CN106547265A - A kind of live reliability estimation method and system of track traffic electronic-controlled installation - Google Patents
A kind of live reliability estimation method and system of track traffic electronic-controlled installation Download PDFInfo
- Publication number
- CN106547265A CN106547265A CN201610936093.8A CN201610936093A CN106547265A CN 106547265 A CN106547265 A CN 106547265A CN 201610936093 A CN201610936093 A CN 201610936093A CN 106547265 A CN106547265 A CN 106547265A
- Authority
- CN
- China
- Prior art keywords
- data
- life
- electronic
- span
- controlled installation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0281—Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
Landscapes
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Automation & Control Theory (AREA)
- Complex Calculations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of live reliability estimation method and system of track traffic electronic-controlled installation, and the method step includes:1) the original scene service data of all electronic-controlled installations in train is gathered, and the life-span for failure product in each electronic-controlled installation being calculated according to original scene service data becomes reconciled the truncation life-span of product, acquires the lifetime data of electronic-controlled installation;2) lifetime data of failure product in the lifetime data for getting is fitted according to various different distributions models respectively, the target distribution model of current age data distribution characteristic is determined for compliance with according to fitting result;3) reliability assessment is carried out according to target distribution model to lifetime data;The system includes data acquisition and procession module, Lifetime Distribution Analysis module and reliability assessment module.The present invention can realize the live reliability assessment of electronic-controlled installation, and have the advantages that implementation method simply, Evaluation accuracy and with a high credibility, applied widely.
Description
Technical field
The present invention relates to technical field of rail traffic, more particularly to a kind of scene reliability of track traffic electronic-controlled installation
Property appraisal procedure and system.
Background technology
Scientific and technological progress promotes track transportation industry to develop rapidly, electronic-controlled installation as collection control, network service and
The car-mounted device that the functions such as fault diagnosis are integrated, such as electronic control module, electronic control system etc., its reliability is to train net
Safe and reliable most important, requirement of the user to its reliability also more and more higher of network system.
It is less currently for the Research on Reliability Evaluation of track traffic electronic-controlled installation, it is typically based on testing or imitates
True existing, electronic-controlled installation generates substantial amounts of reliability information during development, test, operation, and the use of product can
Field data to be relied on just more accurately to be analyzed by property and life-span, and be based on test or emulation fail effectively utilizes operation
Reliability information, lacks the effective statistical analysiss to reliability information, thus Evaluation accuracy and credibility is not high.Existing scene
Operation reliability evaluation method is normally based on particular type and is distributed (such as exponential), i.e., be distributed as certain kinds to assume the life-span
It is estimated premised on type distribution, but the operating condition of electronic-controlled installation is complicated, is directly carried out using particular type distribution
Assessment time error is larger, it is impossible to obtains accurate assessment result, thus is not directly adaptable to use and track traffic Electronic Control is filled
The assessment put.
The content of the invention
The technical problem to be solved in the present invention is that:For the technical problem that prior art is present, the present invention provides one
The scene for planting simple implementation method, Evaluation accuracy and track traffic electronic-controlled installation with a high credibility and applied widely is reliable
Property appraisal procedure and system.
To solve above-mentioned technical problem, technical scheme proposed by the present invention is:
A kind of live reliability estimation method of track traffic electronic-controlled installation, step include:
1) data acquisition and procession:The original scene service data of all target electronic control devices in collection train, and
Become reconciled the truncation life-span of product according to the life-span of failure product in each electronic-controlled installation of original scene service data calculating, obtained
Obtain the lifetime data of electronic-controlled installation;
2) Lifetime Distribution Analysis:By the step 1) in the lifetime data that gets failure product lifetime data respectively according to
Various different distributions models are fitted, and are determined for compliance with the target distribution mould of current age data distribution characteristic according to fitting result
Type;
3) reliability assessment:To the step 1) lifetime data that gets, according to the step 2) determine the mesh for obtaining
Mark distributed model carries out reliability assessment, and assessment obtains the reliability of target electronic control device.
As the further improvement of the inventive method, the step 1) the middle longevity for calculating failure product in each electronic-controlled installation
Become reconciled truncation life-span of product of life concretely comprises the following steps:If failure product, from determining the life-span by the original scene service data of device
Begin to calculate point, and according to device down time and the life-span of the life-span initial calculation point computing device for determining;If preferably
Product, determine life-span initial calculation point and truncated time by the original scene service data of device, and according to the life-span for determining from
Begin to calculate the truncation life-span of point and truncated time computing device.
Used as the further improvement of the inventive method, what the life-span initial calculation point determined concretely comprises the following steps:From original
In field operational data, according to device initial operation time, carry vehicle on-line time, carry the vehicle time of making the product and device
The priority orders at the time of making the product make a look up, by the time for preferentially finding as the life-span initial calculation point.
As the further improvement of the inventive method, the step 2) concretely comprise the following steps:
2.11) to the step 1) lifetime data of failure product is counted in the lifetime data that gets, and press respectively
It is fitted according to various different distributions models, obtains the fitting result of lifetime data statistical result and each distributed model of correspondence;
2.22) fitting result of each distributed model is compared with the lifetime data statistical result respectively, by
Comparative result determination obtains meeting the target distribution model of current age data distribution characteristic.
As the further improvement of the inventive method:The step 2.11) in specifically by the rectangular histogram of the lifetime data
As lifetime data statistical result.
As the further improvement of the inventive method, the step 2) also include distributed model testing sequence, concrete steps
For:By the step 1) lifetime data of failure product is ranked up successively in the lifetime data that gets, and according to target distribution
Failure probability that model conversion is obtained, linear relationship generating probability curve between the out-of-service time;Whether judge the probability curve
Tend to linear, if it is, determination check passes through, proceed to execution step 3);Otherwise determination check does not pass through, and return performs step
It is rapid 2) redefining target distribution model
As the further improvement of the inventive method, the step 3) concretely comprise the following steps:
3.1) to the step 1) lifetime data that gets, according to the step 2) the target distribution model that determines carries out
Parameter estimation, obtains estimates of parameters;
3.2) to determining that the Reliability Function for obtaining is solved by the estimates of parameters, obtain electronic-controlled installation
Q-percentile life, and Electronic Control is calculated by the estimates of parameters, the corresponding failure density function of target distribution model
The average life of device.
As the further improvement of the inventive method:The step 3.1) in specifically carried out using Maximum Likelihood Estimation
Parameter estimation.
As the further improvement of the inventive method:The distributed model specifically includes exponential distribution model, Weibull point
Cloth model and logarithm normal distribution model.
A kind of live reliability evaluation system of track traffic electronic-controlled installation, including:
Data acquisition and procession module, the original scene for gathering all target electronic control devices in train run number
According to, and become reconciled the truncation longevity of product according to the life-span of failure product in each electronic-controlled installation of original scene service data calculating
Life, acquires the lifetime data of electronic-controlled installation;
Lifetime Distribution Analysis module, for failure product in the lifetime data that gets the lifetime data acquisition module
Lifetime data is fitted according to various different distributions models respectively, is determined for compliance with current age data distribution according to fitting result
The target distribution model of characteristic;
Reliability assessment module, for the lifetime data got to the lifetime data acquisition module, according to the longevity
Life distributional analysiss module determines that the target distribution model for obtaining carries out reliability assessment, and assessment obtains target electronic control device
Reliability.
Compared with prior art, it is an advantage of the current invention that:
1) present invention carries out reliability assessment based on the field operational data of electronic-controlled installation, effectively make use of
Electronic installation scene reliability of operation information, compared to test, the assessment result more true and accurate of emulation mode, by right
The process of original scene service data gets lifetime data and is analyzed, by failure product lifetime data respectively according to various differences
Distributed model is fitted, and is determined for compliance with the target distribution model of lifetime data distribution character, with traditional directly using specific
Distribution pattern is estimated, and can accurately characterize the life-span distribution character of electronic-controlled installation such that it is able to suitable for track
The reliability assessment of high accuracy and credibility is realized in vehicular traffic to electronic-controlled installation;
2) present invention can determine different life distribution types for the field operational data of different device, can be applied to
Assessment in track traffic to all kinds of electronic-controlled installations, applied widely, universality are strong;
3) present invention makes full use of a large amount of reliability informations of electronic-controlled installation to be estimated, and can be applied to large sample
In the case of electronic-controlled installation live reliability assessment, so as to instruct the reliability level control of large sample electronic-controlled installation
System;
4) present invention realizes adopting for original scene service data further using the data processing method based on priority
Collection, arrangement and analysis, can realize the standardization processing of live authentic communication, while can be as far as possible for different aforementioned sources
Accurate lifetime data is acquired, the utilization rate of live authentic communication is drastically increased, while ensureing reliability assessment
Precision, credibility.
Description of the drawings
Fig. 1 be the live reliability estimation method of the present embodiment track traffic electronic-controlled installation realize flow process illustrate
Figure.
Fig. 2 is that the live reliability estimation method of electronic-controlled installation in the specific embodiment of the invention realizes that flow process is illustrated
Figure.
Fig. 3 is lifetime data statistical result and fitting result schematic diagram in the specific embodiment of the invention.
Fig. 4 be in the specific embodiment of the invention obtained by lifetime data probability curve schematic diagram.
Fig. 5 be in the specific embodiment of the invention obtained by reliability curve schematic diagram.
Specific embodiment
Below in conjunction with Figure of description and concrete preferred embodiment, the invention will be further described, but not therefore and
Limit the scope of the invention.
As shown in figure 1, the live reliability estimation method of the present embodiment track traffic electronic-controlled installation, step includes:
1) data acquisition and procession:The original scene service data of all target electronic control devices in collection train, and
Become reconciled the truncation life-span of product according to the life-span of failure product in each electronic-controlled installation of original scene service data calculating, acquired
The lifetime data of electronic-controlled installation;
2) Lifetime Distribution Analysis:By step 1) in the lifetime data that gets failure product lifetime data respectively according to various
Different distributions model is fitted, and is determined for compliance with the target distribution model of current age data distribution characteristic according to fitting result;
3) reliability assessment:To step 1) lifetime data that gets, according to step 2) determine the target distribution mould for obtaining
Type carries out reliability assessment, and assessment obtains the reliability of target electronic control device.
The present embodiment carries out reliability assessment based on the field operational data of electronic-controlled installation, effectively make use of
Electronic installation scene reliability of operation information, compared to test, the assessment result more true and accurate of emulation mode, by right
The process of original scene service data gets lifetime data and is analyzed, by failure product lifetime data respectively according to various differences
Distributed model is fitted, and is determined for compliance with the target distribution model of lifetime data distribution character, with traditional directly using specific
Distribution pattern is estimated, and can accurately characterize the life-span distribution character of electronic-controlled installation, so as to realize high accuracy and can
The electronic-controlled installation reliability assessment of reliability.
In the present embodiment, step 1) in calculate life-span of failure product in each electronic-controlled installation and become reconciled truncation life-span of product
Concretely comprise the following steps:If failure product, life-span initial calculation point is determined by the original scene service data of device, and is sent out according to device
Raw fault time and the life-span of the life-span initial calculation point computing device for determining;If preferably product, are transported by the original scene of device
Row data determine life-span initial calculation point and truncated time, and are calculated according to the life-span initial calculation point and truncated time for determining
The truncation life-span of device.
In the present embodiment, what life-span initial calculation point determined concretely comprises the following steps:From the service data of original scene, according to dress
Put initial operation time, the priority orders carried vehicle on-line time, carry the vehicle time of making the product and the device time of making the product
Make a look up, by the time for preferentially finding as life-span initial calculation point.Determine that electronic-controlled installation life-span flow process is concrete
It is as follows:
If failure product, the determining device life-span concretely comprises the following steps:
1.11) search whether there is the record of device initial operation time, if it has, by device down time, dress
Put initial operation time and determine the life-span for obtaining device, otherwise proceed to execution step 1.12);
1.12) search whether there is the record for carrying vehicle on-line time, if it has, by device down time, taking
Carry vehicle on-line time and determine the life-span for obtaining device;Execution step is proceeded to otherwise 1.13);
1.13) search whether there is the record for carrying the vehicle time of making the product, if it has, by device down time, taking
Carry the life-span that the determination of the vehicle time of making the product obtains device;Execution step is proceeded to otherwise 1.14);
1.14) record at the device time of making the product is searched whether, if it has, being dispatched from the factory by device down time, device
The life-span of time determining device.
If preferably product, determine concretely comprising the following steps for corresponding life-span:
1.21) search whether there is the record of device initial operation time, if it has, being opened by data statisticss time, device
Beginning run time determines the truncation life-span for obtaining device;Execution step is proceeded to otherwise 1.22);
1.22) search whether there is the record that device carries vehicle on-line time, if it has, by the data statisticss time, taking
Carry vehicle on-line time and determine the truncation life-span for obtaining device;Execution step is proceeded to otherwise 1.23);
1.23) search whether there is the record that device carries the vehicle time of making the product, if it has, by data statisticss time, dress
Put the truncation life-span for carrying that the determination of the vehicle time of making the product obtains device;Execution step is proceeded to otherwise 1.24);
1.24) search whether to there are the record at the device time of making the product, if it has, being dispatched from the factory by data statisticss time, device
Time determines the truncation life-span for obtaining device.
The live reliability information source of track traffic electronic-controlled installation is generally of low quality, such as there may be and cannot determine
Device making time, only comprising fault data, the disappearance situation such as Random Censorship and normal work life of product data, it is impossible to
Use directly as assessment data.The present embodiment by realizing the collection of original scene service data, arranging using said method
And analysis, the standardization processing of live authentic communication can be realized, while can obtain as far as possible for different aforementioned sources
To accurate lifetime data, it is ensured that the precision of reliability assessment, credibility.
The present embodiment specifically gathers the urban rail transit vehicles online operation time first to electronics in the data statisticss time
The original scene service data of control device is analyzed.For the fault data of failure product, pick-up time, failure can be obtained
Time, troubleshooting end time, failure product reception time, reparation product send time etc., by the information source situation of fault data
Specifically processed by table 1 with computing device life-span (run time).
Table 1:Field failure data processing.
For the fault-free censored data of failure free operation device, by information source situation in data specifically according to table 2
Processed with the computing device truncation life-span.
Table 2:Live failure-free data is processed.
Consider the too short impact to assessment result of truncated time, the present embodiment specifically (is specifically taken the service time shorter<1
Year) device lifetime data definition be invalid data, will collection data remove invalid data after finally give Electronic Control dress
The overall life data put.
In the specific embodiment of the invention, the counted overall life data for obtaining are as shown in table 3 below.
Table 3:Electronic-controlled installation lifetime data.
In the present embodiment, step 2) concretely comprise the following steps:
2.11) to step 1) lifetime data of failure product is counted in the lifetime data that gets, and respectively according to many
Plant different distributions model to be fitted, obtain the fitting result of lifetime data statistical result and each distributed model of correspondence;
2.22) fitting result of each distributed model is compared with lifetime data statistical result respectively, by comparative result
It is determined that obtaining meeting the target distribution model of current age data distribution characteristic.
The present embodiment on the basis of lifetime data is fitted according to various different distributions models, by each distributed model
Fitting result be compared with lifetime data statistical result respectively, can fast and accurately determine and meet the most current age
The distributed model of data distribution characteristic, it is ensured that the precision and credibility of reliability assessment.
In the present embodiment, step 2.11) in specifically by the rectangular histogram of lifetime data as lifetime data statistical result.I.e. by
The lifetime data of failure product draws rectangular histogram, and is fitted by specified various distributed models respectively, by the plan of each distributed model
Close result to be compared with lifetime data rectangular histogram respectively, the distributed model for meeting the most is selected as target distribution model.
In the present embodiment, step 2) also include distributed model testing sequence, concretely comprise the following steps:By step 1) longevity for getting
Fate lifetime data of failure product according in is ranked up successively, and obtain according to target distribution model conversion failure probability, lose
Linear relationship generating probability curve between the effect time;Judge whether probability curve tends to linear, if it is, determination check is logical
Cross, proceed to execution step 3);Otherwise determination check does not pass through, and returns execution step 2) to redefine target distribution model.
The present embodiment is concrete to primarily determine that target distribution model by the fitting result of each distributed model first, then to determination
Distributed model is tested, and the idiographic flow of inspection is:
1. n lifetime data is ranked up successively:x(1)≤x(2)≤…≤x(n);
2. line translation is entered to the current distributed model for determining, obtains the linear relationship of failure probability and out-of-service time;
3. the coordinate for 2. n lifetime data being exported according to step successively described point one by one on probability paper, obtains life-span number
According to probability curve;
4. judge whether probability curve tends to linear, i.e. each point approximately in straight line, show that current age data are come
From the distribution totality of current distributed model, i.e., current distributed model meets current age data distribution characteristic, does not otherwise meet and work as
Front lifetime data distribution character, needs to redefine distributed model.
In the present embodiment, step 3) concretely comprise the following steps:
3.1) to step 1) lifetime data that gets, according to step 2) the target distribution model that determines enters line parameter and estimates
Meter, obtains estimates of parameters;
3.2) to determining that by estimates of parameters the Reliability Function for obtaining is solved, obtain the reliability of electronic-controlled installation
Life-span, and the flat of electronic-controlled installation is calculated by estimates of parameters, the corresponding failure density function of target distribution model
The equal life-span.
In the present embodiment, step 3.1) in parameter estimation, parameter estimation reality are carried out using Maximum Likelihood Estimation specifically
Now simple and high precision.
After determining the distributed model of current age data, you can with determine corresponding distribution function, failure density function with
And Reliability Function.Live running similar to a Based on Censored Data process for having replacement, is utilized greatly seemingly by the present embodiment
So method of estimation estimates distributed constant;The Reliability Function of correspondence distribution can be obtained according to parameter estimation result, when known reliability
During degree R, the time t in Reliability Function is solved, Q-percentile life t is obtainedR;To estimate that parameter is substituted in failure density function, and
The mathematic expectaion of seeking time t, obtains average life E (T), and by reliability, Q-percentile life can assessment electronics dress as evaluation index
The reliability state put.
Exponential distribution model, Weibull distributed models (two-parameter weibull distribution model) are included with distributed model below
And the present invention is further described as a example by three kinds of logarithm normal distribution model.
Exponential can characterize the life-span distribution after rejecting initial failure, now accidental mistake of the product in life cycle
Effect phase, failure rate estimation are constant;The form parameter m value of Weibull distributions is different, can characterize the difference of product life cycle
In the stage, work as m<When 1, failure rate estimation monotone decreasing, product are in earlier failure period, and during m=1, Weibull distributions are index
Distribution, during m > 1, failure rate estimation monotonic increase, product are in wear-out failure period;The failure rate estimation of logarithm normal distribution from
Zero starts, and first rises and declines afterwards.Each distribution character and parameter estimation procedure are as follows:
1. exponential
The failure density function of exponential is:
F (t)=λ e-λt (1)
(2) are estimated to exponential parameter according to the following formula:
2. Weibull distributions
Weibull distribution failure density function be:
(4), (5) are estimated to Weibull distributed constants according to the following formula:
Wherein, transcendental equation of the formula (4) with regard to m is solved, the 1. formula that substitutes into can obtain the estimated value of η.
3. logarithm normal distribution
The failure density function of logarithm normal distribution is:
(7) are estimated to Weibull distributed constants according to the following formula:
Wherein,
As shown in Fig. 2 the present embodiment realizes that the idiographic flow of electronic-controlled installation scene reliability assessment is:
Step one:Data acquisition and procession
The original scene service data (field failure information) of electronic-controlled installation is gathered by qualitative data Surveillance center,
Including fault data and fault-free censored data;Original scene service data is processed, for failure product, failure is determined
Product pick-up time, fault time, run time, for fault-free product (good product), when determining that fault-free product sum, fault-free are got on the bus
Between, data available is obtained after the completion of process and forms reliability information storehouse;In reliability information storehouse, to each electronic-controlled installation base
In initial operation time, the priority orders carried vehicle on-line time, carry the vehicle time of making the product and the device time of making the product
Search, the time for preferentially finding calculates point as life-span starting point, calculate the life-span or truncation life-span of each device, obtain electronics control
The lifetime data of device processed.
Step 2:Lifetime Distribution Analysis.
The present embodiment is got after lifetime data respectively to failure product using reliability, Q-percentile life as evaluation index
The distribution of lifetime data fit indices, Weibull distributions and logarithm normal distribution simultaneously draw rectangular histogram, the probability density letter of fitting
Number curve and lifetime data histogram results are as shown in figure 3, from comparing result in figure, the failure of Weibull distributions is general
Rate density function is coincide the most with field life data, then the life-span of preliminary judgement electronic-controlled installation be distributed as Weibull point
Cloth.
Step 3:Life-span distribution inspection.
The failure probability that the lifetime data of failure product is distributed based on Weibull and the linear relationship of out-of-service time, general
Generating probability curve on rate paper.Resulting Weibull probability curves as shown in figure 4, it is seen that data point substantially into
Straight line, it is taken as that life-span obedience two-parameter weibull distribution Wei (m, η) of the electronic-controlled installation.That is fault density
Shown in function such as formula (3).
Step 4:Reliability assessment.
The lifetime data obtained by step one, using life-span distribution ginseng of the Maximum Likelihood Estimation to electronic-controlled installation
Number is estimated that the likelihood function of wherein two-parameter weibull distribution Wei (m, η) is:
Formula (8) both sides are taken the logarithm, you can obtain log-likelihood function:
Seek local derviation to parameter m and η respectively, and make local derviation be zero, then obtain equation group:
Solving equation group (10) can obtain parameter m and the estimated value of η is:
The Reliability Function that electronic-controlled installation under weibull distribution occasions can be obtained by estimates of parameters then is:
Q-percentile life is:
According to the above-mentioned estimation formulas of Q-percentile life, and life level when reliability is 0.9 and 0.5 is paid close attention to, can be obtained:
1., when reliability is 0.9, the Q-percentile life that can be calculated electronic-controlled installation is 321 days, is slightly less than 11 months;
2., when reliability is 0.5, the median life of product is 2803 days, about 7.68.
According to the estimated result of average life, can obtain average life is:
That is the MTBF of device is 4273 days, about 11.71.
The resulting electronic-controlled installation reliability curves of this enforcement are illustrated in figure 5, by reliability curves characterization apparatus
Use reliability trend over time.
Step 5:Assessment result is analyzed.
As shown in figure 5, the reliability of electronic-controlled installation declines in early stage rapidly in the present embodiment, after tend to be steady, say
The initial failure of bright product is more.Additionally, form parameter m=0.86938 of weibull distributions<1, also illustrate that product is located at present
In infant mortality stage.Accordingly it is contemplated that strengthen the screening conditions before product export, what reduction was brought due to reasons
Initial failure, so as to improve the inherent reliability level of product.
The present embodiment distributed model be exponential distribution model, Weibull distributed models and logarithm normal distribution model, when
Other types distributed model so can also be set according to the actual requirements, further to improve Evaluation accuracy.
The live reliability evaluation system of the present embodiment middle orbit electronic traffic control device, including:
Data acquisition and procession module, the original scene for gathering all target electronic control devices in train run number
According to, and become reconciled the truncation life-span of product according to the life-span of failure product in each electronic-controlled installation of original scene service data calculating, obtain
Obtain the lifetime data of electronic-controlled installation;
Lifetime Distribution Analysis module, for the life-span of failure product in the lifetime data that gets lifetime data acquisition module
Data are fitted according to various different distributions models respectively, are determined for compliance with current age data distribution characteristic according to fitting result
Target distribution model;
Reliability assessment module, for the lifetime data got to lifetime data acquisition module, according to life-span distribution point
Analysis module determines that the target distribution model for obtaining carries out reliability assessment, and assessment obtains the reliability of target electronic control device.
The present embodiment assessment system is system corresponding with above-mentioned appraisal procedure, and its principle is consistent with said method.
Above-mentioned simply presently preferred embodiments of the present invention, not makees any pro forma restriction to the present invention.Although of the invention
It is disclosed above with preferred embodiment, but it is not limited to the present invention.Therefore, it is every without departing from technical solution of the present invention
Content, according to the technology of the present invention essence to any simple modification made for any of the above embodiments, equivalent variations and modification, all should fall
In the range of technical solution of the present invention protection.
Claims (10)
1. a kind of live reliability estimation method of track traffic electronic-controlled installation, it is characterised in that step includes:
1) data acquisition and procession:The original scene service data of all target electronic control devices in collection train, and according to
The original scene service data calculates the life-span of failure product in each electronic-controlled installation and becomes reconciled truncation life-span of product, acquires
The lifetime data of electronic-controlled installation;
2) Lifetime Distribution Analysis:By the step 1) in the lifetime data that gets failure product lifetime data respectively according to various
Different distributions model is fitted, and is determined for compliance with the target distribution model of current age data distribution characteristic according to fitting result;
3) reliability assessment:To the step 1) lifetime data that gets, according to the step 2) determine the target point for obtaining
Cloth model carries out reliability assessment, and assessment obtains the reliability of target electronic control device.
2. the live reliability estimation method of track traffic electronic-controlled installation according to claim 1, it is characterised in that
The step 1) in calculate become reconciled truncation life-span of product in life-span of failure product in each electronic-controlled installation and concretely comprise the following steps:If
Failure product, determine life-span initial calculation point by the original scene service data of device, and according to device down time and really
The life-span of the life-span initial calculation point computing device for arriving surely;If preferably product, determine the life-span by the original scene service data of device
Initial calculation point and truncated time, and according to the truncation longevity of the life-span initial calculation point and truncated time computing device for determining
Life.
3. the live reliability estimation method of track traffic electronic-controlled installation according to claim 2, it is characterised in that
What the life-span initial calculation point determined concretely comprises the following steps:From the service data of original scene, according to device initial operation time,
The priority orders for carrying vehicle on-line time, the carrying vehicle time of making the product and the device time of making the product make a look up, by preferential
The time for finding is used as the life-span initial calculation point.
4. the live reliability estimation method of track traffic electronic-controlled installation according to claim 3, it is characterised in that
The step 2) concretely comprise the following steps:
2.11) to the step 1) lifetime data of failure product is counted in the lifetime data that gets, and respectively according to many
Plant different distributions model to be fitted, obtain the fitting result of lifetime data statistical result and each distributed model of correspondence;
2.22) fitting result of each distributed model is compared with the lifetime data statistical result respectively, by comparing
As a result determine and obtain meeting the target distribution model of current age data distribution characteristic.
5. the live reliability estimation method of track traffic electronic-controlled installation according to claim 4, it is characterised in that
The step 2.11) in specifically by the rectangular histogram of the lifetime data as lifetime data statistical result.
6. the live reliability estimation method of track traffic electronic-controlled installation according to claim 4, it is characterised in that
The step 2) also include distributed model testing sequence, concretely comprise the following steps:By the step 1) in the lifetime data that gets therefore
The lifetime data of barrier product is ranked up successively, and obtain according to target distribution model conversion failure probability, between the out-of-service time
Linear relationship generating probability curve;Judge whether the probability curve tends to linear, if it is, determination check passes through, turn
Enter execution step 3);Otherwise determination check does not pass through, and returns execution step 2) to redefine target distribution model.
7. the live reliability assessment side of the track traffic electronic-controlled installation according to any one in claim 1~6
Method, it is characterised in that the step 3) concretely comprise the following steps:
3.1) to the step 1) lifetime data that gets, according to the step 2) the target distribution model that determines enters line parameter
Estimate, obtain estimates of parameters;
3.2) to determining that the Reliability Function for obtaining is solved by the estimates of parameters, obtain the reliability of electronic-controlled installation
Life-span, and electronic-controlled installation is calculated by the estimates of parameters, the corresponding failure density function of target distribution model
Average life.
8. the live reliability estimation method of track traffic electronic-controlled installation according to claim 7, it is characterised in that
The step 3.1) in parameter estimation is carried out using Maximum Likelihood Estimation specifically.
9. the live reliability assessment side of the track traffic electronic-controlled installation according to any one in claim 1~6
Method, it is characterised in that:The distributed model specifically includes exponential distribution model, Weibull distributed models and lognormal point
Cloth model.
10. a kind of live reliability evaluation system of track traffic electronic-controlled installation, it is characterised in that include:
Data acquisition and procession module, for gathering the original scene service data of all target electronic control devices in train,
And become reconciled the truncation life-span of product according to the life-span of failure product in each electronic-controlled installation of original scene service data calculating, obtain
Obtain the lifetime data of electronic-controlled installation;
Lifetime Distribution Analysis module, for the life-span of failure product in the lifetime data that gets the lifetime data acquisition module
Data are fitted according to various different distributions models respectively, are determined for compliance with current age data distribution characteristic according to fitting result
Target distribution model;
Reliability assessment module, for the lifetime data got to the lifetime data acquisition module, according to the life-span point
Cloth analysis module determines that the target distribution model for obtaining carries out reliability assessment, and assessment obtains the reliability of target electronic control device
Property.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610936093.8A CN106547265B (en) | 2016-11-01 | 2016-11-01 | A kind of live reliability estimation method and system of rail traffic electronic control unit |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610936093.8A CN106547265B (en) | 2016-11-01 | 2016-11-01 | A kind of live reliability estimation method and system of rail traffic electronic control unit |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106547265A true CN106547265A (en) | 2017-03-29 |
CN106547265B CN106547265B (en) | 2019-01-29 |
Family
ID=58392267
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610936093.8A Active CN106547265B (en) | 2016-11-01 | 2016-11-01 | A kind of live reliability estimation method and system of rail traffic electronic control unit |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106547265B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108595847A (en) * | 2018-04-27 | 2018-09-28 | 公安部天津消防研究所 | A kind of appraisal procedure for gas extinguishing system reliability |
CN109766217A (en) * | 2018-12-20 | 2019-05-17 | 北京梧桐车联科技有限责任公司 | A kind of vehicle system fault repairing method and device |
CN111027988A (en) * | 2019-12-05 | 2020-04-17 | 山东中车风电有限公司 | Product reliability pre-estimation system based on truncated data |
CN111679955A (en) * | 2020-08-11 | 2020-09-18 | 北京东方通软件有限公司 | Monitoring diagnosis and snapshot analysis system for application server |
CN111814360A (en) * | 2020-08-24 | 2020-10-23 | 中国人民解放军海军航空大学青岛校区 | Method for evaluating use reliability of airborne electromechanical equipment |
CN112257215A (en) * | 2019-07-02 | 2021-01-22 | 中车株洲电力机车研究所有限公司 | Maximum likelihood estimation solving method and system for product life distribution parameters |
CN112379198A (en) * | 2020-11-05 | 2021-02-19 | 华润电力技术研究院有限公司 | Method and system for evaluating residual life of equipment |
CN112966093A (en) * | 2021-03-04 | 2021-06-15 | 北京航空航天大学 | Method, device, equipment and medium for improving electronic product |
CN113468039A (en) * | 2021-08-30 | 2021-10-01 | 深圳荣耀智能机器有限公司 | Reliability evaluation method and related equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070274304A1 (en) * | 2006-05-23 | 2007-11-29 | Lycette William H | Fail rate method for fast measurement of equipment reliabiliy |
CN102103658A (en) * | 2010-12-03 | 2011-06-22 | 北京航空航天大学 | Practical electronic product service life evaluation model parameter high-accuracy extraction method |
CN104933323A (en) * | 2015-07-10 | 2015-09-23 | 北京航空航天大学 | Method for evaluating reliability by fusing success/failure data and failure time data of product |
CN105718722A (en) * | 2016-01-18 | 2016-06-29 | 中国人民解放军国防科学技术大学 | Product reliability estimation method based on time-truncated life testing data |
-
2016
- 2016-11-01 CN CN201610936093.8A patent/CN106547265B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070274304A1 (en) * | 2006-05-23 | 2007-11-29 | Lycette William H | Fail rate method for fast measurement of equipment reliabiliy |
CN102103658A (en) * | 2010-12-03 | 2011-06-22 | 北京航空航天大学 | Practical electronic product service life evaluation model parameter high-accuracy extraction method |
CN104933323A (en) * | 2015-07-10 | 2015-09-23 | 北京航空航天大学 | Method for evaluating reliability by fusing success/failure data and failure time data of product |
CN105718722A (en) * | 2016-01-18 | 2016-06-29 | 中国人民解放军国防科学技术大学 | Product reliability estimation method based on time-truncated life testing data |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108595847A (en) * | 2018-04-27 | 2018-09-28 | 公安部天津消防研究所 | A kind of appraisal procedure for gas extinguishing system reliability |
CN109766217A (en) * | 2018-12-20 | 2019-05-17 | 北京梧桐车联科技有限责任公司 | A kind of vehicle system fault repairing method and device |
CN112257215A (en) * | 2019-07-02 | 2021-01-22 | 中车株洲电力机车研究所有限公司 | Maximum likelihood estimation solving method and system for product life distribution parameters |
CN111027988A (en) * | 2019-12-05 | 2020-04-17 | 山东中车风电有限公司 | Product reliability pre-estimation system based on truncated data |
CN111027988B (en) * | 2019-12-05 | 2023-07-14 | 山东中车风电有限公司 | Product reliability prediction system based on truncated data |
CN111679955A (en) * | 2020-08-11 | 2020-09-18 | 北京东方通软件有限公司 | Monitoring diagnosis and snapshot analysis system for application server |
CN111814360A (en) * | 2020-08-24 | 2020-10-23 | 中国人民解放军海军航空大学青岛校区 | Method for evaluating use reliability of airborne electromechanical equipment |
CN112379198A (en) * | 2020-11-05 | 2021-02-19 | 华润电力技术研究院有限公司 | Method and system for evaluating residual life of equipment |
CN112966093A (en) * | 2021-03-04 | 2021-06-15 | 北京航空航天大学 | Method, device, equipment and medium for improving electronic product |
CN113468039A (en) * | 2021-08-30 | 2021-10-01 | 深圳荣耀智能机器有限公司 | Reliability evaluation method and related equipment |
CN113468039B (en) * | 2021-08-30 | 2021-12-17 | 深圳荣耀智能机器有限公司 | Reliability evaluation method and related equipment |
Also Published As
Publication number | Publication date |
---|---|
CN106547265B (en) | 2019-01-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106547265B (en) | A kind of live reliability estimation method and system of rail traffic electronic control unit | |
WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
Zheng et al. | From univariate to bivariate extreme value models: Approaches to integrate traffic conflict indicators for crash estimation | |
CN106649709B (en) | Vehicle stopping behavior pattern prediction and evaluation method based on data mining | |
CN110288032A (en) | A kind of vehicle driving trace type detection method and device | |
CN106485528A (en) | The method and apparatus of detection data | |
CN108389631A (en) | Varicella morbidity method for early warning, server and computer readable storage medium | |
CN110598999B (en) | Traffic travel analysis method, system and storage medium based on individual data | |
CN107330469A (en) | A kind of trip mode recognition methods based on GPS track data | |
CN114236645B (en) | Large-scale rainfall monitoring abnormal site screening method | |
CN109254861A (en) | OD requirement extract and its analysis method for reliability based on track data | |
CN112153574B (en) | Method and system for checking accuracy of roadside device clock based on floating vehicle | |
CN110706016A (en) | Method and device for detecting business abnormity and computer readable storage medium | |
CN107798418A (en) | A kind of traffic accident frequency Forecasting Methodology based on traffic analysis cell | |
CN107093224B (en) | Overspeed of vehicle detection data efficiency assessment method | |
CN110164136A (en) | Fake license plate vehicle recognition method | |
Egozcue et al. | Wave-height hazard analysis in Eastern Coast of Spain-Bayesian approach using generalized Pareto distribution | |
CN115248993A (en) | Method and device for detecting reality of simulation scene model and storage medium | |
CN112614309B (en) | Geological disaster meteorological early warning accuracy rate calculation method | |
CN114648310A (en) | Supplier behavior data analysis method, system and device | |
CN114328479A (en) | Anomaly detection method oriented to financial stream data | |
CN113808393A (en) | Method for eliminating influence of hybrid control object | |
CN106323329B (en) | Mileage acquisition methods and device based on vehicle diagnosing system | |
CN114333334B (en) | Automatic road monitoring method and system and network side server | |
CN109598464A (en) | A kind of calculation method of exponential unit spare part loss quantity |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |