, if after checking by the driver and conductor scene, select the I compressor not beat wind, system can by regular importance degree successively calling rule R0237 ~ R0242 carry out with integrated data base in the fact mate.And show location of fault may occur by the importance degree of minimal cut set.
The software function module design
System login and main interface
The user name of system's log-in interface has uniqueness, that is to say that can not there be two duplicate users of user name in this system, when clicking login, system can go to search according to user name this user's authority, thereby some function of limited subscriber is unlikely destroyed and can not normally move with the assurance system.Then enter fault diagnosis master interface.The level in the fault of electric locomotive characteristics has been used for reference in the design of this Failure Detection Expert System Software, being about to the fault of electric locomotive diagnostic system is divided into electric part, mechanical part, air pipe line partly and behind other parts 4 sub-systems, again each subsystem is subdivided into corresponding functional part.When each parts broke down, the corresponding function parts in can click figure entered corresponding fault diagnosis interface.
The fault diagnosis interface
System will unpack rear demonstration, storage from the TCP/IP data that traction control partly sends over.On fault diagnosis expert system master interface, click the button that indicates a certain subsystem, enter corresponding fault diagnosis expert system interface.
The fault diagnosis interface mainly comprises following a few part: phenomenon of the failure is used for input or selects phenomenon of the failure; User's question and answer be for the answer system when the matched rule, in the situation that the fault fact can't detect automatically by checkout equipment, must be by artificial Site Detection, and answer "Yes", "No" or " uncertain " so that the reasoning function continues diagnosis goes down; Fault diagnosis result hurdle output fault diagnosis result; Reasoning is explained and is used for explaining the process of reasoning, and makes user Geng Yi accept diagnostic result, embodies the transparency of expert system.Fault handling suggestion is the method that proposes maintenance according to diagnostic result, makes there not being in maintenance technician's the situation fault also can in time process, to reduce loss.Rule acquisition module is obtained rule and computation rule importance degree according to the acquisition methods based on fault tree, and preserves the rule base table, and its each nodes encoding form of its storage form in relational database is automatic coding, can check from dictionary table.
High but utilize the not good fault of expert system diagnosis effect to some occurrence frequencies, after entering the Diagnostics Interfaces of this fault, can select to comparatively effective other diagnostic mode of this fault, such as neural network algorithm, multi-sensor information fusion monitoring, characteristic spectrum analysis etc.Software can be developed further into the system ensemble into condition monitoring and fault diagnosis on this basis.
In test process, detection system will be to electric current and voltage, rate signal, and the temperature and pressure signal carries out Real-time Collection, these data will by the PXI cabinet real-time send host computer to, host computer is read by software and preserves in database, and fault diagnosis expert system is taked the ad hoc fashion deal with data, draws diagnosis and fault handling result.The data of each diagnosis can find and derive with text file format in following fault history inquiry.
The knowledge base management interface
Knowledge base management master interface mainly realizes fault tree is increased node, deletion of node, editor's node.Knowledge base management master interface is the fault tree of TreeView view form, clicks wherein deployable its all subordinate's child node of a certain node.Certain node in the right click fault tree can eject right-click menu, and it comprises newly-built node, revises the functions such as node, deletion of node, realizes expansion, the renewal of fault tree, thereby further improves the expert system rule storehouse.
The fault history query interface
The fault history inquiry of native system has three kinds of modes: check whole historical records 1.; 2. press the time of failure inquiry; 3. by the inquiry of fault occurrence type.
Claims (4)
1. a rail traffic vehicles is equipped general detection and method for diagnosing faults, it is characterized in that, will be input in the fault diagnosis module by the signal of data collecting module collected, obtains the fault diagnosis conclusion;
Be provided with the expert system rule storehouse in the described fault diagnosis module, the expert system rule stock contains the many rules relevant with fault; The expert system rule storehouse adopts fault tree to characterize the mutual relationship of each rule;
Failure diagnostic process is the Data Matching process based on importance degree;
Importance degree is defined as P
C|T=P
C/ P
T, wherein, P
CBe the probability of happening of minimal cut set C, P
TProbability of happening for the fault tree top event;
The data of collection and the rule in the expert system rule storehouse are mated from big to small according to importance degree; If the match is successful, then the output matching result gives the conclusion that is out of order;
All can't the match is successful if travel through whole rule base, then expression is not broken down.
2. rail traffic vehicles according to claim 1 is equipped general detection and method for diagnosing faults, it is characterized in that, the method for building up in expert system rule storehouse is:
The expert system rule storehouse is comprised of many fault trees, and each fault tree is corresponding with a kind of fault phase respectively;
Construction method for the fault tree of a certain fault is: obtain all minimal cut sets for the fault tree of a certain fault, each minimal cut set of fault tree is converted to the rule in the knowledge base again, thereby form a fault tree for a certain fault;
Pass between the superior and the subordinate's node in the fault tree be " with " or the logical relation of "or".
3. a rail traffic vehicles is equipped general detection and fault diagnosis system, it is characterized in that, adopts claim 1 or 2 described rail traffic vehicles equip general detection and method for diagnosing faults carries out fault diagnosis;
Rail traffic vehicles equips general detection and fault diagnosis system comprises data acquisition module and fault diagnosis module.
4. rail traffic vehicles according to claim 1 is equipped general detection and fault diagnosis system, it is characterized in that, data acquisition module comprises host computer, exchanges variable voltage source, exchanges adjustable current source and data acquisition unit;
Exchange variable voltage source and all be connected with AC power by contactor or isolating switch with the input side that is connected adjustable current source, Devices to test connects the output terminal that exchanges variable voltage source or the output terminal that exchanges adjustable current source;
Data acquisition unit is used for gathering current sensor signal, voltage sensor signals, speed sensor signal, temperature sensor signal and pressure sensor signal, and the signal that gathers is transferred to host computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210363416.0A CN102879680B (en) | 2012-09-26 | 2012-09-26 | The general detection of rail transit vehicle equipment and method for diagnosing faults and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210363416.0A CN102879680B (en) | 2012-09-26 | 2012-09-26 | The general detection of rail transit vehicle equipment and method for diagnosing faults and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102879680A true CN102879680A (en) | 2013-01-16 |
| CN102879680B CN102879680B (en) | 2015-07-29 |
Family
ID=47481076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210363416.0A Active CN102879680B (en) | 2012-09-26 | 2012-09-26 | The general detection of rail transit vehicle equipment and method for diagnosing faults and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102879680B (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217972A (en) * | 2013-04-17 | 2013-07-24 | 北京全路通信信号研究设计院有限公司 | High-speed railway active transponder message automatic verification method and system |
| CN103257650A (en) * | 2013-04-17 | 2013-08-21 | 北京全路通信信号研究设计院有限公司 | Check system used for function test of train control system |
| CN103258110A (en) * | 2013-01-23 | 2013-08-21 | 辽宁工程技术大学 | Method for determining accident trend of electrical system on basis of states |
| 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 |
| CN103812727A (en) * | 2014-01-27 | 2014-05-21 | 中国电子科技集团公司第十研究所 | Diagnostic method for automatically analyzing and positioning equipment failure of deep space measurement and control station |
| CN104714058A (en) * | 2015-02-10 | 2015-06-17 | 株洲南车时代电气股份有限公司 | Test tool and equipment of locomotive converter |
| CN104777828A (en) * | 2014-10-29 | 2015-07-15 | 中国神华能源股份有限公司 | Method for judging fault of electrical system of electric locomotive |
| CN104778821A (en) * | 2015-04-09 | 2015-07-15 | 银江股份有限公司 | Automatic alarm system and method for transportation equipment |
| CN104991549A (en) * | 2015-05-27 | 2015-10-21 | 中国铁路总公司 | Track circuit red-light strip default diagnosis method based on FTA and multilevel fuzzy-neural sub-networks |
| CN105159283A (en) * | 2015-09-02 | 2015-12-16 | 南京南车浦镇城轨车辆有限责任公司 | Remote fault analysis and feedback system of urban rail transit vehicle |
| CN105841980A (en) * | 2016-03-21 | 2016-08-10 | 山东云舜智能科技有限公司 | Method and system for monitoring working condition of HXD type locomotive cooling channel and fault pre-diagnosis |
| CN105974225A (en) * | 2016-04-28 | 2016-09-28 | 上海机电工程研究所 | Fault diagnosis system based on distributed detection data and fault diagnosis method thereof |
| CN106293630A (en) * | 2016-08-19 | 2017-01-04 | 四川网达科技有限公司 | Railway signal fault analyzes logic rule generating means and method |
| CN107967545A (en) * | 2016-10-19 | 2018-04-27 | 中国辐射防护研究院 | The Birnbaum importances and structure importance computational methods of subsystem component in probabilistic safety assessment |
| CN108956107A (en) * | 2018-05-18 | 2018-12-07 | 合肥通用机械研究院有限公司 | Couple the Fault tree diagnosis method of the reciprocating compressor typical fault of Triangular Fuzzy Number |
| CN109358255A (en) * | 2018-12-18 | 2019-02-19 | 北京交通大学 | Traction converter failure analysis method and device |
| CN109443789A (en) * | 2018-09-30 | 2019-03-08 | 北京新联铁集团股份有限公司 | The processing method and processing system of rolling stock health |
| CN110163374A (en) * | 2018-12-07 | 2019-08-23 | 贵州航天风华精密设备有限公司 | A kind of fault diagnosis reasoning system based on Word generic configuration |
| CN110262461A (en) * | 2019-07-03 | 2019-09-20 | 浙江好得电气有限公司 | Blower fan control system two dimensional code intelligent fault diagnosis method and system |
| CN110606100A (en) * | 2019-09-03 | 2019-12-24 | 中车青岛四方机车车辆股份有限公司 | Fault determination method and device |
| CN110646706A (en) * | 2019-09-12 | 2020-01-03 | 国电南瑞科技股份有限公司 | Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar |
| CN110827350A (en) * | 2019-12-10 | 2020-02-21 | 中交一公局电气化工程有限公司 | Tramcar real-time data acquisition system based on Labview and Modbus/TCP communication protocol |
| CN110837530A (en) * | 2019-11-07 | 2020-02-25 | 交控科技股份有限公司 | Fault information processing method and device based on rail transit integrated equipment monitoring |
| CN111337764A (en) * | 2020-02-14 | 2020-06-26 | 重庆国翰能源发展有限公司 | Charging pile fault diagnosis system and method and storage medium |
| WO2020211846A1 (en) * | 2019-04-19 | 2020-10-22 | 深圳市德塔防爆电动汽车有限公司 | Safety tree model-based electric vehicle operation and maintenance optimization method |
| CN111813807A (en) * | 2020-06-05 | 2020-10-23 | 中国电子科技集团公司电子科学研究院 | Real-time fault diagnosis method and device based on expert diagnosis library |
| CN111845852A (en) * | 2019-04-24 | 2020-10-30 | 广州地铁集团有限公司 | Train traction lockout diagnosis method, system and device and readable storage medium |
| CN111898195A (en) * | 2020-06-15 | 2020-11-06 | 北京交通大学 | Rail transit train system multi-state reliability analysis method based on improved d-MC |
| CN111971545A (en) * | 2018-04-18 | 2020-11-20 | 梅施发动机国际贸易有限公司 | Diagnostic system and method for processing data of a motor vehicle |
| CN112224241A (en) * | 2020-11-18 | 2021-01-15 | 中国铁道科学研究院集团有限公司 | Speed acquisition system, fault alarm method and device |
| CN112241511A (en) * | 2019-07-19 | 2021-01-19 | 上海杰之能软件科技有限公司 | Performance detection method and device of auxiliary electrical system of vehicle and terminal |
| CN112379200A (en) * | 2020-11-10 | 2021-02-19 | 深圳市康必达控制技术有限公司 | Fault location and solution method |
| CN113238535A (en) * | 2021-06-03 | 2021-08-10 | 中国核动力研究设计院 | Fault diagnosis method and system for nuclear safety level DCS analog input module |
| CN113320565A (en) * | 2020-02-28 | 2021-08-31 | 株洲中车时代电气股份有限公司 | Vehicle-mounted real-time fault diagnosis method and device |
| CN113505282A (en) * | 2021-06-11 | 2021-10-15 | 国网浙江省电力有限公司嘉兴供电公司 | Expert system-based high-voltage circuit breaker state identification method and system |
| TWI751464B (en) * | 2018-12-26 | 2022-01-01 | 日商納博特斯克股份有限公司 | Air compression system for railway vehicles |
| CN114462608A (en) * | 2022-04-12 | 2022-05-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Method, system, computer and storage medium for inferring traffic route problems |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2679354A1 (en) * | 1991-07-19 | 1993-01-22 | Souriau Diagnostic Electron | Fault diagnosis apparatus for motor vehicle |
| CN101487865A (en) * | 2008-01-16 | 2009-07-22 | 西门子公司 | Fault diagnosis method and fault diagnosis system |
| CN102508076A (en) * | 2011-11-09 | 2012-06-20 | 东北大学 | Fault diagnosis device and method based on multi-agent system and wavelet analysis |
-
2012
- 2012-09-26 CN CN201210363416.0A patent/CN102879680B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2679354A1 (en) * | 1991-07-19 | 1993-01-22 | Souriau Diagnostic Electron | Fault diagnosis apparatus for motor vehicle |
| CN101487865A (en) * | 2008-01-16 | 2009-07-22 | 西门子公司 | Fault diagnosis method and fault diagnosis system |
| CN102508076A (en) * | 2011-11-09 | 2012-06-20 | 东北大学 | Fault diagnosis device and method based on multi-agent system and wavelet analysis |
Non-Patent Citations (3)
| Title |
|---|
| 周正: "基于故障树的机车故障诊断专家系统的研究", 《中国水运》, vol. 8, no. 7, 31 July 2008 (2008-07-31), pages 138 - 139 * |
| 王轶等: "基于故障树的电力机车故障诊断专家系统", 《电力机车与城轨车辆》, vol. 27, no. 6, 20 November 2004 (2004-11-20), pages 35 - 2 * |
| 黄志武等: "8K型电力机车电气故障诊断系统", 《机车电传动》, no. 3, 10 May 2004 (2004-05-10) * |
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258110A (en) * | 2013-01-23 | 2013-08-21 | 辽宁工程技术大学 | Method for determining accident trend of electrical system on basis of states |
| CN103258110B (en) * | 2013-01-23 | 2017-05-17 | 辽宁工程技术大学 | Method for determining accident trend of electrical system on basis of states |
| CN103257650B (en) * | 2013-04-17 | 2015-12-23 | 北京全路通信信号研究设计院集团有限公司 | Verification system for function test of train control system |
| CN103257650A (en) * | 2013-04-17 | 2013-08-21 | 北京全路通信信号研究设计院有限公司 | Check system used for function test of train control system |
| CN103217972A (en) * | 2013-04-17 | 2013-07-24 | 北京全路通信信号研究设计院有限公司 | High-speed railway active transponder message automatic verification method and system |
| CN103217972B (en) * | 2013-04-17 | 2016-01-27 | 北京全路通信信号研究设计院集团有限公司 | Automatic checking method and system for active transponder message of high-speed railway |
| 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 |
| CN103345207B (en) * | 2013-05-31 | 2015-06-24 | 北京泰乐德信息技术有限公司 | Mining analyzing and fault diagnosis system of rail transit monitoring data |
| CN103812727A (en) * | 2014-01-27 | 2014-05-21 | 中国电子科技集团公司第十研究所 | Diagnostic method for automatically analyzing and positioning equipment failure of deep space measurement and control station |
| CN104777828A (en) * | 2014-10-29 | 2015-07-15 | 中国神华能源股份有限公司 | Method for judging fault of electrical system of electric locomotive |
| CN104714058A (en) * | 2015-02-10 | 2015-06-17 | 株洲南车时代电气股份有限公司 | Test tool and equipment of locomotive converter |
| CN104778821A (en) * | 2015-04-09 | 2015-07-15 | 银江股份有限公司 | Automatic alarm system and method for transportation equipment |
| CN104991549A (en) * | 2015-05-27 | 2015-10-21 | 中国铁路总公司 | Track circuit red-light strip default diagnosis method based on FTA and multilevel fuzzy-neural sub-networks |
| CN104991549B (en) * | 2015-05-27 | 2017-06-30 | 中国铁路总公司 | Track circuit red band method for diagnosing faults based on FTA and multi-layer fuzzy nerve sub-network |
| CN105159283A (en) * | 2015-09-02 | 2015-12-16 | 南京南车浦镇城轨车辆有限责任公司 | Remote fault analysis and feedback system of urban rail transit vehicle |
| CN105159283B (en) * | 2015-09-02 | 2017-11-28 | 南京中车浦镇城轨车辆有限责任公司 | Urban rail transit vehicles remote fault analysis and reponse system |
| CN105841980B (en) * | 2016-03-21 | 2019-05-17 | 山东云舜智能科技有限公司 | HXD type locomotive cooling duct monitoring of working condition and fault pre-diagnosing method and system |
| CN105841980A (en) * | 2016-03-21 | 2016-08-10 | 山东云舜智能科技有限公司 | Method and system for monitoring working condition of HXD type locomotive cooling channel and fault pre-diagnosis |
| CN105974225A (en) * | 2016-04-28 | 2016-09-28 | 上海机电工程研究所 | Fault diagnosis system based on distributed detection data and fault diagnosis method thereof |
| CN106293630A (en) * | 2016-08-19 | 2017-01-04 | 四川网达科技有限公司 | Railway signal fault analyzes logic rule generating means and method |
| CN106293630B (en) * | 2016-08-19 | 2018-07-27 | 四川网达科技有限公司 | Railway signal fault analyzes logic rules generating means and method |
| CN107967545A (en) * | 2016-10-19 | 2018-04-27 | 中国辐射防护研究院 | The Birnbaum importances and structure importance computational methods of subsystem component in probabilistic safety assessment |
| CN107967545B (en) * | 2016-10-19 | 2022-05-17 | 中国辐射防护研究院 | Method for calculating Birnbaum importance and structure importance of subsystem component in probability safety evaluation |
| CN111971545A (en) * | 2018-04-18 | 2020-11-20 | 梅施发动机国际贸易有限公司 | Diagnostic system and method for processing data of a motor vehicle |
| CN108956107A (en) * | 2018-05-18 | 2018-12-07 | 合肥通用机械研究院有限公司 | Couple the Fault tree diagnosis method of the reciprocating compressor typical fault of Triangular Fuzzy Number |
| CN109443789A (en) * | 2018-09-30 | 2019-03-08 | 北京新联铁集团股份有限公司 | The processing method and processing system of rolling stock health |
| CN109443789B (en) * | 2018-09-30 | 2021-02-19 | 北京新联铁集团股份有限公司 | Method and system for processing locomotive vehicle health |
| CN110163374B (en) * | 2018-12-07 | 2022-02-11 | 贵州航天风华精密设备有限公司 | Fault diagnosis reasoning system based on Word general configuration |
| CN110163374A (en) * | 2018-12-07 | 2019-08-23 | 贵州航天风华精密设备有限公司 | A kind of fault diagnosis reasoning system based on Word generic configuration |
| CN109358255A (en) * | 2018-12-18 | 2019-02-19 | 北京交通大学 | Traction converter failure analysis method and device |
| CN109358255B (en) * | 2018-12-18 | 2024-03-05 | 北京交通大学 | Traction converter fault analysis method and device |
| TWI751464B (en) * | 2018-12-26 | 2022-01-01 | 日商納博特斯克股份有限公司 | Air compression system for railway vehicles |
| WO2020211846A1 (en) * | 2019-04-19 | 2020-10-22 | 深圳市德塔防爆电动汽车有限公司 | Safety tree model-based electric vehicle operation and maintenance optimization method |
| CN111845852A (en) * | 2019-04-24 | 2020-10-30 | 广州地铁集团有限公司 | Train traction lockout diagnosis method, system and device and readable storage medium |
| CN110262461A (en) * | 2019-07-03 | 2019-09-20 | 浙江好得电气有限公司 | Blower fan control system two dimensional code intelligent fault diagnosis method and system |
| CN112241511B (en) * | 2019-07-19 | 2024-05-14 | 上海杰之能软件科技有限公司 | Performance detection method and device for auxiliary electrical system of vehicle and terminal |
| CN112241511A (en) * | 2019-07-19 | 2021-01-19 | 上海杰之能软件科技有限公司 | Performance detection method and device of auxiliary electrical system of vehicle and terminal |
| CN110606100A (en) * | 2019-09-03 | 2019-12-24 | 中车青岛四方机车车辆股份有限公司 | Fault determination method and device |
| CN110646706A (en) * | 2019-09-12 | 2020-01-03 | 国电南瑞科技股份有限公司 | Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar |
| CN110837530A (en) * | 2019-11-07 | 2020-02-25 | 交控科技股份有限公司 | Fault information processing method and device based on rail transit integrated equipment monitoring |
| CN110827350B (en) * | 2019-12-10 | 2023-05-02 | 中交一公局电气化工程有限公司 | Tramcar real-time data acquisition system based on Labview and Modbus/TCP communication protocols |
| CN110827350A (en) * | 2019-12-10 | 2020-02-21 | 中交一公局电气化工程有限公司 | Tramcar real-time data acquisition system based on Labview and Modbus/TCP communication protocol |
| CN111337764A (en) * | 2020-02-14 | 2020-06-26 | 重庆国翰能源发展有限公司 | Charging pile fault diagnosis system and method and storage medium |
| CN113320565A (en) * | 2020-02-28 | 2021-08-31 | 株洲中车时代电气股份有限公司 | Vehicle-mounted real-time fault diagnosis method and device |
| CN111813807A (en) * | 2020-06-05 | 2020-10-23 | 中国电子科技集团公司电子科学研究院 | Real-time fault diagnosis method and device based on expert diagnosis library |
| CN111813807B (en) * | 2020-06-05 | 2024-01-12 | 中国电子科技集团有限公司电子科学研究院 | Expert diagnosis library-based real-time fault diagnosis method and device |
| CN111898195B (en) * | 2020-06-15 | 2023-10-13 | 北京交通大学 | Rail transit train system polymorphism reliability analysis method based on improved d-MC |
| CN111898195A (en) * | 2020-06-15 | 2020-11-06 | 北京交通大学 | Rail transit train system multi-state reliability analysis method based on improved d-MC |
| CN112379200B (en) * | 2020-11-10 | 2024-02-13 | 深圳市康必达控制技术有限公司 | Fault positioning and solving method |
| CN112379200A (en) * | 2020-11-10 | 2021-02-19 | 深圳市康必达控制技术有限公司 | Fault location and solution method |
| CN112224241B (en) * | 2020-11-18 | 2022-08-02 | 中国铁道科学研究院集团有限公司 | Speed acquisition system, fault alarm method and device |
| CN112224241A (en) * | 2020-11-18 | 2021-01-15 | 中国铁道科学研究院集团有限公司 | Speed acquisition system, fault alarm method and device |
| CN113238535A (en) * | 2021-06-03 | 2021-08-10 | 中国核动力研究设计院 | Fault diagnosis method and system for nuclear safety level DCS analog input module |
| CN113505282A (en) * | 2021-06-11 | 2021-10-15 | 国网浙江省电力有限公司嘉兴供电公司 | Expert system-based high-voltage circuit breaker state identification method and system |
| CN114462608A (en) * | 2022-04-12 | 2022-05-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Method, system, computer and storage medium for inferring traffic route problems |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102879680B (en) | 2015-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102879680B (en) | The general detection of rail transit vehicle equipment and method for diagnosing faults and system | |
| CN113283704B (en) | Intelligent power grid fault handling system and method based on knowledge graph | |
| CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
| CN106199276A (en) | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system | |
| CN105809260A (en) | Method for intelligently generating monitoring information point list of dispatching automation system | |
| CN103901882A (en) | Online monitoring fault diagnosis system and method of train power system | |
| CN107798395A (en) | A kind of power grid accident signal automatic diagnosis method and system | |
| CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN111444169A (en) | Transformer substation electrical equipment state monitoring and diagnosis system and method | |
| CN104463696A (en) | Power grid operating risk recognition and prevention method and system | |
| CN104777827A (en) | Method for diagnosing fault of high-speed railway signal system vehicle-mounted equipment | |
| CN112734256A (en) | Intelligent operation and maintenance system for rail transit vehicle | |
| CN102800030B (en) | Comprehensive reliability interactive iteration assessment method for regional power grid relay protection equipment | |
| CN110707687A (en) | Intelligent checking platform and method for power grid running state | |
| CN104091243A (en) | Intelligent switching operation ticket mechanism designing and achieving method | |
| CN107491876A (en) | A kind of methods of risk assessment of intelligent substation protection system | |
| CN111708817B (en) | Intelligent disposal method for transformer substation monitoring information | |
| CN104361531A (en) | Identification method and system for high-risk failure equipment of substation automation system | |
| CN106483472A (en) | A kind of power system failure diagnostic method based on airborne power supply management and control device | |
| Du et al. | A digital twin framework and an implementation method for urban rail transit | |
| CN113159517B (en) | Three-dimensional visual power grid operation data analysis system | |
| CN213894861U (en) | Escalator full life cycle data management system based on data center station | |
| CN112002179B (en) | Rail transit multiplex linkage control method and system based on remote distribution | |
| CN109543156A (en) | A kind of Substation switching automatic invoice issuance system based on IEC61850 | |
| CN107463162A (en) | Energy-conserving and environment-protective electronic logistic car fault diagnosis control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |