CN107015875A - A kind of complete electronic set storage life appraisal procedure and device - Google Patents
A kind of complete electronic set storage life appraisal procedure and device Download PDFInfo
- Publication number
- CN107015875A CN107015875A CN201710206016.1A CN201710206016A CN107015875A CN 107015875 A CN107015875 A CN 107015875A CN 201710206016 A CN201710206016 A CN 201710206016A CN 107015875 A CN107015875 A CN 107015875A
- Authority
- CN
- China
- Prior art keywords
- data
- sample
- electronic set
- complete electronic
- complete
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/008—Reliability or availability analysis
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of complete electronic set storage life appraisal procedure and device.Method includes：Obtain the Performance Degradation Data and the natural storage time limit of complete electronic set；Test sample in the Performance Degradation Data builds degraded data trend model, and the checking sample in the degraded data trend model and the Performance Degradation Data, obtains the bimetry of the complete electronic set；Accelerated factor is obtained according to the natural storage time limit and pre-established acceleration model；The characteristics life of the complete electronic set is obtained according to the bimetry of the complete electronic set and the accelerated factor.The present invention is analyzed by the Performance Degradation Data to complete electronic set, and according to the life-span of analysis result assessment electronics complete machine, the storage time limit for being then based on complete electronic set analyzes the accelerated factor of complete electronic set, and then the characteristics life of the life-span evaluated and accelerated factor assessment electronics complete machine is combined, have the advantages that assessment accuracy is high.
Description
Technical field
The present invention relates to complete electronic set technical field, and in particular to a kind of complete electronic set storage life appraisal procedure and dress
Put.
Background technology
In complete electronic set accelerated storage test, due to reasons such as electronic system product function complexity, there are properties of product
Deterioration law complexity, natural storage data and accelerated storage test data and situation about depositing.Such case causes result of the test
The difficulty of assessment, traditional accelerated test data assessment method can not carry out data processing for such case so that can not
Assess the accelerated factor or storage life for obtaining product, it is impossible to reach test objective.
For electronic system product performance degradation rule is complicated, natural storage data and accelerated storage test data and deposit feelings
The assessment approach of condition is common at present, be also the engineering problem of urgent need to resolve.Can using effective accelerated test appraisal procedure
To improve effective utilization to data resource, and then improve the accuracy of assessment result, in some instances it may even be possible to influence result of study, reduce
The hidden danger that situations such as life appraisal result is inaccurate is brought.
When carrying out trend prediction to properties of product deterioration law, conventional processing method is regression analysis, returns and divides
Analysis method carries out regression fit with linear function, exponential function, power function etc. to the Performance Degradation Data of product, obtains degradation trend
Regression equation, then carry out the prediction of degradation trend, but for the complicated non-linear degradation data of certain law, regression analysis side
The precision of method is not high, or even is difficult to apply sometimes.The focus studied at present also has artificial neural network method, but in engineer applied
In, prediction of the Artificial Neural Network to product degradation trend is not satisfactory, and its application need further research.
During the present invention is realized, inventor has found for natural storage data and accelerated storage test data and deposited
Situation, current processing method is first to carry out result of the test assessment using accelerated test data, obtains the storage life of product
As a result, the natural storage time then is simply added in lifetime results, or even can be neglected certainly when assessing accelerated factor sometimes
Right store data, these processing methods can all cause assessment result to produce deviation.
The content of the invention
It is an object of the invention to solve prior art to carry out electronic system product the assessment news commentary of storage life
Estimate the problem of result has error.
The present invention proposes a kind of complete electronic set storage life appraisal procedure, including：
Obtain the Performance Degradation Data and the natural storage time limit of complete electronic set；
Test sample in the Performance Degradation Data builds degraded data trend model, and according to the degeneration number
According to the checking sample in trend model and the Performance Degradation Data, the bimetry of the complete electronic set is obtained；
Accelerated factor is obtained according to the natural storage time limit and pre-established acceleration model；
The characteristics life of the complete electronic set is obtained according to the bimetry of the complete electronic set and the accelerated factor.
Optionally, the Performance Degradation Data includes：It is multigroup including properties of product data and with the properties of product data
Corresponding detection time sample data；
Correspondingly, the test sample in the Performance Degradation Data builds degraded data trend model and included：
The Performance Degradation Data is divided into by test sample and checking sample according to the detection time；
Initial degraded data trend model is set up using SVMs；
Using the properties of product data in the test sample as input vector, Performance Degradation Data value is output vector, profit
The initial degraded data trend model is trained with least square method supporting vector machine algorithm, degraded data trend mould is built
Type.
Optionally, the checking sample in the degraded data trend model and the Performance Degradation Data,
Obtaining the bimetry of the complete electronic set includes：
According to the sequencing of detection time, perform prediction step；
The prediction steps include：
Using the detection time in first group of sample data in the checking sample as input, become with reference to the degraded data
Potential model, obtains the predicted value of corresponding particular product performance parameters；
Judge whether the predicted value of the particular product performance parameters reaches the upper limit or lower limit of product failure threshold values；
If so, then using the corresponding detection time of the predicted value of the particular product performance parameters as the complete electronic set prediction
Life-span.
Optionally, if the predicted value of the particular product performance parameters is not up to the upper limit or lower limit of product failure threshold values,
First group of sample data in the checking sample is updated to the degraded data trend model；
First group of sample data in the checking sample is deleted；
The prediction steps are repeated, until obtaining the bimetry of the complete electronic set.
Optionally, before accelerated factor is obtained according to the natural storage time limit and pre-established acceleration model, the side
Method also includes：
The temperature stress data included according to the Performance Degradation Data, with reference to the degraded data trend model, are obtained
The bimetry of multiple test electron complete machines under different temperatures stress；
According to the bimetry of multiple test electron complete machines under different temperatures stress and the nature of each test electron complete machine
Store the time limit and build acceleration model；
Correspondingly, obtaining accelerated factor according to the natural storage time limit and pre-established acceleration model includes：
Parameter in the acceleration model is assessed according to the bimetry of multiple test electron complete machines under different temperatures stress；
The accelerated factor for obtaining the complete electronic set under different temperatures stress is calculated according to the acceleration model.
The present invention proposes a kind of complete electronic set storage life apparatus for evaluating, including：
Acquisition module, Performance Degradation Data and the natural storage time limit for obtaining complete electronic set；
Evaluation module, degraded data trend model is built for the test sample in the Performance Degradation Data, and
According to the checking sample in the degraded data trend model and the Performance Degradation Data, the pre- of the complete electronic set is obtained
Survey the life-span；
Processing module, for obtaining accelerated factor according to the natural storage time limit and pre-established acceleration model；
Optimization module, the complete electronic set is obtained for the bimetry according to the complete electronic set and the accelerated factor
Characteristics life.
Optionally, the Performance Degradation Data includes：It is multigroup including properties of product data and with the properties of product data
Corresponding detection time sample data；
Correspondingly, the evaluation module, for the Performance Degradation Data to be divided into experiment according to the detection time
Sample and checking sample；Initial degraded data trend model is set up using SVMs；With the product in the test sample
Performance data is input vector, and Performance Degradation Data value is output vector, using least square method supporting vector machine algorithm to described
Initial degraded data trend model is trained, and builds degraded data trend model.
Optionally, the evaluation module, is additionally operable to the sequencing according to detection time, perform prediction step；
The prediction steps include：Using the detection time in first group of sample data in the checking sample as input,
With reference to the degraded data trend model, the predicted value of corresponding particular product performance parameters is obtained；Judge the particular product performance parameters
Predicted value whether reach the upper limit or lower limit of product failure threshold values；If so, then by the predicted value of the particular product performance parameters
Corresponding detection time as the complete electronic set bimetry.
Optionally, the evaluation module, if being additionally operable to judge to know that the predicted value of the particular product performance parameters is not up to production
The upper limit or lower limit of product failure threshold values, then become according to the first group of sample data verified in sample to the degraded data
Potential model is updated；First group of sample data in the checking sample is deleted；The prediction steps are repeated, until
Obtain the bimetry of the complete electronic set.
Optionally, described device also includes：Modeling module；
The modeling module, for the temperature stress data included according to the Performance Degradation Data, degenerates with reference to described
Data trend model, obtains the bimetry of multiple test electron complete machines under different temperatures stress；According under different temperatures stress
The bimetry of multiple test electron complete machines and the natural storage time limit of each test electron complete machine build acceleration model；
Correspondingly, handled module, for being commented according to the bimetry of multiple test electron complete machines under different temperatures stress
Estimate the parameter in the acceleration model；Calculated according to the acceleration model and obtain the complete electronic set under different temperatures stress
Accelerated factor.
As shown from the above technical solution, a kind of complete electronic set storage life appraisal procedure proposed by the present invention and device pass through
The Performance Degradation Data of complete electronic set is analyzed, and according to the life-span of analysis result assessment electronics complete machine, is then based on electricity
The storage time limit of sub- complete machine analyzes the accelerated factor of complete electronic set, and then combines the life-span evaluated and accelerated factor assessment electronics
The characteristics life of complete machine, has the advantages that assessment accuracy is high..
Brief description of the drawings
The features and advantages of the present invention can be more clearly understood from by reference to accompanying drawing, accompanying drawing is schematical without that should manage
Solve to carry out any limitation to the present invention, in the accompanying drawings：
Fig. 1 shows a kind of schematic flow sheet for complete electronic set storage life appraisal procedure that the present invention one is provided；
Fig. 2 shows the schematic flow sheet for the prediction steps that the present invention is provided；
Fig. 3 a- Fig. 3 c show the schematic diagram of the product test data under the different magnitude of stress that the present invention is provided；
Fig. 4 a- Fig. 4 c show the product degradation trend prediction curve signal under the different magnitude of stress that the present invention is provided
Figure；
Fig. 5 shows a kind of structural representation for complete electronic set storage life apparatus for evaluating that the present invention is provided.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the accompanying drawing in the present invention, to this
Technical scheme in invention is clearly and completely described, it is clear that described embodiment is the part implementation of the present invention
Example, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creativeness
The every other embodiment obtained on the premise of work, belongs to the scope of protection of the invention.
Fig. 1 shows a kind of flow signal for complete electronic set storage life appraisal procedure that one embodiment of the invention is provided
Figure, referring to Fig. 1, this method can be realized by processor, specifically include following steps：
110th, the Performance Degradation Data and the natural storage time limit of complete electronic set are obtained；
120th, the test sample in the Performance Degradation Data builds degraded data trend model, and is moved back according to described
Change the checking sample in data trend model and the Performance Degradation Data, obtain the bimetry of the complete electronic set；
130th, accelerated factor is obtained according to the natural storage time limit and pre-established acceleration model；
It should be noted that before step 130, in addition to：The temperature stress included according to the Performance Degradation Data
Data, with reference to the degraded data trend model, obtain the bimetry of multiple test electron complete machines under different temperatures stress；Root
According to the bimetry of multiple test electron complete machines under different temperatures stress and the natural storage time limit structure of each test electron complete machine
Build acceleration model；
Correspondingly, step 130 is specifically included：
Parameter in the acceleration model is assessed according to the bimetry of multiple test electron complete machines under different temperatures stress；
The accelerated factor for obtaining the complete electronic set under different temperatures stress is calculated according to the acceleration model.
140th, the feature longevity of the complete electronic set is obtained according to the bimetry of the complete electronic set and the accelerated factor
Life.
It can be seen that, the embodiment of the present invention is analyzed by the Performance Degradation Data to complete electronic set, and according to analysis result
The life-span of assessment electronics complete machine, the storage time limit for being then based on complete electronic set analyzes the accelerated factor of complete electronic set, and then combines
The life-span evaluated and the characteristics life of accelerated factor assessment electronics complete machine, have the advantages that assessment accuracy is high.
Fig. 2 shows the schematic flow sheet for the prediction steps that one embodiment of the invention is provided, and this method can be real by processor
It is existing, specifically include following steps：
210th, training data
The Performance Degradation Data includes：It is multigroup including properties of product data and it is corresponding with the properties of product data inspection
Survey time samples data；
220th, degradation trend model is set up by least square method supporting vector machine
The Performance Degradation Data is divided into by test sample and checking sample according to the detection time；
Initial degraded data trend model is set up using SVMs；
Using the properties of product data in the test sample as input vector, Performance Degradation Data value is output vector, profit
The initial degraded data trend model is trained with least square method supporting vector machine algorithm, degraded data trend mould is built
Type.
230th, according to degradation trend model prediction Performance Degradation Data value
According to the sequencing of detection time, perform prediction step；
The prediction steps include：
Using the detection time in first group of sample data in the checking sample as input, become with reference to the degraded data
Potential model, obtains the predicted value of corresponding particular product performance parameters；
240th, judge whether Performance Degradation Data value reaches failure threshold values, if so, then performing step 250；If it is not, then performing
Step 260；
250th, using the corresponding detection time of the predicted value of the particular product performance parameters as the complete electronic set the prediction longevity
Life.
260th, first group of sample data in the checking sample is updated to the degraded data trend model；
First group of sample data in the checking sample is deleted；
The prediction steps are repeated, until obtaining the bimetry of the complete electronic set.
With reference to the outcome evaluation of certain type complete electronic set accelerated storage test, the present invention is described in further detail：
Put into 9 progress accelerated storage tests of certain type electronic system product, all existing certain natural storage year of 9 products
Limit, experiment is carried out using constant stress applying mode, and proof stress is temperature stress, and stress level is divided into 3 grades, is respectively
80 DEG C, 95 DEG C and 110 DEG C, respectively 3 products are arranged to be tested under each stress level, test click-through according to the rules during experiment
The performance parameter test of row product, has obtained the Performance Degradation Data of 9 products, such as Fig. 3 a- Fig. 3 c, and data have omitted unit.
Step 1: setting up degraded data trend model using SVMs：
The trend model of degraded data is set up first with SVMs, with the corresponding detection time of Performance Degradation Data
T=(t1,t2,…,tn) it is input vector, Performance Degradation Data value Y=(y1,y2,…,yn) it is output vector, utilize a most young waiter in a wineshop or an inn
Multiply algorithm of support vector machine and can train and draw degraded data trend model：
In formula, α and β supporting vector machine model parameters, ψ (*) are kernel function, and kernel function used herein is radial direction base
(RBF) kernel function.
The present invention completes building for above-mentioned trend model by the least square method supporting vector machine tool box in MATLAB softwares
It is vertical, by adjusting regular parameter gam (this example takes gam=220), kernel parameter sig2 (this example takes sig2=13), it is adapted to
Degraded data trend model.
Step 2: utilizing degradation trend model prediction life of product：
By obtained degradation trend model f (t), by the corresponding time t of prediction datan+1As input, product can obtain
The predicted value y of performance parametern+1, that is, obtain one group of prediction data { tn+1,yn+1}.This group of data are added original performance degradation
As new model training data in data, i.e., new model training data are T '=(t1,t2,…,tn,tn+1) and Y '=(y1,
y2,…,yn,yn+1), new degraded data trend model f ' (t) is can obtain, then pass through new degraded data trend model f ' (t)
Obtain next group of prediction data { tn+2,yn+2}.Forecast model and predicted number are so constantly updated according to the method described above
According to the properties of product data { t obtained when predictionn+m,yn+m(m >=1) reached product failure threshold values (failure threshold values be 0.639)
When, tn+mThe as bimetry of product.
The degradation trend prediction curve for obtaining product under each stress levels is shown in Fig. 4 a- Fig. 4 c, the life prediction knot of product
Fruit is as shown in table 1.
The life prediction result of table 1
Step 3: merging natural storage data and accelerated storage test data：
In temperature stress Si(i=1,2 ..., k) under have riIndividual product, prediction obtains these products in stress SiUnder longevity
Life is respectively Pi1,Pi2,…,Piri(being shown in Table 1), the existing natural storage time limit of product is respectively Qi1,Qi2,…,Qiri(9 products
Respectively 8 years, 8 years, 10 years, 10 years, 10 years, 10 years, 8 years, 8 years, 8 years), and set acceleration temperature stress Si(i=1,2 ...,
K) accelerated factor relative to normal temperature stress S0 be Ai, then actual life of the product under temperature stress Si should be：
Lij=Pij+Qij/Ai(i=1,2 ..., k；J=1,2 ..., ri) (2)
Step 4: acceleration model parameter evaluation：
The characteristics life θ of productiWith accelerating temperature stress SiBetween have following acceleration model：
In formula, a and b is parameter to be estimated, SiTo accelerate temperature stress.
Product can obtain in the horizontal S of accelerated stress according to acceleration modeliUnder S horizontal relative to normal stress0Under acceleration because
Son is：
Understand AiFor b function, then the life of product L in formula (2)ijIt is b function.
Generally assume that the life-span of sophisticated electronic machine product obeys exponential distribution, according to the parameter Estimation side of exponential distribution
Method, each stress levels SiThe Maximum-likelihood estimation of lower product average life span is：
Due to LijIt is b function, so θiAlso all it is b function.
According to k group temperature stress levels and average life span { 1/Si,lnθi(i=1,2 ..., k), using formula (3), by most
Small square law can obtain parameter a and b estimate：
Above-mentioned transcendental equations are solved, the present invention realizes asking for above-mentioned equation group by MATLAB software programmings
Solution, is as a result a=-6.17, b=5644.8.
Step 5: accelerated factor is assessed with storage life：
Obtain after parameter a and b, you can calculated according to formula (4) and obtain accelerated factor, obtained certain type complete electronic set and add at each
Relative to the accelerated factor under normal temperature (25 DEG C) under fast temperature stress, as a result as shown in table 2.And produced according to formula (3) calculating
Storage characteristics life of the product under normal temperature (25 DEG C), is as a result 40.2.
The accelerated factor result of table 2
It can be seen that, the present invention has the following technical effect that：
(1) to when being predicted of trend of linearly or nonlinearly degraded data, being modeled using SVMs can
So that the trend of prediction data is consistent with observation data, and SVMs is very convenient to use.
(2) for the product of certain storage time limit, using accelerated factor by naturally using data and accelerated test number
According to combining, can fully, reasonably utilize natural storage data, improve the utilization rate of data resource, make assessment result
Precision it is higher.
For method embodiment, in order to be briefly described, therefore it is all expressed as to a series of combination of actions, but ability
Field technique personnel should know that embodiment of the present invention is not limited by described sequence of movement, because according to the present invention
Embodiment, some steps can be carried out sequentially or simultaneously using other.Secondly, those skilled in the art should also know,
Embodiment described in this description belongs to preferred embodiment, involved action embodiment party not necessarily of the present invention
Necessary to formula.
Fig. 5 shows a kind of structural representation for complete electronic set storage life apparatus for evaluating that one embodiment of the invention is provided
Figure, referring to Fig. 5, the device includes：Acquisition module 510, evaluation module 520, processing module 530 and optimization module 540, its
In：
Acquisition module 510, Performance Degradation Data and the natural storage time limit for obtaining complete electronic set；
Evaluation module 520, degraded data trend model is built for the test sample in the Performance Degradation Data,
And the checking sample in the degraded data trend model and the Performance Degradation Data, obtain the complete electronic set
Bimetry；
Processing module 530, for obtaining accelerated factor according to the natural storage time limit and pre-established acceleration model；
Optimization module 540, the electronics is obtained for the bimetry according to the complete electronic set and the accelerated factor
The characteristics life of complete machine.
Each functional mode in the present embodiment is described in detail below：
Performance Degradation Data includes：It is multigroup including properties of product data and during detection corresponding with the properties of product data
Between sample data；
The evaluation module 520, for the Performance Degradation Data to be divided into test sample according to the detection time
With checking sample；Initial degraded data trend model is set up using SVMs；With the properties of product in the test sample
Data are input vector, and Performance Degradation Data value is output vector, using least square method supporting vector machine algorithm to described initial
Degraded data trend model is trained, and builds degraded data trend model.
The evaluation module 520, is additionally operable to the sequencing according to detection time, perform prediction step；
The prediction steps include：Using the detection time in first group of sample data in the checking sample as input,
With reference to the degraded data trend model, the predicted value of corresponding particular product performance parameters is obtained；Judge the particular product performance parameters
Predicted value whether reach the upper limit or lower limit of product failure threshold values；If so, then by the predicted value of the particular product performance parameters
Corresponding detection time as the complete electronic set bimetry.
The evaluation module 520, if being additionally operable to judge that the predicted value for knowing the particular product performance parameters is not up to product mistake
The upper limit or lower limit of threshold values are imitated, then first group of sample data in the checking sample is to the degraded data trend mould
Type is updated；First group of sample data in the checking sample is deleted；The prediction steps are repeated, until obtaining
The bimetry of the complete electronic set.
In a possible example, device also includes：Modeling module；
The modeling module, for the temperature stress data included according to the Performance Degradation Data, degenerates with reference to described
Data trend model, obtains the bimetry of multiple test electron complete machines under different temperatures stress；According under different temperatures stress
The bimetry of multiple test electron complete machines and the natural storage time limit of each test electron complete machine build acceleration model；
Correspondingly, handled module 530, for the bimetry according to multiple test electron complete machines under different temperatures stress
Assess the parameter in the acceleration model；Calculated according to the acceleration model and obtain the complete electronic set under different temperatures stress
Accelerated factor.
It can be seen that, the embodiment of the present invention is analyzed by the Performance Degradation Data to complete electronic set, and according to analysis result
The life-span of assessment electronics complete machine, the storage time limit for being then based on complete electronic set analyzes the accelerated factor of complete electronic set, and then combines
The life-span evaluated and the characteristics life of acceleration therefore assessment electronics complete machine, have the advantages that assessment accuracy is high.
For device embodiments, because it is substantially similar to method embodiment, so description is fairly simple,
Related part illustrates referring to the part of method embodiment.
It should be noted that in all parts of the device of the present invention, according to the function that it to be realized to therein
Part has carried out logical partitioning, still, and the present invention is not only restricted to this, all parts can be repartitioned as needed or
Person combines.
The present invention all parts embodiment can be realized with hardware, or with one or more processor transport
Capable software module is realized, or is realized with combinations thereof.In the present apparatus, PC is by realizing internet to equipment or device
Remote control, the step of accurately control device or device are each operated.The present invention is also implemented as being used to perform here
The some or all equipment or program of device of described method are (for example, computer program and computer program production
Product).Being achieved in that the program of the present invention can store on a computer-readable medium, and the file or document tool that program is produced
Having can be statistical, produces data report and cpk reports etc., and batch testing can be carried out to power amplifier and is counted.It should be noted that on
Stating embodiment, the present invention will be described rather than limits the invention, and those skilled in the art are not departing from
Replacement embodiment can be designed in the case of the scope of attached claim.In the claims, it will should not be located between bracket
Any reference symbol be configured to limitations on claims.Word "comprising" does not exclude the presence of member not listed in the claims
Part or step.Word "a" or "an" before element does not exclude the presence of multiple such elements.The present invention can be borrowed
Help include the hardware of some different elements and realized by means of properly programmed computer.If listing equipment for drying
Unit claim in, several in these devices can be embodied by same hardware branch.Word first,
Second and third use do not indicate that any order.These words can be construed to title.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. a kind of complete electronic set storage life appraisal procedure, it is characterised in that including：
Obtain the Performance Degradation Data and the natural storage time limit of complete electronic set；
Test sample in the Performance Degradation Data builds degraded data trend model, and is become according to the degraded data
Checking sample in potential model and the Performance Degradation Data, obtains the bimetry of the complete electronic set；
Accelerated factor is obtained according to the natural storage time limit and pre-established acceleration model；
The characteristics life of the complete electronic set is obtained according to the bimetry of the complete electronic set and the accelerated factor.
2. according to the method described in claim 1, it is characterised in that the Performance Degradation Data includes：It is multigroup including product
Can data and detection time sample data corresponding with the properties of product data；
Correspondingly, the test sample in the Performance Degradation Data builds degraded data trend model and included：
The Performance Degradation Data is divided into by test sample and checking sample according to the detection time；
Initial degraded data trend model is set up using SVMs；
Using the properties of product data in the test sample as input vector, Performance Degradation Data value is output vector, using most
A young waiter in a wineshop or an inn multiplies algorithm of support vector machine and the initial degraded data trend model is trained, and builds degraded data trend model.
3. method according to claim 2, it is characterised in that according to the degraded data trend model and the performance
Checking sample in degraded data, obtaining the bimetry of the complete electronic set includes：
According to the sequencing of detection time, perform prediction step；
The prediction steps include：
Using the detection time in first group of sample data in the checking sample as input, with reference to the degraded data trend mould
Type, obtains the predicted value of corresponding particular product performance parameters；
Judge whether the predicted value of the particular product performance parameters reaches the upper limit or lower limit of product failure threshold values；
If so, then using the corresponding detection time of the predicted value of the particular product performance parameters as the complete electronic set the prediction longevity
Life.
4. method according to claim 3, it is characterised in that if the predicted value of the particular product performance parameters is not up to product
The upper limit or lower limit of failure threshold values, then first group of sample data in the checking sample is to the degraded data trend
Model is updated；
First group of sample data in the checking sample is deleted；
The prediction steps are repeated, until obtaining the bimetry of the complete electronic set.
5. method according to claim 2, it is characterised in that according to the natural storage time limit and pre-established acceleration mould
Type is obtained before accelerated factor, and methods described also includes：
The temperature stress data included according to the Performance Degradation Data, with reference to the degraded data trend model, obtain different
The bimetry of multiple test electron complete machines under temperature stress；
According to the bimetry of multiple test electron complete machines under different temperatures stress and the natural storage of each test electron complete machine
The time limit builds acceleration model；
Correspondingly, it is described to be included according to the natural storage time limit and pre-established acceleration model acquisition accelerated factor：
Parameter in the acceleration model is assessed according to the bimetry of multiple test electron complete machines under different temperatures stress；
The accelerated factor for obtaining the complete electronic set under different temperatures stress is calculated according to the acceleration model.
6. a kind of complete electronic set storage life apparatus for evaluating, it is characterised in that including：
Acquisition module, Performance Degradation Data and the natural storage time limit for obtaining complete electronic set；
Evaluation module, for the test sample structure degraded data trend model in the Performance Degradation Data, and according to
Checking sample in the degraded data trend model and the Performance Degradation Data, obtains the prediction longevity of the complete electronic set
Life；
Processing module, for obtaining accelerated factor according to the natural storage time limit and pre-established acceleration model；
Optimization module, the spy of the complete electronic set is obtained for the bimetry according to the complete electronic set and the accelerated factor
Levy the life-span.
7. device according to claim 6, it is characterised in that the Performance Degradation Data includes：It is multigroup including product
Can data and detection time sample data corresponding with the properties of product data；
Correspondingly, the evaluation module, for the Performance Degradation Data to be divided into test sample according to the detection time
With checking sample；Initial degraded data trend model is set up using SVMs；With the properties of product in the test sample
Data are input vector, and Performance Degradation Data value is output vector, using least square method supporting vector machine algorithm to described initial
Degraded data trend model is trained, and builds degraded data trend model.
8. device according to claim 7, it is characterised in that the evaluation module, is additionally operable to the elder generation according to detection time
Afterwards sequentially, perform prediction step；
The prediction steps include：Using the detection time in first group of sample data in the checking sample as input, with reference to
The degraded data trend model, obtains the predicted value of corresponding particular product performance parameters；Judge the pre- of the particular product performance parameters
Whether measured value reaches the upper limit or lower limit of product failure threshold values；If so, then by the predicted value correspondence of the particular product performance parameters
Detection time as the complete electronic set bimetry.
9. device according to claim 8, it is characterised in that the evaluation module, if being additionally operable to judge to know the production
The predicted value of product performance parameter is not up to the upper limit or lower limit of product failure threshold values, then first in the checking sample
Group sample data is updated to the degraded data trend model；First group of sample data in the checking sample is deleted
Remove；The prediction steps are repeated, until obtaining the bimetry of the complete electronic set.
10. device according to claim 6, it is characterised in that described device also includes：Modeling module；
The modeling module, for the temperature stress data included according to the Performance Degradation Data, with reference to the degraded data
Trend model, obtains the bimetry of multiple test electron complete machines under different temperatures stress；According to multiple under different temperatures stress
The bimetry of test electron complete machine and the natural storage time limit of each test electron complete machine build acceleration model；
Correspondingly, the processing module, is assessed for the bimetry according to multiple test electron complete machines under different temperatures stress
Parameter in the acceleration model；Calculated according to the acceleration model and obtain the complete electronic set adding under different temperatures stress
The fast factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710206016.1A CN107015875B (en) | 2017-03-31 | 2017-03-31 | Method and device for evaluating storage life of electronic complete machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710206016.1A CN107015875B (en) | 2017-03-31 | 2017-03-31 | Method and device for evaluating storage life of electronic complete machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107015875A true CN107015875A (en) | 2017-08-04 |
| CN107015875B CN107015875B (en) | 2020-09-04 |
Family
ID=59444960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710206016.1A Active CN107015875B (en) | 2017-03-31 | 2017-03-31 | Method and device for evaluating storage life of electronic complete machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107015875B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446523A (en) * | 2018-05-11 | 2018-08-24 | 北京航天自动控制研究所 | A kind of assessment of complete electronic set storage life and prediction technique |
| CN108846239A (en) * | 2018-07-03 | 2018-11-20 | 北京强度环境研究所 | A kind of elastic epoxy resin accelerated storage test and appraisal procedure based on temperature and humidity |
| CN110263487A (en) * | 2019-07-02 | 2019-09-20 | 中国航空综合技术研究所 | A kind of engineering goods accelerate fatigue life test method |
| CN110889084A (en) * | 2018-09-10 | 2020-03-17 | 湖南银杏可靠性技术研究所有限公司 | Regression confidence interval method for consistency test of degraded data in accelerated storage and natural storage |
| CN111625990A (en) * | 2020-04-16 | 2020-09-04 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Method and device for continuously evaluating storage life of electronic complete machine |
| CN111898236A (en) * | 2020-05-25 | 2020-11-06 | 中国航天标准化研究所 | Acceleration factor analysis method for accelerated storage test of electronic complete machine based on failure big data |
| CN113378368A (en) * | 2021-06-03 | 2021-09-10 | 中国人民解放军32181部队 | Acceleration factor evaluation method based on nonlinear degradation trajectory model |
| CN114062820A (en) * | 2021-11-18 | 2022-02-18 | 西安太乙电子有限公司 | Method for identifying weak components and parts in electronic whole machine storage test and evaluating influence |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100242001A1 (en) * | 2009-03-23 | 2010-09-23 | Vijay Kumar Reddy | Parameter Drift Prediction |
| TW201118400A (en) * | 2009-11-25 | 2011-06-01 | Inventec Corp | Method for predicting fan life-span |
| CN103176136A (en) * | 2011-12-23 | 2013-06-26 | 三星Sdi株式会社 | Device for estimating a lifetime of a secondary battery and method thereof |
-
2017
- 2017-03-31 CN CN201710206016.1A patent/CN107015875B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100242001A1 (en) * | 2009-03-23 | 2010-09-23 | Vijay Kumar Reddy | Parameter Drift Prediction |
| TW201118400A (en) * | 2009-11-25 | 2011-06-01 | Inventec Corp | Method for predicting fan life-span |
| CN103176136A (en) * | 2011-12-23 | 2013-06-26 | 三星Sdi株式会社 | Device for estimating a lifetime of a secondary battery and method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 刘子如等: ""预估火炸药寿命的数学模型及其计算", 《火炸药学报》 * |
| 齐浩淳: "海洋环境下晶体管长贮可靠性研究", 《中国博士学位论文全文数据库信息科技编辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446523B (en) * | 2018-05-11 | 2022-04-08 | 北京航天自动控制研究所 | Method for evaluating and predicting storage life of electronic complete machine |
| CN108446523A (en) * | 2018-05-11 | 2018-08-24 | 北京航天自动控制研究所 | A kind of assessment of complete electronic set storage life and prediction technique |
| CN108846239A (en) * | 2018-07-03 | 2018-11-20 | 北京强度环境研究所 | A kind of elastic epoxy resin accelerated storage test and appraisal procedure based on temperature and humidity |
| CN108846239B (en) * | 2018-07-03 | 2022-11-22 | 北京强度环境研究所 | Temperature and humidity-based accelerated storage test and evaluation method for elastic epoxy resin |
| CN110889084A (en) * | 2018-09-10 | 2020-03-17 | 湖南银杏可靠性技术研究所有限公司 | Regression confidence interval method for consistency test of degraded data in accelerated storage and natural storage |
| CN110889084B (en) * | 2018-09-10 | 2020-11-17 | 湖南银杏可靠性技术研究所有限公司 | Regression confidence interval method for consistency test of degraded data in accelerated storage and natural storage |
| CN110263487A (en) * | 2019-07-02 | 2019-09-20 | 中国航空综合技术研究所 | A kind of engineering goods accelerate fatigue life test method |
| CN111625990A (en) * | 2020-04-16 | 2020-09-04 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Method and device for continuously evaluating storage life of electronic complete machine |
| CN111625990B (en) * | 2020-04-16 | 2023-08-04 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Method and device for continuously evaluating storage life of electronic complete machine |
| CN111898236A (en) * | 2020-05-25 | 2020-11-06 | 中国航天标准化研究所 | Acceleration factor analysis method for accelerated storage test of electronic complete machine based on failure big data |
| CN111898236B (en) * | 2020-05-25 | 2024-01-09 | 中国航天标准化研究所 | Acceleration factor analysis method for accelerated storage test based on failure big data |
| CN113378368A (en) * | 2021-06-03 | 2021-09-10 | 中国人民解放军32181部队 | Acceleration factor evaluation method based on nonlinear degradation trajectory model |
| CN114062820A (en) * | 2021-11-18 | 2022-02-18 | 西安太乙电子有限公司 | Method for identifying weak components and parts in electronic whole machine storage test and evaluating influence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107015875B (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107015875A (en) | A kind of complete electronic set storage life appraisal procedure and device | |
| CN104750932B (en) | A kind of Analysis of structural reliability method based on agent model under Hybrid parameter matrix | |
| JP6472621B2 (en) | Classifier construction method, image classification method, and image classification apparatus | |
| CN108200030A (en) | Detection method, system, device and the computer readable storage medium of malicious traffic stream | |
| CN107545095A (en) | Forecasting Methodology and system for the structure repair during aircraft overhaul | |
| CN106021928A (en) | Comprehensive stress acceleration test method | |
| CN109060817B (en) | Artificial intelligence reinspection system and method thereof | |
| CN108334943A (en) | The semi-supervised soft-measuring modeling method of industrial process based on Active Learning neural network model | |
| CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
| CN112129741A (en) | Insulating oil aging analysis method and device, computer equipment and storage medium | |
| CN108628164A (en) | A kind of semi-supervised flexible measurement method of industrial process based on Recognition with Recurrent Neural Network model | |
| CN106203103A (en) | The method for detecting virus of file and device | |
| CN108830492B (en) | Method for determining spot-check merchants based on big data | |
| CN111160667B (en) | Method and device for improving robustness of food safety prediction model | |
| CN112084505A (en) | Deep learning model malicious sample detection method, system, device and storage medium | |
| CN110850358A (en) | Electric energy meter comprehensive verification method and system based on stepwise regression algorithm | |
| CN110276385A (en) | Mechanical part remaining life prediction technique based on similitude | |
| JP3234742B2 (en) | Method and apparatus for estimating remaining life of electronic component | |
| CN113033845B (en) | Construction method and device for power transmission resource co-construction and sharing | |
| US11493901B2 (en) | Detection of defect in edge device manufacturing by artificial intelligence | |
| US20210157707A1 (en) | Transferability determination apparatus, transferability determination method, and recording medium | |
| RU99107094A (en) | METHOD FOR SELECTION OF ELECTRONIC EQUIPMENT PRODUCTS BY RESISTANCE OR RELIABILITY | |
| CN111898314A (en) | Lake water body parameter detection method and device, electronic equipment and storage medium | |
| CN107290603B (en) | Product reliability evaluation method and device | |
| CN114998070B (en) | Immersive digital learning method and system for enterprise digital learning platform |
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 |