Complete machine level product life analysis method and system based on component level life information

Abstract

The invention relates to a whole-machine-level product service life analysis method and device based on component-level service life information, and the method comprises the steps: carrying out a stress accelerated storage test on component-level products included in the whole-machine-level products, and obtaining performance parameter degradation track information of the component-level products; in the stress accelerated storage test, the performance of the component-level product at a specified moment is determined according to a given performance initial value, a performance change speed constant and aging time; according to the storage life distribution of the component-level products in the complete-machine-level products, the storage life distribution of the complete-machine-level products is constructed, so that the relative entropy of the storage life distribution of the complete-machine-level products and the storage life distribution of the component-level products is minimum; and taking the storage life distribution of the complete machine-level product with the minimum relative entropy with the storage life distribution of the component-level product as a complete machine storage life analysis result. The relative entropy method is adopted to determine the whole machine storage life distribution parameters, the whole machine level product life can be effectively predicted and analyzed, and a bottom layer technical support is provided for whole machine level product life analysis.

Description

Technical Field

[0001] The present invention belongs to the technical field of life test and evaluation, and in particular relates to a whole-machine-level product life analysis method based on component-level life information. Background Art

[0002] At present, in the storage life test and evaluation of equipment, due to the high cost of whole-machine-level products, a large number of accelerated storage tests of components and parts are carried out in the actual test process to obtain acceleration factors or storage life information, and the information is converted to the whole-machine level. 1 to 3 whole-machine products are selected to carry out storage period verification tests based on the acceleration factors obtained in the early stage to achieve storage life evaluation.

[0003] Therefore, the key issue in the storage life assessment of whole-machine-level products is the conversion of component life information to whole-machine-level life information. At present, the failure rate of components can be obtained from standard manuals, but the failure rate of components lacks data support and is difficult to apply in engineering. Therefore, there is currently a lack of a scientific, reasonable and feasible whole-machine-level product life analysis technical solution based on component-level life information. Summary of the invention

[0004] In view of this, the purpose of the present invention is to propose a whole-machine-level product life analysis method and system based on component-level life information, so as to solve the problem that traditional technology is difficult to scientifically, reasonably and accurately analyze and predict the life of whole-machine-level products.

[0005] Based on the above purpose, the present invention provides a whole-machine-level product life analysis method based on component-level life information, comprising:

[0006] Conducting stress accelerated storage test on component-level products included in the whole machine-level products to obtain performance parameter degradation trajectory information of the component-level products; in the stress accelerated storage test, the performance of the component-level products at a specified time is determined according to a given performance initial value, performance change rate constant and aging time;

[0007] According to the storage life distribution of the component-level products in the whole-machine-level products, the storage life distribution of the whole-machine-level products is constructed so that the relative entropy between the storage life distribution of the whole-machine-level products and the storage life distribution of the component-level products is minimized, and the storage life distribution of the whole-machine-level product with the minimum relative entropy with the storage life distribution of the component-level products is taken as the storage life analysis result of the whole machine.

[0008] As a preferred solution of the whole machine level product life analysis method based on component level life information, the model formula obeyed by the performance parameter degradation trajectory information of the component level product includes:

[0009] P=P0+Klogt

[0010] P=P0+Kt

[0011] P=P0e -Kt

[0012] Where P is the performance of the component-level product at a specified time, P0 is the given initial value of the performance, K is the temperature-related performance change rate constant, and t is the aging time.

[0013] As a preferred solution for the whole machine product life analysis method based on component-level life information, the degradation threshold of the component-level product performance parameter is preset to M. When the performance parameter P of the component-level product at a specified time is equal to M, it means that the component-level product has reached its life. The pseudo-failure life of the component-level product is obtained by extrapolation using the fitted equation. The expression formula of the pseudo-failure life information is:

[0014] T1,T2,...,T n

[0015] Where, T n is the pseudo failure life of component-level product n.

[0016] As a preferred solution of the whole machine level product life analysis method based on component level life information, the storage life of the component level product obeys the Weibull distribution, and the storage reliability R(t) of the component level product is expressed as:

[0017]

[0018] The failure density function f(t) of the component-level product is expressed as:

[0019]

[0020] The failure rate λ(t) of the component-level product is expressed as:

[0021] λ(t)=mη -m t m-1

[0022] Where m and η are positive numbers, representing shape parameter and characteristic life, respectively.

[0023] As a preferred solution for the whole machine level product life analysis method based on component level life information, the formula for the component failure rate function of the i-th component level product is:

[0024]

[0025] The storage reliability function of the i-th component-level product components is:

[0026]

[0027] In the formula, m i is the shape parameter of the storage life distribution of the i-th component-level product components; η i is the scale parameter of the storage life distribution of the i-th component-level product components.

[0028] As a preferred solution of the whole machine level product life analysis method based on component level life information, when the storage life of the component level product obeys the Weibull distribution, the accelerated stress level S j The expression formula of the acceleration factor is:

[0029]

[0030] Where η0 is the characteristic life of the component-level product under the reference storage stress level S0;

[0031] η j For component-level products at accelerated storage stress level S j The characteristic life of the following.

[0032] As a preferred solution for the whole machine level product life analysis method based on component level life information, the acceleration factors of different component level products are calculated using the Arrhenius formula:

[0033]

[0034] Where AF ij is the acceleration factor of different component-level products; K is the Boltzmann constant; E a is the activation energy, T0 is the reference temperature, T s To accelerate the temperature.

[0035] As a preferred solution for the whole machine level product life analysis method based on component level life information, the expression formula for the whole machine storage life analysis result is:

[0036]

[0037] Where D KLmin is the relative entropy value of each component and the whole machine; Ω is the life range of each component; h(x) is the storage life distribution of the whole machine level product; F i (x) is the storage life distribution of each component product.

[0038] The present invention also provides a whole-machine-level product life analysis device based on component-level life information, comprising:

[0039] A stress accelerated storage test module is used to carry out a stress accelerated storage test on a component-level product included in a whole-machine-level product to obtain performance parameter degradation trajectory information of the component-level product; in the stress accelerated storage test, the performance of the component-level product at a specified time is determined according to a given performance initial value, performance change rate constant and aging time;

[0040] The whole machine storage life analysis module is used to construct the storage life distribution of the whole machine-level product according to the storage life distribution of the component-level products in the whole machine-level product, so that the relative entropy between the storage life distribution of the whole machine-level product and the storage life distribution of the component-level product is minimized, and the storage life distribution of the whole machine-level product with the minimum relative entropy with the storage life distribution of the component-level product is used as the whole machine storage life analysis result.

[0041] As a preferred solution of the whole machine level product life analysis device based on component level life information, in the stress accelerated storage test module, the model formula obeyed by the performance parameter degradation trajectory information of the component level product includes:

[0042] P=P0+Klogt

[0043] P=P0+Kt

[0044] P=P0e -Kt

[0045] Where P is the performance of the component-level product at a specified time, P0 is the given initial value of the performance, K is the temperature-related performance change rate constant, and t is the aging time.

[0046] As a preferred solution of the whole machine product life analysis device based on component-level life information, in the stress accelerated storage test module, the degradation threshold of the component-level product performance parameter is preset as M. When the performance parameter P of the component-level product at a specified time is equal to M, it means that the component-level product has reached its life. The pseudo-failure life of the component-level product is obtained by extrapolation using the fitted equation. The expression formula of the pseudo-failure life information is:

[0047] T1,T2,...,T n

[0048] Where, T n is the pseudo failure life of component-level product n.

[0049] As a preferred solution of the whole machine level product life analysis device based on component level life information, in the stress accelerated storage test module, the storage life of the component level product obeys the Weibull distribution, and the storage reliability R(t) of the component level product is expressed as follows:

[0050]

[0051] The failure density function f(t) of the component-level product is expressed as:

[0052]

[0053] The failure rate λ(t) of the component-level product is expressed as:

[0054] λ(t)=mη -m t m-1

[0055] Where m and η are positive numbers, representing shape parameter and characteristic life, respectively.

[0056] As a preferred solution of the whole machine level product life analysis device based on component level life information, in the stress accelerated storage test module, the failure rate function formula of the i-th component level product component is:

[0057]

[0058] The storage reliability function of the i-th component-level product components is:

[0059]

[0060] In the formula, m i is the shape parameter of the storage life distribution of the i-th component-level product components; η i is the scale parameter of the storage life distribution of the i-th component-level product components.

[0061] As a preferred solution of the whole machine level product life analysis device based on component level life information, in the stress accelerated storage test module, when the storage life of the component level product obeys the Weibull distribution, the accelerated stress level S j The expression formula of the acceleration factor is:

[0062]

[0063] Where η0 is the characteristic life of the component-level product under the reference storage stress level S0;

[0064] η j For component-level products at accelerated storage stress level S j The characteristic life of the following.

[0065] As a preferred solution of the whole machine level product life analysis device based on component level life information, in the stress accelerated storage test module, the acceleration factors of different component level products are calculated using the Arrhenius formula:

[0066]

[0067] Where AF ij is the acceleration factor of different component-level products; K is the Boltzmann constant; E a is the activation energy, T0 is the reference temperature, T s To accelerate the temperature.

[0068] As a preferred solution of the whole machine level product life analysis device based on component level life information, in the whole machine storage life analysis module, the expression formula of the whole machine storage life analysis result is:

[0069]

[0070] Where D KLmin is the relative entropy value of each component and the whole machine; Ω is the life range of each component; h(x) is the storage life distribution of the whole machine level product; F i (x) is the storage life distribution of each component product.

[0071] From the above, it can be seen that the technical solution provided by the present invention carries out stress accelerated storage test on the component-level products included in the whole machine-level products to obtain the degradation trajectory information of the performance parameters of the component-level products; in the stress accelerated storage test, the performance of the component-level products at a specified time is determined according to the given initial performance value, performance change rate constant and aging time; according to the storage life distribution of the component-level products in the whole machine-level products, the storage life distribution of the whole machine-level products is constructed, so that the relative entropy between the storage life distribution of the whole machine-level products and the storage life distribution of the component-level products is minimized, and the storage life distribution of the whole machine-level products with the minimum relative entropy with the storage life distribution of the component-level products is used as the whole machine storage life analysis result. The present invention adopts the relative entropy method to determine the storage life distribution parameters of the whole machine, and the method is more scientific and reasonable, and can effectively predict and analyze the life of the whole machine-level products, and provide underlying technical support for the life analysis of the whole machine-level products. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0073] Figure 1 A schematic diagram of a whole-machine-level product life analysis method based on component-level life information provided by an embodiment of the present invention;

[0074] Figure 2 A diagram showing the calculation results of the relative entropy of a whole machine at normal temperature in a whole machine-level product life analysis method based on component-level life information provided in an embodiment of the present invention;

[0075] Figure 3 A diagram showing the calculation results of the relative entropy of the whole machine at 90°C in the whole machine-level product life analysis method based on component-level life information provided in an embodiment of the present invention;

[0076] Figure 4 A diagram showing the calculation results of the relative entropy of the whole machine at 95°C in the whole machine-level product life analysis method based on component-level life information provided in an embodiment of the present invention;

[0077] Figure 5 A diagram showing the calculation results of the whole machine relative entropy at 100°C in the whole machine level product life analysis method based on component level life information provided in an embodiment of the present invention;

[0078] Figure 6 A diagram showing the calculation results of the whole machine relative entropy at 105°C in the whole machine level product life analysis method based on component level life information provided in an embodiment of the present invention;

[0079] Figure 7 An architecture diagram of a whole-machine-level product life analysis device based on component-level life information provided by an embodiment of the present invention;

[0080] Figure 8 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0082] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The words "include" or "comprise" and the like used in the embodiments of the present invention mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, but do not exclude other elements or objects.

[0083] In traditional technology, the storage life parameters are usually processed using statistical methods such as minimum, maximum, average, and weighted failure rate. However, the minimum, maximum, and average are simple mathematical processing, and the processing methods are simple and crude. For example, if three products with a reliability of 0.9 are connected in series, the reliability of the whole machine is only 0.729. In terms of the processing of acceleration factors, the minimum, maximum, or average value can be selected as the acceleration factor of the whole machine, but the method is relatively simple and crude and lacks underlying theoretical support. In view of this, it is necessary to provide a scientific, reasonable, and feasible whole-machine product life analysis technical solution based on component-level life information.

[0084] See also Figure 1 The embodiment of the present invention provides a whole-machine-level product life analysis method based on component-level life information, comprising the following steps:

[0085] S1. Conduct stress accelerated storage test on component-level products included in the whole machine-level products to obtain performance parameter degradation trajectory information of the component-level products; in the stress accelerated storage test, the performance of the component-level products at a specified time is determined according to a given performance initial value, performance change rate constant and aging time;

[0086] S2. Based on the storage life distribution of the component-level products in the whole-machine-level products, construct the storage life distribution of the whole-machine-level products so that the relative entropy between the storage life distribution of the whole-machine-level products and the storage life distribution of the component-level products is minimized; and the storage life distribution of the whole-machine-level products having the minimum relative entropy with the storage life distribution of the component-level products is used as the storage life analysis result of the whole machine.

[0087] In this embodiment, the life information of component-level products can be obtained through storage testing or component conversion. In the component-level storage life distribution determination scheme based on storage testing, the model formula obeyed by the performance parameter degradation trajectory information of the component-level product includes:

[0088] P=P0+Klogt (1)

[0089] P=P0+Kt (2)

[0090] P=P0e -Kt (3)

[0091] Where P is the performance of the component-level product at a specified time, P0 is the given initial value of the performance, K is the temperature-related performance change rate constant, and t is the aging time.

[0092] The degradation threshold of the component-level product performance parameter is preset to M. When the performance parameter P of the component-level product at a specified time is equal to M, it indicates that the component-level product has reached its lifespan. The pseudo-failure lifespan of the component-level product is obtained by extrapolation using the fitted equation. The pseudo-failure lifespan information is expressed as:

[0093] T1,T2,...,T n (4)

[0094] Where, T n is the pseudo failure life of component-level product n.

[0095] It is assumed that the storage life of the component-level product follows the Weibull distribution, and the storage reliability R(t) of the component-level product is expressed as follows:

[0096]

[0097] The failure density function f(t) of the component-level product is expressed as:

[0098]

[0099] The failure rate λ(t) of the component-level product is expressed as:

[0100] λ(t)=mη -m t m-1 (7)

[0101] In this example, it is assumed that n samples are put into the test and the test is stopped when r samples fail. The order statistics of the observed failure time is t (1) ≤t (2) ≤...≤t (r) , its likelihood function can be written as:

[0102]

[0103] Taking the logarithm and derivation of formula (8), we can get the following after simplification:

[0104]

[0105] Where m and η are positive numbers, representing shape parameters and characteristic life, respectively. When η = 1, the storage life distribution function transforms into exponential distribution, when η = 2, the storage life distribution function transforms into Rayleigh distribution, and when η = 3-4, its shape is very close to the normal distribution. The relationship between Weibull distribution and other distributions is relatively close, and the range of its shape parameter values ​​reflects the failure characteristics of the product. Therefore, it has a strong adaptability to various types of test data and is widely used.

[0106] In this embodiment, in the component-level storage life distribution determination scheme based on components, it is generally believed in the standard manual that the storage life of components obeys the exponential distribution. However, in actual experiments, components may also obey the Weibull distribution. Considering that the exponential distribution is a special form of the Weibull distribution, this embodiment uniformly considers the case where the components obey the Weibull distribution. Typical component information is shown in Table 1.

[0107] Table 1 Typical component storage life information

[0108]

[0109] If the storage life of components and products follows the Weibull distribution,

[0110] As a preferred solution for the whole-machine product life analysis method based on component-level life information, let the shape parameter and scale parameter of the storage life distribution of the i-th (i=1,2,…,n) component be m respectively. i , η i , the component failure rate function formula of the i-th component-level product is:

[0111]

[0112] The storage reliability function of the i-th component-level product components is:

[0113]

[0114] In the formula, m i is the shape parameter of the storage life distribution of the i-th component-level product components; η i is the scale parameter of the storage life distribution of the i-th component-level product components.

[0115] If the m value of each component is different, it can be processed by weighted average:

[0116]

[0117] Among them, the characteristic storage life expression of component-level products is:

[0118]

[0119] This means that if the underlying component shape parameter m i , the scale parameter η i Different, the storage life of the component-level product follows the shape parameter and scale parameter The Weibull distribution of .

[0120] In this embodiment, when the storage life of the component-level product follows the Weibull distribution, the accelerated stress level S j Acceleration factor AF under (j=1,2,…,k) j The expression formula is:

[0121]

[0122] It is known that the i-th (i=1,2,…,n) component is under accelerated stress level S j The acceleration factor under AF is j , component-level products are subjected to accelerated stress level S j The characteristic storage life η under j See the formula:

[0123]

[0124] Therefore, it can be concluded that the Weibull distribution component under the accelerated stress level S j The acceleration factor formula is:

[0125]

[0126] Where η0 is the characteristic life of the component-level product under the reference storage stress level S0;

[0127] η j For component-level products at accelerated storage stress level S j The characteristic life of the following.

[0128] The acceleration factors of the different component-level products are calculated using the Arrhenius formula:

[0129]

[0130] Where AF ij is the acceleration factor of different component-level products; K is the Boltzmann constant, which is equal to 8.617*10-5eV / ℃; Ea is the activation energy, T0 is the reference temperature, T s To accelerate the temperature.

[0131] In this embodiment, it is assumed that the whole machine-level product includes three component-level products, and the information of each component-level product is shown in Table 2:

[0132] Table 2 Typical component storage life information

[0133]

[0134] Relative entropy, also known as KL divergence, is used to indicate the amount of information loss when the fitted distribution Q(x) matches the true distribution P(x). The smaller the KL divergence value, the better the match between the model and the actual data. The definition of KL divergence has two expressions: discrete and continuous. The expression is as follows:

[0135]

[0136] Among them, in the discrete case, P(x) and Q(x) are two probability distribution functions of the random variable X. In the continuous case, p(x) and q(x) are the probability density functions of distributions P and Q respectively. N represents the number of values ​​of the random variable X in the discrete case, Ω represents the range of values ​​of the one-dimensional random variable X in the continuous case, and X represents the life data, which should be in the range of (0, +∞). When the distributions P and Q are the same, the KL divergence is 0.

[0137] Let p(x) be the storage life distribution F1, F2, F3 of each component, and construct a storage life distribution h(x) so that its relative entropy with the storage life distribution of each component is the smallest. Then it is the life distribution result after data fusion, that is, the storage life distribution result of the whole machine. The expression formula of the whole machine storage life analysis result is:

[0138]

[0139] Where D KLmin is the relative entropy value of each component and the whole machine; Ω is the life range of each component; h(x) is the storage life distribution of the whole machine level product; F i (x) is the storage life distribution of each component product.

[0140] The application example of the embodiment of the present invention is as follows:

[0141] An electronic whole-machine-level product contains two component-level products, one of which can obtain the corresponding life distribution through similar product information or storage life test data, and the other component-level product needs to be calculated through component data. The storage life information of these two component-level products is combined to realize the storage life evaluation of the whole-machine-level product.

[0142] The storage life information of component-level product 1 is shown in Table 3:

[0143] Table 3 Storage life information of component 1

[0144]

[0145] The storage life information of component-level product 2 is shown in Table 4:

[0146] Table 4 Storage life information of components 2

[0147]

[0148] The storage life distribution of the whole machine at different temperature stress levels was calculated using the relative entropy method. The results are shown in Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 As shown in Table 5:

[0149] Table 5 Storage life parameter results of complete product

[0150]

[0151] In summary, this embodiment conducts stress accelerated storage test on the component-level products included in the whole machine-level products to obtain the performance parameter degradation trajectory information of the component-level products; in the stress accelerated storage test, the performance of the component-level products at a specified time is determined according to the given performance initial value, performance change rate constant and aging time; according to the storage life distribution of the component-level products in the whole machine-level products, the storage life distribution of the whole machine-level products is constructed, so that the relative entropy between the storage life distribution of the whole machine-level products and the storage life distribution of the component-level products is minimized, and the storage life distribution of the whole machine-level products with the minimum relative entropy with the storage life distribution of the component-level products is used as the whole machine storage life analysis result. The present invention adopts the relative entropy method to determine the storage life distribution parameters of the whole machine, and the method is more scientific and reasonable, and can effectively predict and analyze the life of the whole machine-level products, and provide underlying technical support for the life analysis of the whole machine-level products.

[0152] It should be noted that the method of the embodiment of the present invention can be performed by a single device, such as a computer or a server. The method of this embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the described method.

[0153] It should be noted that some embodiments of the present invention are described above. In some cases, the actions or steps recorded can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0154] See also Figure 7 Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present invention further provides a whole-machine-level product life analysis device based on component-level life information, comprising:

[0155] The stress accelerated storage test module 100 is used to carry out a stress accelerated storage test on a component-level product included in a whole-machine-level product to obtain performance parameter degradation trajectory information of the component-level product; in the stress accelerated storage test, the performance of the component-level product at a specified time is determined according to a given performance initial value, performance change rate constant and aging time;

[0156] The whole machine storage life analysis module 200 is used to construct the storage life distribution of the whole machine-level product according to the storage life distribution of the component-level products in the whole machine-level product, so that the relative entropy between the storage life distribution of the whole machine-level product and the storage life distribution of the component-level product is minimized, and the storage life distribution of the whole machine-level product with the minimum relative entropy with the storage life distribution of the component-level product is used as the whole machine storage life analysis result.

[0157] In this embodiment, in the stress accelerated storage test module 100, the model formula obeyed by the performance parameter degradation trajectory information of the component-level product includes:

[0158] P=P0+Klogt

[0159] P=P0+Kt

[0160] P=P0e -Kt

[0161] Where P is the performance of the component-level product at a specified time, P0 is the given initial value of the performance, K is the temperature-related performance change rate constant, and t is the aging time.

[0162] In this embodiment, in the stress accelerated storage test module 100, the degradation threshold of the component-level product performance parameter is preset as M. When the performance parameter P of the component-level product at a specified time is equal to M, it indicates that the component-level product has reached its lifespan. The pseudo-failure lifespan of the component-level product is obtained by extrapolation using the fitted equation. The pseudo-failure lifespan information is expressed as follows:

[0163] T1,T2,...,T n

[0164] Where, T n is the pseudo failure life of component-level product n.

[0165] In this embodiment, in the stress accelerated storage test module 100, the storage life of the component-level product obeys the Weibull distribution, and the storage reliability R(t) of the component-level product is expressed as follows:

[0166]

[0167] The failure density function f(t) of the component-level product is expressed as:

[0168]

[0169] The failure rate λ(t) of the component-level product is expressed as:

[0170] λ(t)=mη -m t m-1

[0171] Where m and η are positive numbers, representing shape parameter and characteristic life, respectively.

[0172] In this embodiment, in the stress accelerated storage test module 100, the failure rate function formula of the i-th component-level product component is:

[0173]

[0174] The storage reliability function of the i-th component-level product components is:

[0175]

[0176] In the formula, m i is the shape parameter of the storage life distribution of the i-th component-level product components; η i is the scale parameter of the storage life distribution of the i-th component-level product components.

[0177] In this embodiment, in the stress accelerated storage test module 100, when the storage life of the component-level product obeys the Weibull distribution, the accelerated stress level S j The expression formula of the acceleration factor is:

[0178]

[0179] Where η0 is the characteristic life of the component-level product under the reference storage stress level S0;

[0180] η j For component-level products at accelerated storage stress level S j The characteristic life of the following.

[0181] In this embodiment, in the stress accelerated storage test module 100, the acceleration factors of different component-level products are calculated using the Arrhenius formula:

[0182]

[0183] Where AF ij is the acceleration factor of different component-level products; K is the Boltzmann constant; E a is the activation energy, T0 is the reference temperature, T s To accelerate the temperature.

[0184] In this embodiment, in the whole machine storage life analysis module 200, the expression formula for the whole machine storage life analysis result is:

[0185]

[0186] Where D KLminis the relative entropy value of each component and the whole machine; Ω is the life range of each component; h(x) is the storage life distribution of the whole machine level product; F i (x) is the storage life distribution of each component product.

[0187] The system of the above embodiment is used to implement the whole-machine-level product life analysis method based on component-level life information in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0188] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the landslide hazard identification based on deep learning as described in any of the above embodiments is implemented.

[0189] Figure 8 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 310, a memory 320, an input / output interface 330, a communication interface 340, and a bus 350. The processor 310, the memory 320, the input / output interface 330, and the communication interface 340 are connected to each other in communication within the device through the bus 350.

[0190] The processor 310 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0191] The memory 320 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 320 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 320 and are called and executed by the processor 310.

[0192] The input / output interface 330 is used to connect the input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0193] The communication interface 340 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0194] The bus 350 comprises a pathway that transmits information between the various components of the device (eg, the processor 310 , the memory 320 , the input / output interface 330 , and the communication interface 340 ).

[0195] It should be noted that, although the above device only shows the processor 310, the memory 320, the input / output interface 330, the communication interface 340 and the bus 350, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0196] The electronic device of the above embodiment is used to implement the whole-machine-level product life analysis method based on component-level life information in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0197] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present invention also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the whole-machine-level product life analysis method based on component-level life information as described in any of the above embodiments.

[0198] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0199] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the whole-machine-level product life analysis method based on component-level life information as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0200] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0201] In addition, to simplify the description and discussion, and in order not to obscure the embodiments of the present invention, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the devices may be shown in the form of block diagrams to avoid obscuring the embodiments of the present invention, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present invention will be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that embodiments of the present invention may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0202] Although the present invention has been described in conjunction with specific embodiments of the present invention, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0203] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the scope of the protection claimed. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims

1. A whole-machine-level product life analysis method based on component-level life information, characterized in that: include: Conduct stress accelerated storage tests on component-level products included in the whole-machine-level products to obtain performance parameter degradation trajectory information of the component-level products; In the stress accelerated storage test, the performance of the component-level product at a specified time is determined according to a given initial performance value, a performance change rate constant and an aging time; According to the storage life distribution of the component-level products in the whole-machine-level products, the storage life distribution of the whole-machine-level products is constructed so that the relative entropy between the storage life distribution of the whole-machine-level products and the storage life distribution of the component-level products is minimized, and the storage life distribution of the whole-machine-level product with the minimum relative entropy with the storage life distribution of the component-level products is taken as the storage life analysis result of the whole machine.

2. The whole machine level product life analysis method based on component level life information according to claim 1 is characterized in that: The model formulas obeyed by the performance parameter degradation trajectory information of the component-level product include: P=P0+Klogt P=P0+Kt P=P0e -Kt Where P is the performance of the component-level product at a specified time, P0 is the given initial value of the performance, K is the temperature-related performance change rate constant, and t is the aging time.

3. The whole machine level product life analysis method based on component level life information according to claim 2 is characterized in that: The degradation threshold of the performance parameter of the component-level product is preset to M. When the performance parameter P of the component-level product at a specified time is equal to M, it indicates that the component-level product has reached its lifespan. The pseudo-failure lifespan of the component-level product is obtained by extrapolation using the fitted equation. The expression formula of the pseudo-failure lifespan information is: T1,T2,...,T n Where, T n is the pseudo failure life of component-level product n.

4. The whole machine level product life analysis method based on component level life information according to claim 3 is characterized in that: The storage life of the component-level product follows the Weibull distribution, and the storage reliability R(t) of the component-level product is expressed as follows: The failure density function f(t) of the component-level product is expressed as: The failure rate λ(t) of the component-level product is expressed as: λ(t)=mη -m t m-1 Where m and η are positive numbers, representing shape parameter and characteristic life, respectively.

5. The whole machine level product life analysis method based on component level life information according to claim 4 is characterized in that: The formula for the component failure rate function of the i-th component-level product is: The storage reliability function of the i-th component-level product components is: In the formula, m i is the shape parameter of the storage life distribution of the i-th component-level product components; η i is the scale parameter of the storage life distribution of the i-th component-level product components.

6. The whole machine level product life analysis method based on component level life information according to claim 5 is characterized in that: When the storage life of the component-level product follows the Weibull distribution, the accelerated stress level S j The expression formula of the acceleration factor is: Where η0 is the characteristic life of the component-level product under the reference storage stress level S0; η j For component-level products at accelerated storage stress level S j The characteristic life of the following.

7. The whole machine level product life analysis method based on component level life information according to claim 6 is characterized in that: The acceleration factors of different component-level products are calculated using the Arrhenius formula: Where AF ij is the acceleration factor of different component-level products; K is the Boltzmann constant; E a is the activation energy, T0 is the reference temperature, T s To accelerate the temperature.

8. The whole machine level product life analysis method based on component level life information according to claim 7 is characterized in that: The expression formula of the whole machine storage life analysis result is: Where D KLmin is the relative entropy value of each component and the whole machine; Ω is the life range of each component; h(x) is the storage life distribution of the whole machine level product; F i (x) is the storage life distribution of each component product.

9. A whole-machine-level product life analysis device based on component-level life information, characterized in that: include: A stress accelerated storage test module is used to carry out a stress accelerated storage test on component-level products included in the whole machine-level products to obtain performance parameter degradation trajectory information of the component-level products; In the stress accelerated storage test, the performance of the component-level product at a specified time is determined according to a given initial performance value, a performance change rate constant and an aging time; The whole machine storage life analysis module is used to construct the storage life distribution of the whole machine-level product according to the storage life distribution of the component-level products in the whole machine-level product, so that the relative entropy between the storage life distribution of the whole machine-level product and the storage life distribution of the component-level product is minimized, and the storage life distribution of the whole machine-level product with the minimum relative entropy with the storage life distribution of the component-level product is used as the whole machine storage life analysis result.

10. The whole machine level product life analysis device based on component level life information according to claim 9, characterized in that: In the stress accelerated storage test module, the model formula obeyed by the performance parameter degradation trajectory information of the component-level product includes: P=P0+Klogt P=P0+Kt P=P0e -Kt Where P is the performance of the component-level product at a specified time, P0 is the given initial value of the performance, K is the temperature-related performance change rate constant, and t is the aging time; In the stress accelerated storage test module, the degradation threshold of the component-level product performance parameter is preset to M. When the performance parameter P of the component-level product at a specified time is equal to M, it indicates that the component-level product has reached its life. The pseudo-failure life of the component-level product is obtained by extrapolation using the fitted equation. The expression formula of the pseudo-failure life information is: T1,T2,...,T n Where, T n is the pseudo failure life of component-level product n; In the stress accelerated storage test module, the storage life of the component-level product obeys the Weibull distribution, and the storage reliability R(t) of the component-level product is expressed as follows: The failure density function f(t) of the component-level product is expressed as: The failure rate λ(t) of the component-level product is expressed as: λ(t)=mη -m t m-1 In the formula, m and η are positive numbers, representing shape parameter and characteristic life respectively; In the stress accelerated storage test module, the failure rate function formula of the i-th component-level product component is: The storage reliability function of the i-th component-level product components is: In the formula, m i is the shape parameter of the storage life distribution of the i-th component-level product components; η i is the scale parameter of the storage life distribution of the i-th component-level product components; In the stress accelerated storage test module, when the storage life of the component-level product follows the Weibull distribution, the accelerated stress level S j The expression formula of the acceleration factor is: Where η0 is the characteristic life of the component-level product under the reference storage stress level S0; η j For component-level products at accelerated storage stress level S j Characteristic life under In the stress accelerated storage test module, the acceleration factors of different component-level products are calculated using the Arrhenius formula: Where AF ij is the acceleration factor of different component-level products; K is the Boltzmann constant; E a is the activation energy, T0 is the reference temperature, T s is the accelerating temperature; In the whole machine storage life analysis module, the expression formula of the whole machine storage life analysis result is: Where D KLmin is the relative entropy value of each component and the whole machine; Ω is the life range of each component; h(x) is the storage life distribution of the whole machine level product; F i (x) is the storage life distribution of each component product.

Images