CN107015875B - Method and device for evaluating storage life of electronic complete machine - Google Patents
Method and device for evaluating storage life of electronic complete machine Download PDFInfo
- Publication number
- CN107015875B CN107015875B CN201710206016.1A CN201710206016A CN107015875B CN 107015875 B CN107015875 B CN 107015875B CN 201710206016 A CN201710206016 A CN 201710206016A CN 107015875 B CN107015875 B CN 107015875B
- Authority
- CN
- China
- Prior art keywords
- data
- degradation data
- complete machine
- electronic complete
- electronic
- 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.)
- Active
Links
Images
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
Abstract
The invention discloses a storage life evaluation method and device for an electronic complete machine. The method comprises the following steps: acquiring performance degradation data and natural storage life of the electronic complete machine; constructing a degradation data trend model according to the test samples in the performance degradation data, and acquiring the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data; acquiring an acceleration factor according to the natural storage age and a pre-established acceleration model; and acquiring the characteristic life of the electronic complete machine according to the predicted life of the electronic complete machine and the acceleration factor. The invention analyzes the performance degradation data of the electronic complete machine, evaluates the service life of the electronic complete machine according to the analysis result, then analyzes the acceleration factor of the electronic complete machine based on the storage life of the electronic complete machine, and further evaluates the characteristic service life of the electronic complete machine by combining the evaluated service life and the acceleration factor, and has the advantage of high evaluation accuracy.
Description
Technical Field
The invention relates to the technical field of electronic complete machines, in particular to a method and a device for evaluating the storage life of an electronic complete machine.
Background
In an accelerated storage test of an electronic complete machine, due to the reasons of complex functions of electronic complete machine products and the like, the product performance degradation rule is complex, and the situation that natural storage data and accelerated storage test data coexist exists. The situation causes difficulty in test result evaluation, and the traditional accelerated test data evaluation method cannot process data aiming at the situation, so that the accelerated factor or the storage life of the obtained product cannot be evaluated, and the test purpose cannot be achieved.
The method aims at the situation that the product performance degradation rule of the whole electronic machine is complex, and the coexistence of the natural storage data and the accelerated storage test data is a common and urgent engineering problem. By adopting the effective accelerated test evaluation method, the effective utilization of data resources can be improved, the accuracy of an evaluation result is further improved, even the research result can be influenced, and the hidden danger caused by the conditions of inaccurate life evaluation result and the like is reduced.
When the trend prediction is performed on the product performance degradation rule, a common processing method is a regression analysis method, the regression analysis method performs regression fitting on the performance degradation data of the product by using a linear function, an exponential function, a power function and the like to obtain a regression equation of the degradation trend, and then predicts the degradation trend, but for some nonlinear degradation data with complex rules, the accuracy of the regression analysis method is not high, and even the regression analysis method is difficult to apply sometimes. An artificial neural network method is also researched at present, but in engineering application, the prediction of the product degradation trend by the artificial neural network method is not ideal, and the application of the artificial neural network method is yet to be further researched.
In the process of implementing the invention, the inventor finds that for the condition that the natural storage data and the accelerated storage test data coexist, the current processing method is to firstly adopt the accelerated test data to evaluate the test result to obtain the storage life result of the product, then simply add the natural storage time to the life result, even sometimes neglect the natural storage data when evaluating the acceleration factor, and the processing methods all cause the evaluation result to generate deviation.
Disclosure of Invention
The invention aims to solve the problem that in the prior art, an evaluation result has errors when the storage life of an electronic complete machine product is evaluated.
The invention provides an evaluation method for storage life of an electronic complete machine, which comprises the following steps:
acquiring performance degradation data and natural storage life of the electronic complete machine;
constructing a degradation data trend model according to the test samples in the performance degradation data, and acquiring the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data;
acquiring an acceleration factor according to the natural storage age and a pre-established acceleration model;
and acquiring the characteristic life of the electronic complete machine according to the predicted life of the electronic complete machine and the acceleration factor.
Optionally, the performance degradation data includes: a plurality of groups of detection time sample data which comprise product performance data and correspond to the product performance data;
accordingly, the constructing a degradation data trend model according to the test samples in the performance degradation data comprises:
dividing the performance degradation data into a test sample and a verification sample according to the detection time;
establishing an initial degradation data trend model by using a support vector machine;
and training the initial degradation data trend model by using the product performance data in the test sample as an input vector and the performance degradation data value as an output vector and utilizing a least square support vector machine algorithm to construct a degradation data trend model.
Optionally, the obtaining the predicted life of the electronic complete machine according to the degradation data trend model and the verification sample in the performance degradation data includes:
executing a prediction step according to the sequence of the detection time;
the predicting step includes:
taking the detection time in the first group of sample data in the verification sample as input, and combining the degraded data trend model to obtain a predicted value of a corresponding product performance parameter;
judging whether the predicted value of the product performance parameter reaches the upper limit or the lower limit of a product failure threshold value;
and if so, taking the detection time corresponding to the predicted value of the product performance parameter as the predicted service life of the whole electronic machine.
Optionally, if the predicted value of the product performance parameter does not reach the upper limit or the lower limit of the product failure threshold, updating the degraded data trend model according to a first group of sample data in the verification samples;
deleting a first set of sample data in the validation sample;
and repeatedly executing the prediction step until the predicted service life of the whole electronic machine is obtained.
Optionally, before obtaining the acceleration factor according to the natural storage life and the pre-established acceleration model, the method further includes:
according to temperature stress data included in the performance degradation data, combined with the degradation data trend model, obtaining the predicted service lives of a plurality of test electronic complete machines under different temperature stresses;
establishing an acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses and the natural storage life of each test electronic complete machine;
accordingly, obtaining an acceleration factor based on the natural storage age and a pre-established acceleration model comprises:
evaluating parameters in the acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses;
and calculating and obtaining acceleration factors of the electronic complete machine under different temperature stresses according to the acceleration model.
The invention provides an evaluation device for storage life of an electronic complete machine, which comprises:
the acquisition module is used for acquiring performance degradation data and natural storage life of the electronic complete machine;
the evaluation module is used for constructing a degradation data trend model according to the test samples in the performance degradation data and acquiring the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data;
the processing module is used for obtaining an acceleration factor according to the natural storage age and a pre-established acceleration model;
and the optimization module is used for acquiring the characteristic service life of the electronic complete machine according to the predicted service life of the electronic complete machine and the acceleration factor.
Optionally, the performance degradation data includes: a plurality of groups of detection time sample data which comprise product performance data and correspond to the product performance data;
correspondingly, the evaluation module is used for dividing the performance degradation data into a test sample and a verification sample according to the detection time; establishing an initial degradation data trend model by using a support vector machine; and training the initial degradation data trend model by using the product performance data in the test sample as an input vector and the performance degradation data value as an output vector and utilizing a least square support vector machine algorithm to construct a degradation data trend model.
Optionally, the evaluation module is further configured to execute the prediction step according to the sequence of the detection times;
the predicting step includes: taking the detection time in the first group of sample data in the verification sample as input, and combining the degraded data trend model to obtain a predicted value of a corresponding product performance parameter; judging whether the predicted value of the product performance parameter reaches the upper limit or the lower limit of a product failure threshold value; and if so, taking the detection time corresponding to the predicted value of the product performance parameter as the predicted service life of the whole electronic machine.
Optionally, the evaluation module is further configured to update the degraded data trend model according to a first group of sample data in the verification sample if it is determined that the predicted value of the product performance parameter does not reach an upper limit or a lower limit of a product failure threshold; deleting a first set of sample data in the validation sample; and repeatedly executing the prediction step until the predicted service life of the whole electronic machine is obtained.
Optionally, the apparatus further comprises: a modeling module;
the modeling module is used for acquiring the predicted service lives of a plurality of test electronic complete machines under different temperature stresses according to temperature stress data included in the performance degradation data and by combining the degradation data trend model; establishing an acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses and the natural storage life of each test electronic complete machine;
correspondingly, the processing module is used for evaluating parameters in the acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses; and calculating and obtaining acceleration factors of the electronic complete machine under different temperature stresses according to the acceleration model.
According to the technical scheme, the method and the device for evaluating the storage life of the electronic complete machine, which are provided by the invention, analyze the performance degradation data of the electronic complete machine, evaluate the life of the electronic complete machine according to the analysis result, analyze the acceleration factor of the electronic complete machine based on the storage life of the electronic complete machine, further evaluate the characteristic life of the electronic complete machine by combining the evaluated life and the acceleration factor, and have the advantage of high evaluation accuracy. .
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:
FIG. 1 is a schematic flow chart illustrating a method for evaluating the storage life of an electronic complete machine according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating the prediction steps provided by the present invention;
3 a-3 c show schematic diagrams of product test data at different stress levels provided by the present invention;
4 a-4 c are graphs showing the product degradation trend prediction curves provided by the present invention at different stress levels;
fig. 5 shows a schematic structural diagram of an evaluation apparatus for storage life of an electronic complete machine provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Fig. 1 is a schematic flow chart illustrating a method for evaluating storage life of an electronic complete machine according to an embodiment of the present invention, and referring to fig. 1, the method may be implemented by a processor, and specifically includes the following steps:
110. acquiring performance degradation data and natural storage life of the electronic complete machine;
120. constructing a degradation data trend model according to the test samples in the performance degradation data, and acquiring the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data;
130. acquiring an acceleration factor according to the natural storage age and a pre-established acceleration model;
it should be noted that, before step 130, the method further includes: according to temperature stress data included in the performance degradation data, combined with the degradation data trend model, obtaining the predicted service lives of a plurality of test electronic complete machines under different temperature stresses; establishing an acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses and the natural storage life of each test electronic complete machine;
correspondingly, step 130 specifically includes:
evaluating parameters in the acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses; and calculating and obtaining acceleration factors of the electronic complete machine under different temperature stresses according to the acceleration model.
140. And acquiring the characteristic life of the electronic complete machine according to the predicted life of the electronic complete machine and the acceleration factor.
Therefore, the embodiment of the invention analyzes the performance degradation data of the electronic complete machine, evaluates the service life of the electronic complete machine according to the analysis result, analyzes the acceleration factor of the electronic complete machine based on the storage life of the electronic complete machine, and further evaluates the characteristic service life of the electronic complete machine by combining the evaluated service life and the acceleration factor, and has the advantage of high evaluation accuracy.
Fig. 2 is a flowchart illustrating a prediction step according to an embodiment of the present invention, where the method may be implemented by a processor, and specifically includes the following steps:
210. training data
The performance degradation data includes: a plurality of groups of detection time sample data which comprise product performance data and correspond to the product performance data;
220. method for establishing degradation trend model through least square support vector machine
Dividing the performance degradation data into a test sample and a verification sample according to the detection time;
establishing an initial degradation data trend model by using a support vector machine;
and training the initial degradation data trend model by using the product performance data in the test sample as an input vector and the performance degradation data value as an output vector and utilizing a least square support vector machine algorithm to construct a degradation data trend model.
230. Predicting performance degradation data values from a degradation trend model
Executing a prediction step according to the sequence of the detection time;
the predicting step includes:
taking the detection time in the first group of sample data in the verification sample as input, and combining the degraded data trend model to obtain a predicted value of a corresponding product performance parameter;
240. judging whether the performance degradation data value reaches a failure threshold value, if so, executing a step 250; if not, go to step 260;
250. and taking the detection time corresponding to the predicted value of the product performance parameter as the predicted service life of the whole electronic machine.
260. Updating the degraded data trend model according to a first set of sample data in the verification sample; deleting a first set of sample data in the validation sample;
and repeatedly executing the prediction step until the predicted service life of the whole electronic machine is obtained.
The invention is further described in detail below with reference to the evaluation of the results of the accelerated storage test of a certain type of electronic machine:
9 electronic complete machine products of a certain type are put into the test for accelerated storage, the 9 products have a certain natural storage life, the test is carried out by adopting a constant stress applying mode, the test stress is temperature stress, the stress level is divided into 3 grades, namely 80 ℃, 95 ℃ and 110 ℃, 3 products are arranged under each stress level for test, the performance parameter test of the products is carried out according to specified test points during the test, and the performance degradation data of the 9 products is obtained, for example, the data are omitted in the unit of figures 3 a-3 c.
Step one, establishing a degraded data trend model by using a support vector machine:
firstly, a trend model of degradation data is established by using a support vector machine, and the detection time T corresponding to the performance degradation data is (T ═ T)1,t2,…,tn) For the input vector, the performance degradation data value Y ═ Y1,y2,…,yn) For the output vector, a least square support vector machine algorithm is used for trainable obtaining of a degradation data trend model:
where α and β support vector machine model parameters, ψ (—) is a kernel function, which as used herein is a Radial Basis (RBF) kernel function.
The invention completes the establishment of the trend model through a least square support vector machine tool box in MATLAB software, and obtains a suitable degradation data trend model by adjusting a regular parameter gam (in the example, gam is 220) and a kernel parameter sig2 (in the example, sig2 is 13).
Step two, predicting the service life of the product by using the degradation trend model:
according to the obtained degradation trend model f (t), predicting the time t corresponding to the datan+1As input, the predicted value y of the product performance parameter can be obtainedn+1Obtaining a group of prediction data tn+1,yn+1}. Adding the group of data into the original performance degradation data as new model training data, namely, the new model training data is T' ═ (T)1,t2,…,tn,tn+1) And Y ═ Y1,y2,…,yn,yn+1) Obtaining a new degradation data trend model f '(t), and obtaining the next set of prediction data { t } through the new degradation data trend model f' (t)n+2,yn+2}. Thus, the prediction model is continuously updated and the product performance data is predicted according to the method, and when the product performance data t is predictedn+m,yn+mWhen the value (m is more than or equal to 1) reaches the product failure threshold value (the failure threshold value is 0.639), tn+mI.e. the predicted life of the product.
The obtained degradation trend prediction curves of the products under various stress levels are shown in fig. 4 a-4 c, and the service life prediction results of the products are shown in table 1.
TABLE 1 Life prediction results
Step three, combining the natural storage data and the accelerated storage test data:
stress at temperature Si(i-1, 2, …, k) has a total of riPredicted to obtain stress S of the productsiLower life is Pi1,Pi2,…,Piri(see Table 1), the existing natural storage life of the product is Qi1,Qi2,…,Qiri(9 products are 8 years, 10 years, 8 years and 8 years) respectively) and setting accelerated temperature stress Si(i ═ 1,2, …, k) the acceleration factor with respect to the normal temperature stress S0 is Ai, then the 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 four, accelerating the evaluation of model parameters:
characteristic life theta of the productiAnd accelerated temperature stress SiThe following acceleration models are in between:
in the formula, a and b are parameters to be estimated, SiTo accelerate the temperature stress.
Obtaining the acceleration stress level S of the product according to the acceleration modeliLower relative to normal stress level S0The following acceleration factors are:
it is known that AiAs a function of b, the product life L in equation (2)ijAre all functions of b.
Generally, the service life of a complex electronic complete machine product is assumed to obey exponential distribution, and each stress level S is estimated according to a parameter estimation method of the exponential distributioniThe maximum likelihood estimate of the average life of the product is:
due to LijAre all a function of b, soiAs well as a function of b.
Stress level and average lifetime according to k groups of temperature {1/S }i,lnθi(i ═ 1,2, …, k), using equation (3), estimates of parameters a and b are obtained by the least squares method:
solving the transcendental system of equations, the invention realizes the solving of the transcendental system of equations by programming MATLAB software, and the result is that a is-6.17 and b is 5644.8.
And step five, evaluating the acceleration factor and the storage life:
after the parameters a and b are obtained, the acceleration factor can be calculated according to the formula (4), and the acceleration factor of a certain type of electronic complete machine at each acceleration temperature stress relative to the normal temperature (25 ℃) is obtained, and the results are shown in table 2. And the shelf life characteristic of the product at normal temperature (25 ℃) was calculated from the formula (3) and found to be 40.2 years.
TABLE 2 Accelerator results
As can be seen, the invention has the following technical effects:
(1) when the trend of linear or non-linear degradation data is predicted, the trend of the predicted data can be consistent with the observed data by utilizing the support vector machine for modeling, and the support vector machine is very convenient to use.
(2) For products with a certain storage life, natural use data and accelerated test data are combined by using an acceleration factor, so that the natural storage data can be fully and reasonably utilized, the utilization rate of data resources is improved, and the precision of an evaluation result is higher.
Method embodiments are described as a series of acts or combinations for simplicity of explanation, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts or acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the embodiments of the invention. Furthermore, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Fig. 5 is a schematic structural diagram illustrating an apparatus for evaluating the storage life of an electronic complete machine according to an embodiment of the present invention, and referring to fig. 5, the apparatus includes: an acquisition module 510, an evaluation module 520, a processing module 530, and an optimization module 540, wherein:
an obtaining module 510, configured to obtain performance degradation data and a natural storage life of the electronic complete machine;
the evaluation module 520 is configured to construct a degradation data trend model according to the test samples in the performance degradation data, and obtain the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data;
a processing module 530, configured to obtain an acceleration factor according to the natural storage life and a pre-established acceleration model;
and the optimizing module 540 is configured to obtain the characteristic life of the electronic complete machine according to the predicted life of the electronic complete machine and the acceleration factor.
The functional models in the present embodiment are explained in detail below:
the performance degradation data includes: a plurality of groups of detection time sample data which comprise product performance data and correspond to the product performance data;
the evaluation module 520 is configured to divide the performance degradation data into a test sample and a verification sample according to the detection time; establishing an initial degradation data trend model by using a support vector machine; and training the initial degradation data trend model by using the product performance data in the test sample as an input vector and the performance degradation data value as an output vector and utilizing a least square support vector machine algorithm to construct a degradation data trend model.
The evaluation module 520 is further configured to perform a prediction step according to the sequence of the detection time;
the predicting step includes: taking the detection time in the first group of sample data in the verification sample as input, and combining the degraded data trend model to obtain a predicted value of a corresponding product performance parameter; judging whether the predicted value of the product performance parameter reaches the upper limit or the lower limit of a product failure threshold value; and if so, taking the detection time corresponding to the predicted value of the product performance parameter as the predicted service life of the whole electronic machine.
The evaluation module 520 is further configured to update the degraded data trend model according to a first set of sample data in the verification sample if it is determined that the predicted value of the product performance parameter does not reach the upper limit or the lower limit of the product failure threshold; deleting a first set of sample data in the validation sample; and repeatedly executing the prediction step until the predicted service life of the whole electronic machine is obtained.
In a possible example, the apparatus further comprises: a modeling module;
the modeling module is used for acquiring the predicted service lives of a plurality of test electronic complete machines under different temperature stresses according to temperature stress data included in the performance degradation data and by combining the degradation data trend model; establishing an acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses and the natural storage life of each test electronic complete machine;
accordingly, the processing module 530 is configured to evaluate parameters in the acceleration model according to predicted lifetimes of a plurality of test electronic machines under different temperature stresses; and calculating and obtaining acceleration factors of the electronic complete machine under different temperature stresses according to the acceleration model.
Therefore, the embodiment of the invention analyzes the performance degradation data of the electronic complete machine, evaluates the service life of the electronic complete machine according to the analysis result, analyzes the acceleration factor of the electronic complete machine based on the storage life of the electronic complete machine, and further evaluates the characteristic service life of the electronic complete machine by combining the evaluated service life and acceleration, and has the advantage of high evaluation accuracy.
As for the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should be noted that, in the respective components of the apparatus of the present invention, the components therein are logically divided according to the functions to be implemented thereof, but the present invention is not limited thereto, and the respective components may be newly divided or combined as necessary.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. In the device, the PC remotely controls the equipment or the device through the Internet, and accurately controls each operation step of the equipment or the device. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. The program for realizing the invention can be stored on a computer readable medium, and the file or document generated by the program has statistics, generates a data report and a cpk report, and the like, and can carry out batch test and statistics on the power amplifier. It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for evaluating the storage life of an electronic complete machine is characterized by comprising the following steps:
acquiring performance degradation data and natural storage life of the electronic complete machine;
constructing a degradation data trend model according to the test samples in the performance degradation data, and acquiring the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data;
acquiring an acceleration factor according to the natural storage age and a pre-established acceleration model;
acquiring the characteristic life of the electronic complete machine according to the predicted life of the electronic complete machine and the acceleration factor;
wherein, prior to obtaining an acceleration factor based on the natural storage age and a pre-established acceleration model, the method further comprises:
according to temperature stress data included in the performance degradation data, combined with the degradation data trend model, obtaining the predicted service lives of a plurality of test electronic complete machines under different temperature stresses;
establishing an acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses and the natural storage life of each test electronic complete machine;
accordingly, the obtaining an acceleration factor according to the natural storage age and a pre-established acceleration model comprises:
evaluating parameters in the acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses;
and calculating and obtaining acceleration factors of the electronic complete machine under different temperature stresses according to the acceleration model.
2. The method of claim 1, wherein the performance degradation data comprises: a plurality of groups of detection time sample data which comprise product performance data and correspond to the product performance data;
accordingly, the constructing a degradation data trend model according to the test samples in the performance degradation data comprises:
dividing the performance degradation data into a test sample and a verification sample according to the detection time;
establishing an initial degradation data trend model by using a support vector machine;
and training the initial degradation data trend model by using the product performance data in the test sample as an input vector and the performance degradation data value as an output vector and utilizing a least square support vector machine algorithm to construct a degradation data trend model.
3. The method of claim 2, wherein obtaining the predicted lifetime of the overall electronic machine based on the degradation data trend model and the validation samples in the performance degradation data comprises:
executing a prediction step according to the sequence of the detection time;
the predicting step includes:
taking the detection time in the first group of sample data in the verification sample as input, and combining the degraded data trend model to obtain a predicted value of a corresponding product performance parameter;
judging whether the predicted value of the product performance parameter reaches the upper limit or the lower limit of a product failure threshold value;
and if so, taking the detection time corresponding to the predicted value of the product performance parameter as the predicted service life of the whole electronic machine.
4. The method according to claim 3, wherein if the predicted value of the product performance parameter does not reach an upper limit or a lower limit of a product failure threshold, updating the degraded data trend model according to a first set of sample data in the verification samples;
deleting a first set of sample data in the validation sample;
and repeatedly executing the prediction step until the predicted service life of the whole electronic machine is obtained.
5. An evaluation device for storage life of an electronic complete machine is characterized by comprising:
the acquisition module is used for acquiring performance degradation data and natural storage life of the electronic complete machine;
the evaluation module is used for constructing a degradation data trend model according to the test samples in the performance degradation data and acquiring the predicted service life of the electronic complete machine according to the degradation data trend model and the verification samples in the performance degradation data;
the processing module is used for obtaining an acceleration factor according to the natural storage age and a pre-established acceleration model;
the optimization module is used for obtaining the characteristic service life of the electronic complete machine according to the predicted service life of the electronic complete machine and the acceleration factor;
wherein the apparatus further comprises: a modeling module;
the modeling module is used for acquiring the predicted service lives of a plurality of test electronic complete machines under different temperature stresses according to temperature stress data included in the performance degradation data and by combining the degradation data trend model; establishing an acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses and the natural storage life of each test electronic complete machine;
correspondingly, the processing module is used for evaluating parameters in the acceleration model according to the predicted service lives of a plurality of test electronic complete machines under different temperature stresses; and calculating and obtaining acceleration factors of the electronic complete machine under different temperature stresses according to the acceleration model.
6. The apparatus of claim 5, wherein the performance degradation data comprises: a plurality of groups of detection time sample data which comprise product performance data and correspond to the product performance data;
correspondingly, the evaluation module is used for dividing the performance degradation data into a test sample and a verification sample according to the detection time; establishing an initial degradation data trend model by using a support vector machine; and training the initial degradation data trend model by using the product performance data in the test sample as an input vector and the performance degradation data value as an output vector and utilizing a least square support vector machine algorithm to construct a degradation data trend model.
7. The apparatus of claim 6, wherein the evaluation module is further configured to perform the predicting step according to the sequence of the detection times;
the predicting step includes: taking the detection time in the first group of sample data in the verification sample as input, and combining the degraded data trend model to obtain a predicted value of a corresponding product performance parameter; judging whether the predicted value of the product performance parameter reaches the upper limit or the lower limit of a product failure threshold value; and if so, taking the detection time corresponding to the predicted value of the product performance parameter as the predicted service life of the whole electronic machine.
8. The apparatus according to claim 7, wherein the evaluation module is further configured to update the degraded data trend model according to a first set of sample data in the verification sample if it is determined that the predicted value of the product performance parameter does not reach an upper limit or a lower limit of a product failure threshold; deleting a first set of sample data in the validation sample; and repeatedly executing the prediction step until the predicted service life of the whole electronic machine is obtained.
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 CN107015875A (en) | 2017-08-04 |
| CN107015875B true 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) |
Families Citing this family (8)
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN113378368B (en) * | 2021-06-03 | 2022-07-22 | 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 (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8239814B2 (en) * | 2009-03-23 | 2012-08-07 | Texas Instruments Incorporated | Parameter drift prediction |
-
2017
- 2017-03-31 CN CN201710206016.1A patent/CN107015875B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| "预估火炸药寿命的数学模型及其计算;刘子如等;《火炸药学报》;20160430;第1-5页 * |
| 海洋环境下晶体管长贮可靠性研究;齐浩淳;《中国博士学位论文全文数据库信息科技编辑》;20150315(第03期);第5章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107015875A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107015875B (en) | Method and device for evaluating storage life of electronic complete machine | |
| CN106294120B (en) | Method, apparatus and computer program product for testing code | |
| US20190251474A1 (en) | Smart default threshold values in continuous learning | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| CN113177732A (en) | Process flow management method, device, medium and terminal equipment | |
| CN108133279B (en) | Wind power probability prediction method, storage medium and device | |
| CN114757587B (en) | Product quality control system and method based on big data | |
| CN114066262A (en) | Method, system and device for estimating cause-tracing reasoning of abnormal indexes after power grid dispatching and storage medium | |
| CN113536081A (en) | Data center data management method and system based on artificial intelligence | |
| US10635078B2 (en) | Simulation system, simulation method, and simulation program | |
| WO2020175084A1 (en) | Operation evaluation device, operation evaluation method, and program | |
| CN111025041A (en) | Electric vehicle charging pile monitoring method and system, computer equipment and medium | |
| US11373285B2 (en) | Image generation device, image generation method, and image generation program | |
| CN109743200B (en) | Resource feature-based cloud computing platform computing task cost prediction method and system | |
| CN116166967A (en) | Data processing method, equipment and storage medium based on meta learning and residual error network | |
| CN114780967B (en) | Mining evaluation method based on big data vulnerability mining and AI vulnerability mining system | |
| CN116383048A (en) | Software quality information processing method and device | |
| US11757741B2 (en) | Demand prediction apparatus, demand prediction method and program for predicting a demand of a path on a network using selected trend patterns | |
| CN113987261A (en) | Video recommendation method and system based on dynamic trust perception | |
| CN107290603B (en) | Product reliability evaluation method and device | |
| CN113139332A (en) | Automatic model construction method, device and equipment | |
| CN111126694A (en) | Time series data prediction method, system, medium and device | |
| CN114254764B (en) | Feedback-based machine learning model searching method, system, equipment and medium | |
| CN112434839B (en) | Distribution transformer heavy overload risk prediction method and electronic equipment | |
| CN115543855B (en) | Semiconductor device parameter testing method, device, electronic device and storage medium |
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 |