Method for sampling testability test samples under multiple working conditions

Abstract

The invention relates to a testability test sample sampling method under multiple working conditions, and the method comprises the steps: selecting a unit sample from each component unit of to-be-tested equipment according to the fault occurrence frequency of each component unit; selecting a fault mode sample from each fault mode corresponding to the composition unit according to the fault occurrence frequency of each type of fault mode; according to the fault occurrence frequency of each operation condition, selecting a condition sample from each operation condition corresponding to the fault mode; combining into a sampling sample; and under the condition that the sample sufficiency meets a preset condition, taking the sample as a target sample. A traditional fault sampling method is improved, working condition information is added on the basis of a traditional method, a key formula is corrected, the sampling process is improved, the problem that working condition influences are not considered in a traditional testability sampling method is solved, sampling under the multi-working-condition condition of a testability test is achieved, and the accuracy and reliability of the test are improved.

Description

Technical Field

[0001] The present application relates to the field of testability tests, and in particular to a testability test sample sampling method under multiple working conditions. Background Art

[0002] At present, the sampling methods for test samples mainly rely on standardized procedures and criteria, which usually include fault sampling methods that take risks into consideration, fault sampling methods that combine coverage adequacy with risk methods, and fault sampling methods based on coverage adequacy.

[0003] However, under different working conditions, the system's failure mode set and the failure rate of each failure mode may change, which may have a significant impact on the system's testability level. The existing test sample sampling method fails to fully consider the impact of actual working conditions on testability tests in practical applications, and has certain limitations. The test results obtained are also difficult to accurately reflect the system's true testability level.

[0004] Therefore, it is urgent to develop a test sample sampling method under multiple working conditions to solve one or more of the above-mentioned problems. Summary of the invention

[0005] In view of this, in order to solve the above-mentioned technical problems or part of the technical problems, an embodiment of the present invention provides a test test sample sampling method under multiple working conditions.

[0006] In a first aspect, the present application provides a method for sampling test samples under multiple working conditions, the method comprising:

[0007] Obtain the failure frequency of each component unit of the device to be tested;

[0008] Select unit samples from each component unit of the device to be tested according to the failure frequency of each component unit;

[0009] Obtain the failure frequency of each failure mode of the component unit;

[0010] According to the failure frequency of each type of failure mode, select failure mode samples from each failure mode corresponding to the component unit;

[0011] Obtain the fault occurrence frequency of each operating condition corresponding to the fault mode;

[0012] According to the frequency of failure in each operating condition, select operating condition samples from each operating condition corresponding to the failure mode;

[0013] combining the unit samples, the failure mode samples, and the operating condition samples into a sampling sample;

[0014] When the adequacy of the sampling sample meets the preset conditions, the sampling sample is used as the target sample.

[0015] In a possible implementation manner, the calculation formula for the failure occurrence frequency of each component unit is as follows:

[0016]

[0017] in, is the fault frequency of the k0th component unit; k is the component unit number; j is the operating condition number; i is the fault mode number; k′ is the total number of components; j′ is the total number of operating condition types; i′ is the total number of fault mode types; λ ijk is the failure frequency of the i-th failure mode of the k-th component unit under the j-th operating condition; is the failure frequency of the i-th failure mode of the k0-th component unit under the j-th operating condition; t j is the operating time of the jth operating condition.

[0018] In a possible implementation manner, selecting unit samples from each component unit of the device to be tested according to the failure frequency of each component unit includes:

[0019] According to the failure frequency of each component unit, a component unit sample table is constructed, wherein the number of each component unit in the component unit sample table is proportional to the failure frequency of the component unit;

[0020] A preset sample size of constituent units is randomly selected from the unit sample table as unit samples.

[0021] In a possible implementation manner, the calculation formula for the failure occurrence frequency of each failure mode is as follows:

[0022]

[0023] in, is the fault occurrence frequency of the i0th type of fault mode; j is the operating condition number; i is the fault mode number; j′ is the total number of operating condition types; i′ is the total number of fault mode types; The failure frequency of the i-th failure mode of the k0-th component unit under the j-th operating condition; is the failure frequency of the i0th type of failure mode of the k0th component unit under the jth operating condition; t j is the operating time of the jth operating condition.

[0024] In a possible implementation manner, selecting failure mode samples from each failure mode corresponding to the component unit according to the failure occurrence frequency of each type of failure mode includes:

[0025] According to the failure frequency of each type of failure mode, a failure mode sample table is constructed, wherein the number of each type of failure mode in the failure mode sample table is proportional to the failure frequency of the failure mode;

[0026] A preset sample quantity of failure modes is randomly selected from the failure mode sample table as failure mode samples.

[0027] In a possible implementation manner, the calculation formula for the fault occurrence frequency of each operating condition is as follows:

[0028]

[0029] in, is the fault occurrence frequency under the j0th operating condition; j is the operating condition number; j′ is the total number of operating condition types; is the probability of failure of the i0th type of failure mode of the K0th component unit under the jth operating condition; is the probability of failure of the i0th type of failure mode of the k0th component unit under the j0th operating condition; t j is the operating time of the jth operating condition; is the operating time of the j0th operating condition.

[0030] In a possible implementation manner, selecting operating condition samples from operating conditions corresponding to the failure mode according to the fault occurrence frequency of each operating condition includes:

[0031] According to the fault occurrence frequency of each operating condition, construct an operating condition sample table, wherein the number of each type of operating condition in the operating condition sample table is proportional to the fault occurrence frequency of the operating condition;

[0032] A preset sample quantity of operating conditions is randomly selected from the operating condition sample table as operating condition samples.

[0033] In a possible implementation manner, after combining the unit samples, the failure mode samples, and the operating condition samples into sampling samples, the method further includes:

[0034] Obtaining a feature value set for each operating condition as a first feature value set;

[0035] Obtaining a feature value set for each operating condition in the sample as a second feature value set;

[0036] Determining a sufficiency measure for each operating condition based on a first feature value set and a second feature value set for each operating condition;

[0037] Determine in turn whether the sufficiency measure of each operating condition in the sampled sample is greater than or equal to a preset sufficiency measure threshold;

[0038] When the sufficiency metric of each operating condition in the sampling sample is greater than or equal to a preset sufficiency metric threshold, the sufficiency of the sampling sample meets the preset conditions.

[0039] In a possible implementation, the method further includes:

[0040] In the case where there are operating conditions in the sampled samples whose sufficiency metrics are less than the preset sufficiency metrics threshold, supplementary sampling is performed on the operating conditions whose sufficiency metrics are less than the preset sufficiency metrics threshold so that the sufficiency metrics of the operating conditions after the supplementary sampling are greater than or equal to the preset sufficiency metrics threshold.

[0041] In a possible implementation, the calculation formula of the sufficiency metric is as follows:

[0042]

[0043] Among them, M Aj A is a measure of adequacy; Sj A is the second characteristic value set of the jth operating condition; Uj is the first characteristic value set of the jth operating condition.

[0044] The above-mentioned technical scheme provided by the embodiment of the present application has the following advantages compared with the prior art: the method provided by the embodiment of the present application improves the traditional fault sampling method, adds operating condition information on the basis of the traditional method, corrects the key formulas, improves the sampling process, solves the problem that the operating condition influence is not considered in the traditional test sampling method, realizes sampling under multiple operating conditions of the test test, and improves the accuracy and reliability of the test. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0048] Figure 1 A schematic flow chart of a method for sampling test samples under multiple working conditions provided in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of a process for selecting unit samples provided in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of the steps for selecting a fault mode sample provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of the steps for selecting working condition samples provided in an embodiment of the present application;

[0052] Figure 5 A schematic diagram of the steps of a test sample sampling method under multiple working conditions provided in an embodiment of the present application;

[0053] Figure 6 A schematic diagram of the supplementary sampling process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0056] At present, there are three main methods for sampling test samples: the fault sampling method considering risk, the fault sampling method combining coverage adequacy with risk method, and the fault sampling method based on coverage adequacy.

[0057] The fault sampling method considering risk first needs to extract the equipment parts that need to be injected with faults. If a fixed sample test is used, the proportional stratified sampling method can be used for sample allocation; if a sequential test method with a variable sample size is used, the proportional simple random sampling method can be used. After extracting the equipment parts that need to be injected with faults through the proportional stratified sampling method and the proportional simple random sampling method, it is also necessary to choose what kind of faults to inject into these equipment parts, that is, the choice of failure mode.

[0058] The fault sampling method that combines coverage adequacy with risk methods mainly includes two methods: sample set adequacy optimization and sample set adequacy supplementation. Sample set adequacy optimization: When the sample size n of the test cannot be changed, repeated sampling can be used to generate r groups of sample sets, and their comprehensive adequacy metrics are calculated respectively, and the sample set with the largest value is selected as the final test sample set. Sample set adequacy supplementation: The sample set is supplemented based on the adequacy metric to improve the adequacy of the sample set. If the sample size n of the test can be increased, first determine which values ​​of the characteristics are not covered, and then make targeted sample supplementation selections.

[0059] There are two main options for fault sampling methods based on coverage adequacy: (1) Sample selection without considering the failure rate. When the failure rate is not considered, it can be assumed that the failure rate of each failure mode of the product is the same. In this case, there is no need to determine the sample size, and sampling can be directly performed to establish a sample set that meets the adequacy criterion; (2) Sample selection with failure rate in mind. When the failure rate is taken into account, the failure rate of each failure mode of the product is no longer exactly the same. In this case, the required sample size should be determined first according to the adequacy criterion, and then fault mode sampling should be performed to establish a sample set that meets the separation criterion.

[0060] Working conditions refer to the working conditions of the system during use. Under different working conditions, the system's failure mode set and the failure rate of each failure mode may change. In addition, the structure and function of the system used under different working conditions are also different.

[0061] In order to solve the problem that the fault sampling method that considers risks in the prior art, the fault sampling method that combines coverage sufficiency with risk methods, and the fault sampling method based on coverage sufficiency all do not consider the influence of working conditions on testability tests, and there is a problem that the test results are difficult to accurately reflect the actual testability level of the system. This application provides a test test sample sampling method under multiple working conditions, which considers the influence of working conditions in testability tests and studies sample sampling methods based on different working conditions, which can effectively improve the accuracy of testability test result evaluation.

[0062] Figure 1A flow chart of a method for sampling test samples under multiple working conditions provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method specifically includes:

[0063] S101, obtaining the failure frequency of each component unit of the device to be tested;

[0064] In this embodiment, the device under test is provided with a plurality of component units. First, the failure frequency of each component unit needs to be determined, and then component unit samples are sampled according to the failure frequency of each component unit.

[0065] S102, selecting unit samples from each component unit of the device to be tested according to the failure frequency of each component unit;

[0066] In this embodiment, after the comprehensive relative occurrence frequency of failures of each unit is calculated, the determined sample size n can be distributed to each component unit of the product according to the comprehensive relative occurrence frequency of failures of the component units.

[0067] It should be noted that if the component unit is still divisible, the same method can be used to distribute the sample size of the component unit to its components.

[0068] S103, obtaining the failure occurrence frequency of each failure mode of the component unit;

[0069] In this embodiment, the device under test corresponds to multiple types of failure modes. First, the failure frequency of each failure mode is determined, and then the failure mode sampling is performed according to the failure frequency of each type of failure mode.

[0070] S104, selecting a failure mode sample from each failure mode corresponding to the component unit according to the failure occurrence frequency of each type of failure mode;

[0071] In this embodiment, after the allocation amount of each component unit is determined, it is necessary to allocate the sample amount of the component unit to each failure mode to obtain a failure mode sample.

[0072] S105, obtaining the fault occurrence frequency of each operating condition corresponding to the fault mode;

[0073] In this embodiment, the device under test corresponds to a variety of operating conditions. First, the fault occurrence frequency of each operating condition is determined, and then the operating condition sampling is performed according to the fault occurrence frequency of each operating condition.

[0074] S106, selecting a condition sample from each operating condition corresponding to the failure mode according to the fault occurrence frequency of each operating condition;

[0075] In this embodiment, after the distribution amount of each fault mode is determined, it is necessary to distribute the sample amount of the fault mode to each working condition to obtain the working condition sample.

[0076] S107, combining the unit samples, failure mode samples, and operating condition samples into a sampling sample;

[0077] In this embodiment, the independent sample attributes are integrated to form a comprehensive sampling sample, creating a more representative sampling sample set including unit, failure mode, and operating condition attributes, providing data support for subsequent analysis and research work.

[0078] S108. When the adequacy of the sampling sample meets the preset conditions, the sampling sample is used as the target sample.

[0079] In this embodiment, after the sampling samples are obtained, the adequacy of the sampling samples will be judged. Only when the adequacy of the sampling samples meets the preset conditions, these samples will be used as target samples for subsequent testing experiments.

[0080] like Figure 5 As shown, the sampling method provided in the embodiment of the present application improves the traditional fault sampling method, and adds operating condition information on the basis of the traditional method, including proportional stratified sampling allocation, fault mode selection, fault mode operating condition selection and coverage adequacy supplement algorithm, which solves the problem of not considering the impact of operating conditions in the traditional test sampling method and realizes the sampling method under multiple operating conditions of the test experiment.

[0081] The comprehensive failure rate is the basic formula of the sampling method under multiple working conditions of the test test. Consider the working time proportion, and use the time proportion to weight the failure rate of the failure mode under different working conditions, so as to obtain the comprehensive failure rate of the failure mode, as shown in Formula 1:

[0082]

[0083] Where: m is the total number of working conditions;

[0084] t j is the operating time of the jth operating condition;

[0085] t s is the sum of the operating time of each working condition, that is,

[0086] λ i ′ is the comprehensive failure rate of the i-th failure mode;

[0087] λ ij is the failure rate of the i-th failure mode under the j-th operating condition.

[0088] The theoretical basis for the definition of the comprehensive failure rate is as follows:

[0089] Assume that the equipment has two operating conditions: condition 1 and condition 2. The operating time of each condition is t1 and t2 respectively. Assume that the equipment has only failure mode A. The failure rate under condition 1 is λ a1 , the failure rate under condition 2 is λ a2 , from the relationship between reliability and failure rate, it can be seen that the reliability of the system in the operating stage of working condition 1 is:

[0090]

[0091] The reliability in the operating stage of working condition 2 is:

[0092]

[0093] The equipment's different operating conditions conform to the series model relationship, so the total failure rate of the equipment is:

[0094]

[0095] It can be obtained that the combined failure rate of the equipment under working condition 1 and working condition 2 is:

[0096]

[0097] In an optional solution of the embodiment of the present invention, the calculation formula of the failure occurrence frequency of each component unit is as follows:

[0098]

[0099] in, is the fault frequency of the k0th component unit; k is the component unit number; j is the operating condition number; i is the fault mode number; k′ is the total number of components; j′ is the total number of operating condition types; i′ is the total number of fault mode types; λ ijk is the failure frequency of the i-th failure mode of the k-th component unit under the j-th operating condition; is the failure frequency of the i-th failure mode of the k0-th component unit under the j-th operating condition; t j is the operating time of the jth operating condition.

[0100] In this embodiment, the calculation formula for the failure frequency of each component unit is as follows:

[0101]

[0102] Figure 2 A schematic diagram of a process for selecting unit samples provided in an embodiment of the present application, such as Figure 2 As shown, the method specifically includes:

[0103] S201, constructing a component unit sample table according to the failure frequency of each component unit, wherein the number of each component unit in the component unit sample table is proportional to the failure frequency of the component unit;

[0104] S202: Randomly select constituent units of a preset sample size from the unit sample table as unit samples.

[0105] In this embodiment, a component unit sample table is constructed according to the failure frequency of each component unit, wherein the number of each component unit in the component unit sample table is proportional to the failure frequency of the component unit; and then a preset sample quantity of component units are randomly selected from the unit sample table as unit samples.

[0106] For example, according to the frequency of failure The cumulative range determined by multiplying by 100 is randomly selected from the entire sample using a random number table with a uniform distribution of 00 to 99.

[0107] It should be noted that in the specific sampling process, the cumulative range can be based on the frequency of fault occurrence. Make adjustments.

[0108] For example, if the minimum failure rate is 0.001, then it can be adjusted to the failure frequency The cumulative range determined by multiplying by 1000 is randomly selected from the entire sample using a random number table with a uniform distribution of 000 to 999.

[0109] In an optional solution of the embodiment of the present invention, the calculation formula of the failure occurrence frequency of each failure mode is as follows:

[0110]

[0111] in, is the fault occurrence frequency of the i0th type of fault mode; j is the operating condition number; i is the fault mode number; j′ is the total number of operating condition types; i′ is the total number of fault mode types; is the failure frequency of the i-th failure mode of the k0-th component unit under the j-th operating condition; is the failure frequency of the i0th type of failure mode of the k0th component unit under the jth operating condition; t j is the operating time of the jth operating condition.

[0112] In this embodiment, the calculation method of the failure frequency of each component unit under each failure mode is as follows:

[0113]

[0114] Figure 3 A schematic diagram of the steps for selecting a fault mode sample provided in an embodiment of the present application, such as Figure 3 As shown, the method specifically includes:

[0115] S301, constructing a fault mode sample table according to the fault occurrence frequency of each type of fault mode, wherein the number of each type of fault mode in the fault mode sample table is proportional to the fault occurrence frequency of the fault mode;

[0116] S302 . Randomly select a preset sample quantity of failure modes from the failure mode sample table as failure mode samples.

[0117] In this embodiment, a fault mode sample table is constructed according to the fault occurrence frequency of each type of fault mode, wherein the number of each type of fault mode in the fault mode sample table is proportional to the fault occurrence frequency of the fault mode; and then a preset sample quantity of fault modes is randomly selected from the fault mode sample table as fault mode samples.

[0118] For example, after a component unit is selected, all fault samples of the component unit are sorted according to the comprehensive relative frequency of the fault mode. The cumulative range determined by multiplying by 100 is used to select the fault mode to be injected by random sampling from all samples using a random number table with uniform distribution from 00 to 99.

[0119] It should be noted that in the specific sampling process, the cumulative range can be based on the frequency of fault occurrence. Make adjustments.

[0120] For example, if the minimum failure rate is 0.003, then it can be adjusted to the failure frequency The cumulative range determined by multiplying by 1000 is randomly selected from the entire sample using a random number table with a uniform distribution of 000 to 999.

[0121] In an optional solution of the embodiment of the present invention, the calculation formula of the fault occurrence frequency of each operating condition is as follows:

[0122]

[0123] in, is the fault occurrence frequency under the j0th operating condition; j is the operating condition number; j′ is the total number of operating condition types; is the probability of failure of the i0th type of failure mode of the k0th component unit under the jth operating condition; is the probability of failure of the i0th type of failure mode of the k0th component unit under the j0th operating condition; tj is the operating time of the jth operating condition; is the operating time of the j0th operating condition.

[0124] In this embodiment, the calculation method of the failure occurrence frequency of each component unit in each failure mode under various operating conditions is as follows:

[0125]

[0126] Figure 4 A schematic diagram of the steps for selecting working condition samples provided in the embodiment of the present application, such as Figure 4 As shown, the method specifically includes:

[0127] S401, constructing an operating condition sample table according to the fault occurrence frequency of each operating condition, wherein the number of each type of operating condition in the operating condition sample table is proportional to the fault occurrence frequency of the operating condition;

[0128] S402. Randomly select a preset sample quantity of operating conditions from the operating condition sample table as operating condition samples.

[0129] In this embodiment, an operating condition sample table is constructed based on the fault occurrence frequency of each operating condition, wherein the number of each operating condition in the operating condition sample table is proportional to the fault occurrence frequency of the operating condition; and then a preset sample quantity of operating conditions are randomly selected from the operating condition sample table as condition samples.

[0130] For example, after a component unit and a failure mode are selected, all failure samples of the component unit in the failure mode are sorted according to the comprehensive relative occurrence frequency of the operating conditions. The cumulative range determined by multiplying by 100 is used to select the operating condition to be injected by random sampling from all samples using a random number table with uniform distribution from 00 to 99.

[0131] It should be noted that in the specific sampling process, the cumulative range can be based on the frequency of fault occurrence. Make adjustments.

[0132] For example, if the minimum failure rate is 0.002, then it can be adjusted to the failure frequency The cumulative range determined by multiplying by 1000 is randomly selected from the entire sample using a random number table with a uniform distribution of 000 to 999.

[0133] In an optional solution of the embodiment of the present invention, after combining the unit samples, the fault mode samples, and the operating condition samples into a sampling sample, the method further includes:

[0134] Obtaining a feature value set for each operating condition as a first feature value set;

[0135] Obtaining a feature value set for each operating condition in the sample as a second feature value set;

[0136] Determining a sufficiency measure for each operating condition based on a first feature value set and a second feature value set for each operating condition;

[0137] Determine in turn whether the sufficiency measure of each operating condition in the sampled sample is greater than or equal to a preset sufficiency measure threshold;

[0138] When the sufficiency metric of each operating condition in the sampling sample is greater than or equal to a preset sufficiency metric threshold, the sufficiency of the sampling sample meets the preset conditions.

[0139] In this embodiment, first, a set of feature values ​​under each operating condition before sampling is obtained, and these sets are defined as first feature value sets. Then, a set of feature values ​​under each operating condition in the sampled sample is obtained, and these sets will be defined as second feature value sets. Then, the first feature value set and the second feature value set of each operating condition are compared and analyzed to determine the sufficiency measure of each operating condition. Further, the sufficiency measure of each operating condition in the sampled sample is compared with the sufficiency measure threshold in turn. Only when the sufficiency measure of each operating condition is greater than or equal to the preset sufficiency measure threshold, the sufficiency of the sampled sample is determined to meet the preset conditions.

[0140] In an optional solution of the embodiment of the present invention, the method further includes:

[0141] In the case where there are operating conditions in the sampled samples whose sufficiency metrics are less than the preset sufficiency metrics threshold, supplementary sampling is performed on the operating conditions whose sufficiency metrics are less than the preset sufficiency metrics threshold so that the sufficiency metrics of the operating conditions after the supplementary sampling are greater than or equal to the preset sufficiency metrics threshold.

[0142] In an optional solution of the embodiment of the present invention, the calculation formula of the sufficiency metric is as follows:

[0143]

[0144] Among them, M Aj A is a measure of adequacy; Sj A is the second characteristic value set of the jth operating condition; Uj is the first characteristic value set of the jth operating condition.

[0145] In this embodiment, after the initial sampling is completed, it is determined whether the sample data fully covers all operating conditions. If the condition is met, the sample data is used as the target sample data. If the condition is not met, additional sampling is performed.

[0146] like Figure 6 Specifically, firstly, a characteristic value set corresponding to an operating condition is obtained, and a sample set F is established based on the determined sample size and the risk sampling method based on different operating conditions. S , and determine A based on the mapping relationship S Then, the corresponding working condition sufficiency calculation formula is used to calculate the working condition sufficiency M under the jth working condition. Aj . Working condition sufficiency M Aj The calculation formula is as follows:

[0147]

[0148] Among them, A Sj is the characteristic value set under the jth working condition corresponding to the sample set; |A Sj | is the sample set A Sj The cardinality of Uj is the characteristic value set under the jth working condition; |A Uj | is the sample set A Uj The cardinality of .

[0149] The specific judgment and supplementary sampling methods are as follows:

[0150] Step 1: Determine the elements of the jth working condition based on the product design data: the failure mode set F under the jth working condition Uj , characteristic value set A Uj , mapping relationship P Uj ;

[0151] Step 2: Based on the sample set F established by the risk sampling method based on different working conditions S , and determine A based on the mapping relationship Sj ;

[0152] Step 3: Use the corresponding sufficiency metric calculation formula to calculate the sufficiency metric M under the jth working condition Aj ;

[0153] Step 4: Determine M Aj Is it less than a certain required threshold value? If so, perform additional sampling. If not, determine whether all working conditions have been supplemented with samples. If all working conditions have been supplemented with samples, then end.

[0154] Step 5: Supplementary sampling, specifically using proportional simple random sampling method to supplement a specific failure mode sampling.

[0155] For example, the algorithm input is: sample size is 10; M Aj The required threshold value is 1; the single characteristic is structural failure mode coverage;

[0156] The fault information is shown in Table 1:

[0157] Table 1

[0158]

[0159] Proportional stratified sampling allocation:

[0160] Calculate the comprehensive relative frequency of failures of each unit, and distribute the determined sample size n to each component unit of the product according to the comprehensive relative frequency of failures of the component unit. If the component unit is still divisible, the same method can be used to distribute the sample size of the component unit to its components. The method for calculating the comprehensive relative frequency of failures is shown in Formula 6.

[0161] According to the comprehensive relative frequency of faults C pk The cumulative range determined by multiplying ' by 100 is randomly selected from the entire sample using a random number table with a uniform distribution of 00 to 99.

[0162] Failure mode selection:

[0163] Comprehensive relative frequency The calculation method is shown in Formula 7. Randomly sample all fault samples of the component unit according to the cumulative range determined by multiplying the comprehensive relative occurrence frequency of the fault mode by 100 to select the fault mode to be injected.

[0164] Failure mode condition selection:

[0165] Assuming that a certain fault mode f has been assigned a sample size and has j′ operating conditions, the calculation method for the relative occurrence frequency of the fault mode under the i0th operating condition is as shown in Formula 8.

[0166] Will The cumulative range determined by multiplying by 100 is randomly selected in each working condition using a random number table with a uniform distribution of 00 to 99.

[0167] Supplementary sampling:

[0168] Step 1: Determine the I of the jth working condition based on the product design data Uj =(F Uj ,A Uj ,P Uj ) element: the failure mode set F under the jth working conditionUj , characteristic value set A Uj , mapping relationship P Uj ;

[0169] Step 2: Based on the sample set F established by the risk sampling method based on different working conditions S , and determine A based on the mapping relationship Sj ;

[0170] Step 3: Use the corresponding sufficiency metric calculation formula to calculate the sufficiency metric M under the jth working condition Aj ;

[0171] Step 4: Determine M Aj Is it less than a certain required threshold value? If so, perform additional sampling. If not, determine whether all working conditions have been supplemented with samples. If not, perform additional sampling for the next working condition. If all working conditions have been supplemented with samples, end the sampling.

[0172] Step 5: Supplemental sampling: Use proportional simple random sampling to supplement a specific failure mode sampling.

[0173] The sampling results are shown in Table 2:

[0174] Table 2

[0175] Working conditions Part Name Failure Mode Name Original extraction quantity Supplementary quantity Condition 1 Component 1 F1 0 0 Condition 1 Component 1 F2 0 1 Condition 1 Component 2 F3 2 0 Condition 2 Component 1 F1 0 0 Condition 2 Component 1 F2 2 0 Condition 2 Component 2 F3 6 0

[0176] Results analysis, from the table above, we can see that all components under all working conditions have achieved full coverage of fault sampling, M Aj In both working conditions, the value is 1, which meets the sampling requirements, and the sampling samples are obtained.

[0177] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0178] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for sampling test samples under multiple working conditions, characterized in that: include: Obtain the failure frequency of each component unit of the device to be tested; Select unit samples from each component unit of the device to be tested according to the failure frequency of each component unit; Obtain the failure frequency of each failure mode of the component unit; According to the failure frequency of each type of failure mode, select failure mode samples from each failure mode corresponding to the component unit; Obtain the fault occurrence frequency of each operating condition corresponding to the fault mode; According to the frequency of failure in each operating condition, select operating condition samples from each operating condition corresponding to the failure mode; combining the unit samples, the failure mode samples, and the operating condition samples into a sampling sample; When the adequacy of the sampling sample meets the preset conditions, the sampling sample is used as the target sample.

2. The method according to claim 1, characterized in that The calculation formula for the failure frequency of each component unit is as follows: in, is the fault frequency of the k0th component unit; k is the component unit number; j is the operating condition number; i is the fault mode number; k′ is the total number of components; j′ is the total number of operating condition types; i′ is the total number of fault mode types; λ ijk is the failure frequency of the i-th failure mode of the k-th component unit under the j-th operating condition; is the failure frequency of the i-th failure mode of the k0-th component unit under the j-th operating condition; t j is the operating time of the jth operating condition.

3. The method according to claim 1, characterized in that The selecting unit samples from each component unit of the device to be tested according to the failure frequency of each component unit comprises: According to the failure frequency of each component unit, a component unit sample table is constructed, wherein the number of each component unit in the component unit sample table is proportional to the failure frequency of the component unit; A preset sample size of constituent units is randomly selected from the unit sample table as unit samples.

4. The method according to claim 1, characterized in that The calculation formula for the failure frequency of each failure mode is as follows: in, is the fault occurrence frequency of the i0th type of fault mode; j is the operating condition number; i is the fault mode number; j′ is the total number of operating condition types; i′ is the total number of fault mode types; is the failure frequency of the i-th failure mode of the k0-th component unit under the j-th operating condition; is the failure frequency of the i0th type of failure mode of the k0th component unit under the jth operating condition; t j is the operating time of the jth operating condition.

5. The method according to claim 1, characterized in that The selecting of the failure mode samples from the failure modes corresponding to the component units according to the failure occurrence frequency of each type of failure mode includes: According to the failure frequency of each type of failure mode, a failure mode sample table is constructed, wherein the number of each type of failure mode in the failure mode sample table is proportional to the failure frequency of the failure mode; A preset sample quantity of failure modes is randomly selected from the failure mode sample table as failure mode samples.

6. The method according to claim 1, characterized in that The calculation formula for the fault occurrence frequency of each operating condition is as follows: in, is the fault occurrence frequency under the j0th operating condition; j is the operating condition number; j′ is the total number of operating condition types; is the probability of failure of the i0th type of failure mode of the k0th component unit under the jth operating condition; is the probability of failure of the i0th type of failure mode of the k0th component unit under the j0th operating condition; t j is the operating time of the jth operating condition; t j0 is the operating time of the j0th operating condition.

7. The method according to claim 1, characterized in that The selecting of the operating condition samples from the operating conditions corresponding to the failure mode according to the fault occurrence frequency of each operating condition includes: According to the fault occurrence frequency of each operating condition, construct an operating condition sample table, wherein the number of each type of operating condition in the operating condition sample table is proportional to the fault occurrence frequency of the operating condition; A preset sample quantity of operating conditions is randomly selected from the operating condition sample table as operating condition samples.

8. The method according to claim 1, characterized in that After combining the unit samples, the failure mode samples, and the operating condition samples into sampling samples, the method further includes: Obtaining a feature value set for each operating condition as a first feature value set; Obtaining a feature value set for each operating condition in the sample as a second feature value set; Determining a sufficiency measure for each operating condition based on a first feature value set and a second feature value set for each operating condition; Determine in turn whether the sufficiency measure of each operating condition in the sampled sample is greater than or equal to a preset sufficiency measure threshold; When the sufficiency metric of each operating condition in the sampling sample is greater than or equal to a preset sufficiency metric threshold, the sufficiency of the sampling sample meets the preset conditions.

9. The method according to claim 8, characterized in that The method further comprises: In the case where there are operating conditions in the sampled samples whose sufficiency metrics are less than the preset sufficiency metrics threshold, supplementary sampling is performed on the operating conditions whose sufficiency metrics are less than the preset sufficiency metrics threshold so that the sufficiency metrics of the operating conditions after the supplementary sampling are greater than or equal to the preset sufficiency metrics threshold.

10. The method according to claim 8, characterized in that The calculation formula of the adequacy measure is as follows: Among them, M Aj A is a measure of adequacy; Sj A is the second characteristic value set of the jth operating condition; Uj is the first characteristic value set of the jth operating condition.

Images